{"role": "session_meta", "tools": [{"type": "function", "function": {"name": "clarify", "description": "Ask the user a question when you need clarification, feedback, or a decision before proceeding. Supports two modes:\n\n1. **Multiple choice** — provide up to 4 choices. The user picks one or types their own answer via a 5th 'Other' option.\n2. **Open-ended** — omit choices entirely. The user types a free-form response.\n\nUse this tool when:\n- The task is ambiguous and you need the user to choose an approach\n- You want post-task feedback ('How did that work out?')\n- You want to offer to save a skill or update memory\n- A decision has meaningful trade-offs the user should weigh in on\n\nDo NOT use this tool for simple yes/no confirmation of dangerous commands (the terminal tool handles that). Prefer making a reasonable default choice yourself when the decision is low-stakes.", "parameters": {"type": "object", "properties": {"question": {"type": "string", "description": "The question to present to the user."}, "choices": {"type": "array", "items": {"type": "string"}, "maxItems": 4, "description": "Up to 4 answer choices. Omit this parameter entirely to ask an open-ended question. When provided, the UI automatically appends an 'Other (type your answer)' option."}}, "required": ["question"]}}}, {"type": "function", "function": {"name": "cronjob", "description": "Manage scheduled cron jobs with a single compressed tool.\n\nUse action='create' to schedule a new job from a prompt or one or more skills.\nUse action='list' to inspect jobs.\nUse action='update', 'pause', 'resume', 'remove', or 'run' to manage an existing job.\n\nTo stop a job the user no longer wants: first action='list' to find the job_id, then action='remove' with that job_id. Never guess job IDs — always list first.\n\nJobs run in a fresh session with no current-chat context, so prompts must be self-contained.\nIf skills are provided on create, the future cron run loads those skills in order, then follows the prompt as the task instruction.\nOn update, passing skills=[] clears attached skills.\n\nNOTE: The agent's final response is auto-delivered to the target. Put the primary\nuser-facing content in the final response. Cron jobs run autonomously with no user\npresent — they cannot ask questions or request clarification.\n\nImportant safety rule: cron-run sessions should not recursively schedule more cron jobs.", "parameters": {"type": "object", "properties": {"action": {"type": "string", "description": "One of: create, list, update, pause, resume, remove, run"}, "job_id": {"type": "string", "description": "Required for update/pause/resume/remove/run"}, "prompt": {"type": "string", "description": "For create: the full self-contained prompt. If skills are also provided, this becomes the task instruction paired with those skills."}, "schedule": {"type": "string", "description": "For create/update: '30m', 'every 2h', '0 9 * * *', or ISO timestamp"}, "name": {"type": "string", "description": "Optional human-friendly name"}, "repeat": {"type": "integer", "description": "Optional repeat count. Omit for defaults (once for one-shot, forever for recurring)."}, "deliver": {"type": "string", "description": "Omit this parameter to auto-deliver back to the current chat and topic (recommended). Auto-detection preserves thread/topic context. Only set explicitly when the user asks to deliver somewhere OTHER than the current conversation. Values: 'origin' (same as omitting), 'local' (no delivery, save only), or platform:chat_id:thread_id for a specific destination. Examples: 'telegram:-1001234567890:17585', 'discord:#engineering', 'sms:+15551234567'. WARNING: 'platform:chat_id' without :thread_id loses topic targeting."}, "skills": {"type": "array", "items": {"type": "string"}, "description": "Optional ordered list of skill names to load before executing the cron prompt. On update, pass an empty array to clear attached skills."}, "model": {"type": "object", "description": "Optional per-job model override. If provider is omitted, the current main provider is pinned at creation time so the job stays stable.", "properties": {"provider": {"type": "string", "description": "Provider name (e.g. 'openrouter', 'anthropic', or 'custom:<name>' for a provider defined in custom_providers config — always include the ':<name>' suffix, never pass the bare 'custom'). Omit to use and pin the current provider."}, "model": {"type": "string", "description": "Model name (e.g. 'anthropic/claude-sonnet-4', 'claude-sonnet-4')"}}, "required": ["model"]}, "script": {"type": "string", "description": "Optional path to a script that runs each tick. In the default mode its stdout is injected into the agent's prompt as context (data-collection / change-detection pattern). With no_agent=True, the script IS the job and its stdout is delivered verbatim (classic watchdog pattern). Relative paths resolve under ~/.hermes/scripts/. ``.sh``/``.bash`` extensions run via bash, everything else via Python. On update, pass empty string to clear."}, "no_agent": {"type": "boolean", "default": false, "description": "Default: False (LLM-driven job — the agent runs the prompt each tick). Set True to skip the LLM entirely: the scheduler just runs ``script`` on schedule and delivers its stdout verbatim. No tokens, no agent loop, no model override honoured. \n\nREQUIREMENTS when True: ``script`` MUST be set (``prompt`` and ``skills`` are ignored). \n\nDELIVERY SEMANTICS when True: (a) non-empty stdout is sent verbatim as the message; (b) EMPTY stdout means SILENT — nothing is sent to the user and they won't see anything happened, so design your script to stay quiet when there's nothing to report (the watchdog pattern); (c) non-zero exit / timeout sends an error alert so a broken watchdog can't fail silently. \n\nWHEN TO USE True: recurring script-only pings where the script itself produces the exact message text (memory/disk/GPU watchdogs, threshold alerts, heartbeats, CI notifications, API pollers with a fixed output shape). WHEN TO USE False (default): anything that needs reasoning — summarize a feed, draft a daily briefing, pick interesting items, rephrase data for a human, follow conditional logic based on content."}, "context_from": {"type": "array", "items": {"type": "string"}, "description": "Optional job ID or list of job IDs whose most recent completed output is injected into the prompt as context before each run. Use this to chain cron jobs: job A collects data, job B processes it. Each entry must be a valid job ID (from cronjob action='list'). Note: injects the most recent completed output — does not wait for upstream jobs running in the same tick. On update, pass an empty array to clear."}, "enabled_toolsets": {"type": "array", "items": {"type": "string"}, "description": "Optional list of toolset names to restrict the job's agent to (e.g. [\"web\", \"terminal\", \"file\", \"delegation\"]). When set, only tools from these toolsets are loaded, significantly reducing input token overhead. When omitted, all default tools are loaded. Infer from the job's prompt — e.g. use \"web\" if it calls web_search, \"terminal\" if it runs scripts, \"file\" if it reads files, \"delegation\" if it calls delegate_task. On update, pass an empty array to clear."}, "workdir": {"type": "string", "description": "Optional absolute path to run the job from. When set, AGENTS.md / CLAUDE.md / .cursorrules from that directory are injected into the system prompt, and the terminal/file/code_exec tools use it as their working directory — useful for running a job inside a specific project repo. Must be an absolute path that exists. When unset (default), preserves the original behaviour: no project context files, tools use the scheduler's cwd. On update, pass an empty string to clear. Jobs with workdir run sequentially (not parallel) to keep per-job directories isolated."}}, "required": ["action"]}}}, {"type": "function", "function": {"name": "delegate_task", "description": "Spawn one or more subagents to work on tasks in isolated contexts. Each subagent gets its own conversation, terminal session, and toolset. Only the final summary is returned -- intermediate tool results never enter your context window.\n\nTWO MODES (one of 'goal' or 'tasks' is required):\n1. Single task: provide 'goal' (+ optional context, toolsets)\n2. Batch (parallel): provide 'tasks' array with up to delegation.max_concurrent_children items (default 3, configurable via config.yaml, no hard ceiling). All run concurrently and results are returned together. Nested delegation requires role='orchestrator' and delegation.max_spawn_depth >= 2.\n\nWHEN TO USE delegate_task:\n- Reasoning-heavy subtasks (debugging, code review, research synthesis)\n- Tasks that would flood your context with intermediate data\n- Parallel independent workstreams (research A and B simultaneously)\n\nWHEN NOT TO USE (use these instead):\n- Mechanical multi-step work with no reasoning needed -> use execute_code\n- Single tool call -> just call the tool directly\n- Tasks needing user interaction -> subagents cannot use clarify\n- Durable long-running work that must outlive the current turn -> use cronjob (action='create') or terminal(background=True, notify_on_complete=True) instead. delegate_task runs SYNCHRONOUSLY inside the parent turn: if the parent is interrupted (user sends a new message, /stop, /new) the child is cancelled with status='interrupted' and its work is discarded. Children cannot continue in the background.\n\nIMPORTANT:\n- Subagents have NO memory of your conversation. Pass all relevant info (file paths, error messages, constraints) via the 'context' field.\n- If the user is writing in a non-English language, or asked for output in a specific language / tone / style, say so in 'context' (e.g. \"respond in Chinese\", \"return output in Japanese\"). Otherwise subagents default to English and their summaries will contaminate your final reply with the wrong language.\n- Subagent summaries are SELF-REPORTS, not verified facts. A subagent that claims \"uploaded successfully\" or \"file written\" may be wrong. For operations with external side-effects (HTTP POST/PUT, remote writes, file creation at shared paths, publishing), require the subagent to return a verifiable handle (URL, ID, absolute path, HTTP status) and verify it yourself — fetch the URL, stat the file, read back the content — before telling the user the operation succeeded.\n- Leaf subagents (role='leaf', the default) CANNOT call: delegate_task, clarify, memory, send_message, execute_code.\n- Orchestrator subagents (role='orchestrator') retain delegate_task so they can spawn their own workers, but still cannot use clarify, memory, send_message, or execute_code. Orchestrators are bounded by delegation.max_spawn_depth (default 2) and can be disabled globally via delegation.orchestrator_enabled=false.\n- Each subagent gets its own terminal session (separate working directory and state).\n- Results are always returned as an array, one entry per task.", "parameters": {"type": "object", "properties": {"goal": {"type": "string", "description": "What the subagent should accomplish. Be specific and self-contained -- the subagent knows nothing about your conversation history."}, "context": {"type": "string", "description": "Background information the subagent needs: file paths, error messages, project structure, constraints. The more specific you are, the better the subagent performs."}, "toolsets": {"type": "array", "items": {"type": "string"}, "description": "Toolsets to enable for this subagent. Default: inherits your enabled toolsets. Available toolsets: 'browser', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'kanban', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'video', 'vision', 'web', 'yuanbao'. Common patterns: ['terminal', 'file'] for code work, ['web'] for research, ['browser'] for web interaction, ['terminal', 'file', 'web'] for full-stack tasks."}, "tasks": {"type": "array", "items": {"type": "object", "properties": {"goal": {"type": "string", "description": "Task goal"}, "context": {"type": "string", "description": "Task-specific context"}, "toolsets": {"type": "array", "items": {"type": "string"}, "description": "Toolsets for this specific task. Available: 'browser', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'kanban', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'video', 'vision', 'web', 'yuanbao'. Use 'web' for network access, 'terminal' for shell, 'browser' for web interaction."}, "acp_command": {"type": "string", "description": "Per-task ACP command override (e.g. 'claude'). Overrides the top-level acp_command for this task only."}, "acp_args": {"type": "array", "items": {"type": "string"}, "description": "Per-task ACP args override."}, "role": {"type": "string", "enum": ["leaf", "orchestrator"], "description": "Per-task role override. See top-level 'role' for semantics."}}, "required": ["goal"]}, "description": "Batch mode: tasks to run in parallel (limit configurable via delegation.max_concurrent_children, default 3). Each gets its own subagent with isolated context and terminal session. When provided, top-level goal/context/toolsets are ignored."}, "role": {"type": "string", "enum": ["leaf", "orchestrator"], "description": "Role of the child agent. 'leaf' (default) = focused worker, cannot delegate further. 'orchestrator' = can use delegate_task to spawn its own workers. Requires delegation.max_spawn_depth >= 2 in config; ignored (treated as 'leaf') when the child would exceed max_spawn_depth or when delegation.orchestrator_enabled=false."}, "acp_command": {"type": "string", "description": "Override ACP command for child agents (e.g. 'claude', 'copilot'). When set, children use ACP subprocess transport instead of inheriting the parent's transport. Enables spawning Claude Code (claude --acp --stdio) or other ACP-capable agents from any parent, including Discord/Telegram/CLI."}, "acp_args": {"type": "array", "items": {"type": "string"}, "description": "Arguments for the ACP command (default: ['--acp', '--stdio']). Only used when acp_command is set. Example: ['--acp', '--stdio', '--model', 'claude-opus-4-6']"}}}}}, {"type": "function", "function": {"name": "execute_code", "description": "Run a Python script that can call Hermes tools programmatically. Use this when you need 3+ tool calls with processing logic between them, need to filter/reduce large tool outputs before they enter your context, need conditional branching (if X then Y else Z), or need to loop (fetch N pages, process N files, retry on failure).\n\nUse normal tool calls instead when: single tool call with no processing, you need to see the full result and apply complex reasoning, or the task requires interactive user input.\n\nAvailable via `from hermes_tools import ...`:\n\n  read_file(path: str, offset: int = 1, limit: int = 500) -> dict\n    Lines are 1-indexed. Returns {\"content\": \"...\", \"total_lines\": N}\n  write_file(path: str, content: str) -> dict\n    Always overwrites the entire file.\n  search_files(pattern: str, target=\"content\", path=\".\", file_glob=None, limit=50) -> dict\n    target: \"content\" (search inside files) or \"files\" (find files by name). Returns {\"matches\": [...]}\n  patch(path: str, old_string: str, new_string: str, replace_all: bool = False) -> dict\n    Replaces old_string with new_string in the file.\n  terminal(command: str, timeout=None, workdir=None) -> dict\n    Foreground only (no background/pty). Returns {\"output\": \"...\", \"exit_code\": N}\n\nLimits: 5-minute timeout, 50KB stdout cap, max 50 tool calls per script. terminal() is foreground-only (no background or pty).\n\nScripts run in the session's working directory with the active venv's python, so project deps (pandas, etc.) and relative paths work like in terminal().\n\nPrint your final result to stdout. Use Python stdlib (json, re, math, csv, datetime, collections, etc.) for processing between tool calls.\n\nAlso available (no import needed — built into hermes_tools):\n  json_parse(text: str) — json.loads with strict=False; use for terminal() output with control chars\n  shell_quote(s: str) — shlex.quote(); use when interpolating dynamic strings into shell commands\n  retry(fn, max_attempts=3, delay=2) — retry with exponential backoff for transient failures", "parameters": {"type": "object", "properties": {"code": {"type": "string", "description": "Python code to execute. Import tools with `from hermes_tools import terminal, ...` and print your final result to stdout."}}, "required": ["code"]}}}, {"type": "function", "function": {"name": "memory", "description": "Save durable information to persistent memory that survives across sessions. Memory is injected into future turns, so keep it compact and focused on facts that will still matter later.\n\nWHEN TO SAVE (do this proactively, don't wait to be asked):\n- User corrects you or says 'remember this' / 'don't do that again'\n- User shares a preference, habit, or personal detail (name, role, timezone, coding style)\n- You discover something about the environment (OS, installed tools, project structure)\n- You learn a convention, API quirk, or workflow specific to this user's setup\n- You identify a stable fact that will be useful again in future sessions\n\nPRIORITY: User preferences and corrections > environment facts > procedural knowledge. The most valuable memory prevents the user from having to repeat themselves.\n\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts.\nIf you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\n\nTWO TARGETS:\n- 'user': who the user is -- name, role, preferences, communication style, pet peeves\n- 'memory': your notes -- environment facts, project conventions, tool quirks, lessons learned\n\nACTIONS: add (new entry), replace (update existing -- old_text identifies it), remove (delete -- old_text identifies it).\n\nSKIP: trivial/obvious info, things easily re-discovered, raw data dumps, and temporary task state.", "parameters": {"type": "object", "properties": {"action": {"type": "string", "enum": ["add", "replace", "remove"], "description": "The action to perform."}, "target": {"type": "string", "enum": ["memory", "user"], "description": "Which memory store: 'memory' for personal notes, 'user' for user profile."}, "content": {"type": "string", "description": "The entry content. Required for 'add' and 'replace'."}, "old_text": {"type": "string", "description": "Short unique substring identifying the entry to replace or remove."}}, "required": ["action", "target"]}}}, {"type": "function", "function": {"name": "patch", "description": "Targeted find-and-replace edits in files. Use this instead of sed/awk in terminal. Uses fuzzy matching (9 strategies) so minor whitespace/indentation differences won't break it. Returns a unified diff. Auto-runs syntax checks after editing.\n\nReplace mode (default): find a unique string and replace it.\nPatch mode: apply V4A multi-file patches for bulk changes.", "parameters": {"type": "object", "properties": {"mode": {"type": "string", "enum": ["replace", "patch"], "description": "Edit mode: 'replace' for targeted find-and-replace, 'patch' for V4A multi-file patches", "default": "replace"}, "path": {"type": "string", "description": "File path to edit (required for 'replace' mode)"}, "old_string": {"type": "string", "description": "Text to find in the file (required for 'replace' mode). Must be unique in the file unless replace_all=true. Include enough surrounding context to ensure uniqueness."}, "new_string": {"type": "string", "description": "Replacement text (required for 'replace' mode). Can be empty string to delete the matched text."}, "replace_all": {"type": "boolean", "description": "Replace all occurrences instead of requiring a unique match (default: false)", "default": false}, "patch": {"type": "string", "description": "V4A format patch content (required for 'patch' mode). Format:\n*** Begin Patch\n*** Update File: path/to/file\n@@ context hint @@\n context line\n-removed line\n+added line\n*** End Patch"}}, "required": ["mode"]}}}, {"type": "function", "function": {"name": "process", "description": "Manage background processes started with terminal(background=true). Actions: 'list' (show all), 'poll' (check status + new output), 'log' (full output with pagination), 'wait' (block until done or timeout), 'kill' (terminate), 'write' (send raw stdin data without newline), 'submit' (send data + Enter, for answering prompts), 'close' (close stdin/send EOF).", "parameters": {"type": "object", "properties": {"action": {"type": "string", "enum": ["list", "poll", "log", "wait", "kill", "write", "submit", "close"], "description": "Action to perform on background processes"}, "session_id": {"type": "string", "description": "Process session ID (from terminal background output). Required for all actions except 'list'."}, "data": {"type": "string", "description": "Text to send to process stdin (for 'write' and 'submit' actions)"}, "timeout": {"type": "integer", "description": "Max seconds to block for 'wait' action. Returns partial output on timeout.", "minimum": 1}, "offset": {"type": "integer", "description": "Line offset for 'log' action (default: last 200 lines)"}, "limit": {"type": "integer", "description": "Max lines to return for 'log' action", "minimum": 1}}, "required": ["action"]}}}, {"type": "function", "function": {"name": "read_file", "description": "Read a text file with line numbers and pagination. Use this instead of cat/head/tail in terminal. Output format: 'LINE_NUM|CONTENT'. Suggests similar filenames if not found. Use offset and limit for large files. Reads exceeding ~100K characters are rejected; use offset and limit to read specific sections of large files. NOTE: Cannot read images or binary files — use vision_analyze for images.", "parameters": {"type": "object", "properties": {"path": {"type": "string", "description": "Path to the file to read (absolute, relative, or ~/path)"}, "offset": {"type": "integer", "description": "Line number to start reading from (1-indexed, default: 1)", "default": 1, "minimum": 1}, "limit": {"type": "integer", "description": "Maximum number of lines to read (default: 500, max: 2000)", "default": 500, "maximum": 2000}}, "required": ["path"]}}}, {"type": "function", "function": {"name": "search_files", "description": "Search file contents or find files by name. Use this instead of grep/rg/find/ls in terminal. Ripgrep-backed, faster than shell equivalents.\n\nContent search (target='content'): Regex search inside files. Output modes: full matches with line numbers, file paths only, or match counts.\n\nFile search (target='files'): Find files by glob pattern (e.g., '*.py', '*config*'). Also use this instead of ls — results sorted by modification time.", "parameters": {"type": "object", "properties": {"pattern": {"type": "string", "description": "Regex pattern for content search, or glob pattern (e.g., '*.py') for file search"}, "target": {"type": "string", "enum": ["content", "files"], "description": "'content' searches inside file contents, 'files' searches for files by name", "default": "content"}, "path": {"type": "string", "description": "Directory or file to search in (default: current working directory)", "default": "."}, "file_glob": {"type": "string", "description": "Filter files by pattern in grep mode (e.g., '*.py' to only search Python files)"}, "limit": {"type": "integer", "description": "Maximum number of results to return (default: 50)", "default": 50}, "offset": {"type": "integer", "description": "Skip first N results for pagination (default: 0)", "default": 0}, "output_mode": {"type": "string", "enum": ["content", "files_only", "count"], "description": "Output format for grep mode: 'content' shows matching lines with line numbers, 'files_only' lists file paths, 'count' shows match counts per file", "default": "content"}, "context": {"type": "integer", "description": "Number of context lines before and after each match (grep mode only)", "default": 0}}, "required": ["pattern"]}}}, {"type": "function", "function": {"name": "send_message", "description": "Send a message to a connected messaging platform, or list available targets.\n\nIMPORTANT: When the user asks to send to a specific channel or person (not just a bare platform name), call send_message(action='list') FIRST to see available targets, then send to the correct one.\nIf the user just says a platform name like 'send to telegram', send directly to the home channel without listing first.", "parameters": {"type": "object", "properties": {"action": {"type": "string", "enum": ["send", "list"], "description": "Action to perform. 'send' (default) sends a message. 'list' returns all available channels/contacts across connected platforms."}, "target": {"type": "string", "description": "Delivery target. Format: 'platform' (uses home channel), 'platform:#channel-name', 'platform:chat_id', or 'platform:chat_id:thread_id' for Telegram topics and Discord threads. Examples: 'telegram', 'telegram:-1001234567890:17585', 'discord:999888777:555444333', 'discord:#bot-home', 'slack:#engineering', 'signal:+155****4567', 'matrix:!roomid:server.org', 'matrix:@user:server.org', 'yuanbao:direct:<account_id>' (DM), 'yuanbao:group:<group_code>' (group chat)"}, "message": {"type": "string", "description": "The message text to send. To send an image or file, include MEDIA:<local_path> (e.g. 'MEDIA:/tmp/hermes/cache/img_xxx.jpg') in the message — the platform will deliver it as a native media attachment."}}}}}, {"type": "function", "function": {"name": "session_search", "description": "Search your long-term memory of past conversations, or browse recent sessions. This is your recall -- every past session is searchable, and this tool summarizes what happened.\n\nTWO MODES:\n1. Recent sessions (no query): Call with no arguments to see what was worked on recently. Returns titles, previews, and timestamps. Zero LLM cost, instant. Start here when the user asks what were we working on or what did we do recently.\n2. Keyword search (with query): Search for specific topics across all past sessions. Returns LLM-generated summaries of matching sessions.\n\nUSE THIS PROACTIVELY when:\n- The user says 'we did this before', 'remember when', 'last time', 'as I mentioned'\n- The user asks about a topic you worked on before but don't have in current context\n- The user references a project, person, or concept that seems familiar but isn't in memory\n- You want to check if you've solved a similar problem before\n- The user asks 'what did we do about X?' or 'how did we fix Y?'\n\nDon't hesitate to search when it is actually cross-session -- it's fast and cheap. Better to search and confirm than to guess or ask the user to repeat themselves.\n\nSearch syntax: keywords joined with OR for broad recall (elevenlabs OR baseten OR funding), phrases for exact match (\"docker networking\"), boolean (python NOT java), prefix (deploy*). IMPORTANT: Use OR between keywords for best results — FTS5 defaults to AND which misses sessions that only mention some terms. If a broad OR query returns nothing, try individual keyword searches in parallel. Returns summaries of the top matching sessions.", "parameters": {"type": "object", "properties": {"query": {"type": "string", "description": "Search query — keywords, phrases, or boolean expressions to find in past sessions. Omit this parameter entirely to browse recent sessions instead (returns titles, previews, timestamps with no LLM cost)."}, "role_filter": {"type": "string", "description": "Optional: only search messages from specific roles (comma-separated). E.g. 'user,assistant' to skip tool outputs."}, "limit": {"type": "integer", "description": "Max sessions to summarize (default: 3, max: 5).", "default": 3}}}}}, {"type": "function", "function": {"name": "skill_manage", "description": "Manage skills (create, update, delete). Skills are your procedural memory — reusable approaches for recurring task types. New skills go to ~/.hermes/skills/; existing skills can be modified wherever they live.\n\nActions: create (full SKILL.md + optional category), patch (old_string/new_string — preferred for fixes), edit (full SKILL.md rewrite — major overhauls only), delete, write_file, remove_file.\n\nOn delete, pass `absorbed_into=<umbrella>` when you're merging this skill's content into another one, or `absorbed_into=\"\"` when you're pruning it with no forwarding target. This lets the curator tell consolidation from pruning without guessing, so downstream consumers (cron jobs that reference the old skill name, etc.) get updated correctly. The target you name in `absorbed_into` must already exist — create/patch the umbrella first, then delete.\n\nCreate when: complex task succeeded (5+ calls), errors overcome, user-corrected approach worked, non-trivial workflow discovered, or user asks you to remember a procedure.\nUpdate when: instructions stale/wrong, OS-specific failures, missing steps or pitfalls found during use. If you used a skill and hit issues not covered by it, patch it immediately.\n\nAfter difficult/iterative tasks, offer to save as a skill. Skip for simple one-offs. Confirm with user before creating/deleting.\n\nGood skills: trigger conditions, numbered steps with exact commands, pitfalls section, verification steps. Use skill_view() to see format examples.\n\nPinned skills are protected from deletion only — skill_manage(action='delete') will refuse with a message pointing the user to `hermes curator unpin <name>`. Patches and edits go through on pinned skills so you can still improve them as pitfalls come up; pin only guards against irrecoverable loss.", "parameters": {"type": "object", "properties": {"action": {"type": "string", "enum": ["create", "patch", "edit", "delete", "write_file", "remove_file"], "description": "The action to perform."}, "name": {"type": "string", "description": "Skill name (lowercase, hyphens/underscores, max 64 chars). Must match an existing skill for patch/edit/delete/write_file/remove_file."}, "content": {"type": "string", "description": "Full SKILL.md content (YAML frontmatter + markdown body). Required for 'create' and 'edit'. For 'edit', read the skill first with skill_view() and provide the complete updated text."}, "old_string": {"type": "string", "description": "Text to find in the file (required for 'patch'). Must be unique unless replace_all=true. Include enough surrounding context to ensure uniqueness."}, "new_string": {"type": "string", "description": "Replacement text (required for 'patch'). Can be empty string to delete the matched text."}, "replace_all": {"type": "boolean", "description": "For 'patch': replace all occurrences instead of requiring a unique match (default: false)."}, "category": {"type": "string", "description": "Optional category/domain for organizing the skill (e.g., 'devops', 'data-science', 'mlops'). Creates a subdirectory grouping. Only used with 'create'."}, "file_path": {"type": "string", "description": "Path to a supporting file within the skill directory. For 'write_file'/'remove_file': required, must be under references/, templates/, scripts/, or assets/. For 'patch': optional, defaults to SKILL.md if omitted."}, "file_content": {"type": "string", "description": "Content for the file. Required for 'write_file'."}, "absorbed_into": {"type": "string", "description": "For 'delete' only — declares intent so the curator can tell consolidation from pruning without guessing. Pass the umbrella skill name when this skill's content was merged into another (the target must already exist). Pass an empty string when the skill is truly stale and being pruned with no forwarding target. Omitting the arg on delete is supported for backward compatibility but downstream tooling (e.g. cron-job skill reference rewriting) will have to guess at intent."}}, "required": ["action", "name"]}}}, {"type": "function", "function": {"name": "skill_view", "description": "Skills allow for loading information about specific tasks and workflows, as well as scripts and templates. Load a skill's full content or access its linked files (references, templates, scripts). First call returns SKILL.md content plus a 'linked_files' dict showing available references/templates/scripts. To access those, call again with file_path parameter.", "parameters": {"type": "object", "properties": {"name": {"type": "string", "description": "The skill name (use skills_list to see available skills). For plugin-provided skills, use the qualified form 'plugin:skill' (e.g. 'superpowers:writing-plans')."}, "file_path": {"type": "string", "description": "OPTIONAL: Path to a linked file within the skill (e.g., 'references/api.md', 'templates/config.yaml', 'scripts/validate.py'). Omit to get the main SKILL.md content."}}, "required": ["name"]}}}, {"type": "function", "function": {"name": "skills_list", "description": "List available skills (name + description). Use skill_view(name) to load full content.", "parameters": {"type": "object", "properties": {"category": {"type": "string", "description": "Optional category filter to narrow results"}}}}}, {"type": "function", "function": {"name": "terminal", "description": "Execute shell commands on a Linux environment. Filesystem usually persists between calls.\n\nDo NOT use cat/head/tail to read files — use read_file instead.\nDo NOT use grep/rg/find to search — use search_files instead.\nDo NOT use ls to list directories — use search_files(target='files') instead.\nDo NOT use sed/awk to edit files — use patch instead.\nDo NOT use echo/cat heredoc to create files — use write_file instead.\nReserve terminal for: builds, installs, git, processes, scripts, network, package managers, and anything that needs a shell.\n\nForeground (default): Commands return INSTANTLY when done, even if the timeout is high. Set timeout=300 for long builds/scripts — you'll still get the result in seconds if it's fast. Prefer foreground for short commands.\nBackground: Set background=true to get a session_id. Two patterns:\n  (1) Long-lived processes that never exit (servers, watchers).\n  (2) Long-running tasks with notify_on_complete=true — you can keep working on other things and the system auto-notifies you when the task finishes. Great for test suites, builds, deployments, or anything that takes more than a minute.\nFor servers/watchers, do NOT use shell-level background wrappers (nohup/disown/setsid/trailing '&') in foreground mode. Use background=true so Hermes can track lifecycle and output.\nAfter starting a server, verify readiness with a health check or log signal, then run tests in a separate terminal() call. Avoid blind sleep loops.\nUse process(action=\"poll\") for progress checks, process(action=\"wait\") to block until done.\nWorking directory: Use 'workdir' for per-command cwd.\nPTY mode: Set pty=true for interactive CLI tools (Codex, Claude Code, Python REPL).\n\nDo NOT use vim/nano/interactive tools without pty=true — they hang without a pseudo-terminal. Pipe git output to cat if it might page.\n", "parameters": {"type": "object", "properties": {"command": {"type": "string", "description": "The command to execute on the VM"}, "background": {"type": "boolean", "description": "Run the command in the background. Two patterns: (1) Long-lived processes that never exit (servers, watchers). (2) Long-running tasks paired with notify_on_complete=true — you can keep working and get notified when the task finishes. For short commands, prefer foreground with a generous timeout instead.", "default": false}, "timeout": {"type": "integer", "description": "Max seconds to wait (default: 180, foreground max: 600). Returns INSTANTLY when command finishes — set high for long tasks, you won't wait unnecessarily. Foreground timeout above 600s is rejected; use background=true for longer commands.", "minimum": 1}, "workdir": {"type": "string", "description": "Working directory for this command (absolute path). Defaults to the session working directory."}, "pty": {"type": "boolean", "description": "Run in pseudo-terminal (PTY) mode for interactive CLI tools like Codex, Claude Code, or Python REPL. Only works with local and SSH backends. Default: false.", "default": false}, "notify_on_complete": {"type": "boolean", "description": "When true (and background=true), you'll be automatically notified exactly once when the process finishes. **This is the right choice for almost every long-running task** — tests, builds, deployments, multi-item batch jobs, anything that takes over a minute and has a defined end. Use this and keep working on other things; the system notifies you on exit. MUTUALLY EXCLUSIVE with watch_patterns — when both are set, watch_patterns is dropped.", "default": false}, "watch_patterns": {"type": "array", "items": {"type": "string"}, "description": "Strings to watch for in background process output. HARD RATE LIMIT: at most 1 notification per 15 seconds per process — matches arriving inside the cooldown are dropped. After 3 consecutive 15-second windows with dropped matches, watch_patterns is automatically disabled for that process and promoted to notify_on_complete behavior (one notification on exit, no more mid-process spam). USE ONLY for truly rare, one-shot mid-process signals on LONG-LIVED processes that will never exit on their own — e.g. ['Application startup complete'] on a server so you know when to hit its endpoint, or ['migration done'] on a daemon. DO NOT use for: (1) end-of-run markers like 'DONE'/'PASS' — use notify_on_complete instead; (2) error patterns like 'ERROR'/'Traceback' in loops or multi-item batch jobs — they fire on every iteration and you'll hit the strike limit fast; (3) anything you'd ever combine with notify_on_complete. When in doubt, choose notify_on_complete. MUTUALLY EXCLUSIVE with notify_on_complete — set one, not both."}}, "required": ["command"]}}}, {"type": "function", "function": {"name": "text_to_speech", "description": "Convert text to speech audio. Returns a MEDIA: path that the platform delivers as native audio. Compatible providers render as a voice bubble on Telegram; otherwise audio is sent as a regular attachment. In CLI mode, saves to ~/voice-memos/. Voice and provider are user-configured (built-in providers like edge/openai or custom command providers under tts.providers.<name>), not model-selected.", "parameters": {"type": "object", "properties": {"text": {"type": "string", "description": "The text to convert to speech. Provider-specific character caps apply and are enforced automatically (OpenAI 4096, xAI 15000, MiniMax 10000, ElevenLabs 5k-40k depending on model); over-long input is truncated."}, "output_path": {"type": "string", "description": "Optional custom file path to save the audio. Defaults to ~/.hermes/audio_cache/<timestamp>.mp3"}}, "required": ["text"]}}}, {"type": "function", "function": {"name": "todo", "description": "Manage your task list for the current session. Use for complex tasks with 3+ steps or when the user provides multiple tasks. Call with no parameters to read the current list.\n\nWriting:\n- Provide 'todos' array to create/update items\n- merge=false (default): replace the entire list with a fresh plan\n- merge=true: update existing items by id, add any new ones\n\nEach item: {id: string, content: string, status: pending|in_progress|completed|cancelled}\nList order is priority. Only ONE item in_progress at a time.\nMark items completed immediately when done. If something fails, cancel it and add a revised item.\n\nAlways returns the full current list.", "parameters": {"type": "object", "properties": {"todos": {"type": "array", "description": "Task items to write. Omit to read current list.", "items": {"type": "object", "properties": {"id": {"type": "string", "description": "Unique item identifier"}, "content": {"type": "string", "description": "Task description"}, "status": {"type": "string", "enum": ["pending", "in_progress", "completed", "cancelled"], "description": "Current status"}}, "required": ["id", "content", "status"]}}, "merge": {"type": "boolean", "description": "true: update existing items by id, add new ones. false (default): replace the entire list.", "default": false}}}}}, {"type": "function", "function": {"name": "vision_analyze", "description": "Inspect an image from a URL, file path, or tool output when you need closer detail than what's visible in the conversation. If the user's image is already attached to the conversation and you can see it, just answer directly — only call this tool for images referenced by URL/path, images returned inside other tool results (browser screenshots, search thumbnails), or when you need a deeper look at a specific region the main model's vision may have missed.", "parameters": {"type": "object", "properties": {"image_url": {"type": "string", "description": "Image URL (http/https) or local file path to analyze."}, "question": {"type": "string", "description": "Your specific question or request about the image to resolve. The AI will automatically provide a complete image description AND answer your specific question."}}, "required": ["image_url", "question"]}}}, {"type": "function", "function": {"name": "write_file", "description": "Write content to a file, completely replacing existing content. Use this instead of echo/cat heredoc in terminal. Creates parent directories automatically. OVERWRITES the entire file — use 'patch' for targeted edits. Auto-runs syntax checks on .py/.json/.yaml/.toml and other linted languages; only NEW errors introduced by this write are surfaced (pre-existing errors are filtered out).", "parameters": {"type": "object", "properties": {"path": {"type": "string", "description": "Path to the file to write (will be created if it doesn't exist, overwritten if it does)"}, "content": {"type": "string", "description": "Complete content to write to the file"}}, "required": ["path", "content"]}}}], "model": "kimi-k2.6", "platform": "telegram", "timestamp": "2026-05-13T08:01:04.776775"}
{"role": "user", "content": "Guten Morgen Kiwi", "timestamp": "2026-05-13T08:01:04.776775"}
{"role": "assistant", "content": "Guten Morgen, Ahmed! Was steht heute auf dem Plan? Ein neues 3D-Projekt oder was anderes?", "reasoning": "The user greeted me with \"Guten Morgen Kiwi\". According to the user profile, the user's name is Ahmed Zeyd Aytac, and he refers to me as 'Kiwi'. So he is greeting me (Kiwi) in German.\n\nI should respond in German since he used German, acknowledging the greeting. It's a fresh conversation (daily reset), so I should be friendly but not overdo it.\n\nKey facts from memory:\n- User is Ahmed Zeyd Aytac\n- He calls me Kiwi\n- Location: Wien (Vienna), Austria\n- Prefers 3D design/CAD projects when asked \"what should we build?\"\n- Prefers concise technical CAD reports\n- Doesn't want print recommendations\n- Doesn't want end-of-session skill reviews\n- \"Stop saving\" means stop the skill-update workflow immediately\n\nResponse should be simple: Good morning back, maybe ask what we're working on today or if he has a project in mind. Keep it concise.\n\nIn German: \"Guten Morgen, Ahmed! Was steht heute auf dem Plan? Ein neues 3D-Projekt oder was anderes?\"", "finish_reason": "stop", "reasoning_content": "The user greeted me with \"Guten Morgen Kiwi\". According to the user profile, the user's name is Ahmed Zeyd Aytac, and he refers to me as 'Kiwi'. So he is greeting me (Kiwi) in German.\n\nI should respond in German since he used German, acknowledging the greeting. It's a fresh conversation (daily reset), so I should be friendly but not overdo it.\n\nKey facts from memory:\n- User is Ahmed Zeyd Aytac\n- He calls me Kiwi\n- Location: Wien (Vienna), Austria\n- Prefers 3D design/CAD projects when asked \"what should we build?\"\n- Prefers concise technical CAD reports\n- Doesn't want print recommendations\n- Doesn't want end-of-session skill reviews\n- \"Stop saving\" means stop the skill-update workflow immediately\n\nResponse should be simple: Good morning back, maybe ask what we're working on today or if he has a project in mind. Keep it concise.\n\nIn German: \"Guten Morgen, Ahmed! Was steht heute auf dem Plan? Ein neues 3D-Projekt oder was anderes?\"", "timestamp": "2026-05-13T08:01:04.776775"}
{"role": "user", "content": "Sag mir erst mal was heute im Kalender steht bitte und wie viel Grad es haben wird", "timestamp": "2026-05-13T12:08:46.244729"}
{"role": "assistant", "content": "Lass mich kurz die Kalender-Infos und das Wetter für Wien abrufen.", "reasoning": "Der User möchte wissen, was heute im Kalender steht und wie viel Grad es haben wird. Das bedeutet, ich muss zwei Dinge tun:\n\n1. Kalender/Ereignisse abfragen - dafür habe ich den google-workspace Skill\n2. Wetter für Wien abfragen - dafür habe ich den maps Skill (der Geocoding und Wetter kann? Warte, der maps Skill sagt \"Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.\" Das deckt Wetter nicht ab. Ich habe keinen spezifischen Wetter-Skill. Aber ich kann auch einfach das Wetter via web search oder über einen API-Aufruf im Terminal abfragen.\n\nAber warte - der User hat gesagt \"Sag mir erst mal was heute im Kalender steht\". Der google-workspace Skill könnte Calendar-Zugriff haben. Lass mich den Skill laden.\n\nAber zuerst: Ich habe skills für google-workspace. Lass mich die relevanten Skills laden.\n\nFür Wetter: Kein spezifischer Wetter-Skill. Aber ich kann web_search nutzen oder einen einfachen curl zu wttr.in oder einer anderen Wetter-API. Oder ich nutze execute_code mit einer Python-Bibliothek. Aber ich habe kein web_search Tool direkt - ich habe \"web\" toolset, aber kein dediziertes web_search Tool in der Tool-Liste oben. Warte, ich sehe die Tools: terminal, read_file, write_file, patch, search_files, delegate_task, execute_code, etc. Kein web_search Tool. Aber ich kann über terminal() curl machen.\n\nAlternativ: Ich kann den maps Skill laden, der vielleicht Wetter-Info hat? Nein, OpenStreetMap/OSRM macht kein Wetter.\n\nIch sollte:\n1. google-workspace Skill laden für Kalender\n2. Wetter via terminal/curl abfragen (z.B. wttr.in für Wien)\n\nLass mich die Skills laden.", "finish_reason": "tool_calls", "reasoning_content": "Der User möchte wissen, was heute im Kalender steht und wie viel Grad es haben wird. Das bedeutet, ich muss zwei Dinge tun:\n\n1. Kalender/Ereignisse abfragen - dafür habe ich den google-workspace Skill\n2. Wetter für Wien abfragen - dafür habe ich den maps Skill (der Geocoding und Wetter kann? Warte, der maps Skill sagt \"Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.\" Das deckt Wetter nicht ab. Ich habe keinen spezifischen Wetter-Skill. Aber ich kann auch einfach das Wetter via web search oder über einen API-Aufruf im Terminal abfragen.\n\nAber warte - der User hat gesagt \"Sag mir erst mal was heute im Kalender steht\". Der google-workspace Skill könnte Calendar-Zugriff haben. Lass mich den Skill laden.\n\nAber zuerst: Ich habe skills für google-workspace. Lass mich die relevanten Skills laden.\n\nFür Wetter: Kein spezifischer Wetter-Skill. Aber ich kann web_search nutzen oder einen einfachen curl zu wttr.in oder einer anderen Wetter-API. Oder ich nutze execute_code mit einer Python-Bibliothek. Aber ich habe kein web_search Tool direkt - ich habe \"web\" toolset, aber kein dediziertes web_search Tool in der Tool-Liste oben. Warte, ich sehe die Tools: terminal, read_file, write_file, patch, search_files, delegate_task, execute_code, etc. Kein web_search Tool. Aber ich kann über terminal() curl machen.\n\nAlternativ: Ich kann den maps Skill laden, der vielleicht Wetter-Info hat? Nein, OpenStreetMap/OSRM macht kein Wetter.\n\nIch sollte:\n1. google-workspace Skill laden für Kalender\n2. Wetter via terminal/curl abfragen (z.B. wttr.in für Wien)\n\nLass mich die Skills laden.", "tool_calls": [{"id": "functions.skill_view:0", "call_id": "functions.skill_view:0", "response_item_id": "fc_functionsskill_view0", "type": "function", "function": {"name": "skill_view", "arguments": "{\"name\":\"google-workspace\"}"}}, {"id": "functions.terminal:1", "call_id": "functions.terminal:1", "response_item_id": "fc_functionsterminal1", "type": "function", "function": {"name": "terminal", "arguments": "{\"command\":\"curl -s 'wttr.in/Wien?format=%C:+%t+%w+%h\\\\n' || curl -s 'wttr.in/Vienna?format=%C:+%t+%w+%h\\\\n'\",\"timeout\":15}"}}], "timestamp": "2026-05-13T12:08:46.244729"}
{"role": "tool", "name": "skill_view", "content": "{\"success\": true, \"name\": \"google-workspace\", \"description\": \"Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.\", \"tags\": [\"Google\", \"Gmail\", \"Calendar\", \"Drive\", \"Sheets\", \"Docs\", \"Contacts\", \"Email\", \"OAuth\"], \"related_skills\": [\"himalaya\"], \"content\": \"---\\nname: google-workspace\\ndescription: \\\"Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.\\\"\\nversion: 1.0.1\\nauthor: Nous Research\\nlicense: MIT\\nrequired_credential_files:\\n  - path: google_token.json\\n    description: Google OAuth2 token (created by setup script)\\n  - path: google_client_secret.json\\n    description: Google OAuth2 client credentials (downloaded from Google Cloud Console)\\nmetadata:\\n  hermes:\\n    tags: [Google, Gmail, Calendar, Drive, Sheets, Docs, Contacts, Email, OAuth]\\n    homepage: https://github.com/NousResearch/hermes-agent\\n    related_skills: [himalaya]\\n---\\n\\n# Google Workspace\\n\\nGmail, Calendar, Drive, Contacts, Sheets, and Docs — through Hermes-managed OAuth and a thin CLI wrapper. When `gws` is installed, the skill uses it as the execution backend for broader Google Workspace coverage; otherwise it falls back to the bundled Python client implementation.\\n\\n## References\\n\\n- `references/gmail-search-syntax.md` — Gmail search operators (is:unread, from:, newer_than:, etc.)\\n\\n## Scripts\\n\\n- `scripts/setup.py` — OAuth2 setup (run once to authorize)\\n- `scripts/google_api.py` — compatibility wrapper CLI. It prefers `gws` for operations when available, while preserving Hermes' existing JSON output contract.\\n\\n## First-Time Setup\\n\\nThe setup is fully non-interactive — you drive it step by step so it works\\non CLI, Telegram, Discord, or any platform.\\n\\nDefine a shorthand first:\\n\\n```bash\\nGSETUP=\\\"python ${HERMES_HOME:-$HOME/.hermes}/skills/productivity/google-workspace/scripts/setup.py\\\"\\n```\\n\\n### Step 0: Check if already set up\\n\\n```bash\\n$GSETUP --check\\n```\\n\\nIf it prints `AUTHENTICATED`, skip to Usage — setup is already done.\\n\\n### Step 1: Triage — ask the user what they need\\n\\nBefore starting OAuth setup, ask the user TWO questions:\\n\\n**Question 1: \\\"What Google services do you need? Just email, or also\\nCalendar/Drive/Sheets/Docs?\\\"**\\n\\n- **Email only** → They don't need this skill at all. Use the `himalaya` skill\\n  instead — it works with a Gmail App Password (Settings → Security → App\\n  Passwords) and takes 2 minutes to set up. No Google Cloud project needed.\\n  Load the himalaya skill and follow its setup instructions.\\n\\n- **Email + Calendar** → Continue with this skill, but use\\n  `--services email,calendar` during auth so the consent screen only asks for\\n  the scopes they actually need.\\n\\n- **Calendar/Drive/Sheets/Docs only** → Continue with this skill and use a\\n  narrower `--services` set like `calendar,drive,sheets,docs`.\\n\\n- **Full Workspace access** → Continue with this skill and use the default\\n  `all` service set.\\n\\n**Question 2: \\\"Does your Google account use Advanced Protection (hardware\\nsecurity keys required to sign in)? If you're not sure, you probably don't\\n— it's something you would have explicitly enrolled in.\\\"**\\n\\n- **No / Not sure** → Normal setup. Continue below.\\n- **Yes** → Their Workspace admin must add the OAuth client ID to the org's\\n  allowed apps list before Step 4 will work. Let them know upfront.\\n\\n### Step 2: Create OAuth credentials (one-time, ~5 minutes)\\n\\nTell the user:\\n\\n> You need a Google Cloud OAuth client. This is a one-time setup:\\n>\\n> 1. Create or select a project:\\n>    https://console.cloud.google.com/projectselector2/home/dashboard\\n> 2. Enable the required APIs from the API Library:\\n>    https://console.cloud.google.com/apis/library\\n>    Enable: Gmail API, Google Calendar API, Google Drive API,\\n>    Google Sheets API, Google Docs API, People API\\n> 3. Create the OAuth client here:\\n>    https://console.cloud.google.com/apis/credentials\\n>    Credentials → Create Credentials → OAuth 2.0 Client ID\\n> 4. Application type: \\\"Desktop app\\\" → Create\\n> 5. If the app is still in Testing, add the user's Google account as a test user here:\\n>    https://console.cloud.google.com/auth/audience\\n>    Audience → Test users → Add users\\n> 6. Download the JSON file and tell me the file path\\n>\\n> Important Hermes CLI note: if the file path starts with `/`, do NOT send only the bare path as its own message in the CLI, because it can be mistaken for a slash command. Send it in a sentence instead, like:\\n> `The JSON file path is: /home/user/Downloads/client_secret_....json`\\n\\nOnce they provide the path:\\n\\n```bash\\n$GSETUP --client-secret /path/to/client_secret.json\\n```\\n\\nIf they paste the raw client ID / client secret values instead of a file path,\\nwrite a valid Desktop OAuth JSON file for them yourself, save it somewhere\\nexplicit (for example `~/Downloads/hermes-google-client-secret.json`), then run\\n`--client-secret` against that file.\\n\\n### Step 3: Get authorization URL\\n\\nUse the service set chosen in Step 1. Examples:\\n\\n```bash\\n$GSETUP --auth-url --services email,calendar --format json\\n$GSETUP --auth-url --services calendar,drive,sheets,docs --format json\\n$GSETUP --auth-url --services all --format json\\n```\\n\\nThis returns JSON with an `auth_url` field and also saves the exact URL to\\n`~/.hermes/google_oauth_last_url.txt`.\\n\\nAgent rules for this step:\\n- Extract the `auth_url` field and send that exact URL to the user as a single line.\\n- Tell the user that the browser will likely fail on `http://localhost:1` after approval, and that this is expected.\\n- Tell them to copy the ENTIRE redirected URL from the browser address bar.\\n- If the user gets `Error 403: access_denied`, send them directly to `https://console.cloud.google.com/auth/audience` to add themselves as a test user.\\n\\n### Step 4: Exchange the code\\n\\nThe user will paste back either a URL like `http://localhost:1/?code=4/0A...&scope=...`\\nor just the code string. Either works. The `--auth-url` step stores a temporary\\npending OAuth session locally so `--auth-code` can complete the PKCE exchange\\nlater, even on headless systems:\\n\\n```bash\\n$GSETUP --auth-code \\\"THE_URL_OR_CODE_THE_USER_PASTED\\\" --format json\\n```\\n\\nIf `--auth-code` fails because the code expired, was already used, or came from\\nan older browser tab, it now returns a fresh `fresh_auth_url`. In that case,\\nimmediately send the new URL to the user and have them retry with the newest\\nbrowser redirect only.\\n\\n### Step 5: Verify\\n\\n```bash\\n$GSETUP --check\\n```\\n\\nShould print `AUTHENTICATED`. Setup is complete — token refreshes automatically from now on.\\n\\n### Notes\\n\\n- Token is stored at `~/.hermes/google_token.json` and auto-refreshes.\\n- Pending OAuth session state/verifier are stored temporarily at `~/.hermes/google_oauth_pending.json` until exchange completes.\\n- If `gws` is installed, `google_api.py` points it at the same `~/.hermes/google_token.json` credentials file. Users do not need to run a separate `gws auth login` flow.\\n- To revoke: `$GSETUP --revoke`\\n\\n## Usage\\n\\nAll commands go through the API script. Set `GAPI` as a shorthand:\\n\\n```bash\\nGAPI=\\\"python ${HERMES_HOME:-$HOME/.hermes}/skills/productivity/google-workspace/scripts/google_api.py\\\"\\n```\\n\\n### Gmail\\n\\n```bash\\n# Search (returns JSON array with id, from, subject, date, snippet)\\n$GAPI gmail search \\\"is:unread\\\" --max 10\\n$GAPI gmail search \\\"from:boss@company.com newer_than:1d\\\"\\n$GAPI gmail search \\\"has:attachment filename:pdf newer_than:7d\\\"\\n\\n# Read full message (returns JSON with body text)\\n$GAPI gmail get MESSAGE_ID\\n\\n# Send\\n$GAPI gmail send --to user@example.com --subject \\\"Hello\\\" --body \\\"Message text\\\"\\n$GAPI gmail send --to user@example.com --subject \\\"Report\\\" --body \\\"<h1>Q4</h1><p>Details...</p>\\\" --html\\n$GAPI gmail send --to user@example.com --subject \\\"Hello\\\" --from '\\\"Research Agent\\\" <user@example.com>' --body \\\"Message text\\\"\\n\\n# Reply (automatically threads and sets In-Reply-To)\\n$GAPI gmail reply MESSAGE_ID --body \\\"Thanks, that works for me.\\\"\\n$GAPI gmail reply MESSAGE_ID --from '\\\"Support Bot\\\" <user@example.com>' --body \\\"Thanks\\\"\\n\\n# Labels\\n$GAPI gmail labels\\n$GAPI gmail modify MESSAGE_ID --add-labels LABEL_ID\\n$GAPI gmail modify MESSAGE_ID --remove-labels UNREAD\\n```\\n\\n### Calendar\\n\\n```bash\\n# List events (defaults to next 7 days)\\n$GAPI calendar list\\n$GAPI calendar list --start 2026-03-01T00:00:00Z --end 2026-03-07T23:59:59Z\\n\\n# Create event (ISO 8601 with timezone required)\\n$GAPI calendar create --summary \\\"Team Standup\\\" --start 2026-03-01T10:00:00-06:00 --end 2026-03-01T10:30:00-06:00\\n$GAPI calendar create --summary \\\"Lunch\\\" --start 2026-03-01T12:00:00Z --end 2026-03-01T13:00:00Z --location \\\"Cafe\\\"\\n$GAPI calendar create --summary \\\"Review\\\" --start 2026-03-01T14:00:00Z --end 2026-03-01T15:00:00Z --attendees \\\"alice@co.com,bob@co.com\\\"\\n\\n# Delete event\\n$GAPI calendar delete EVENT_ID\\n```\\n\\n### Drive\\n\\n```bash\\n$GAPI drive search \\\"quarterly report\\\" --max 10\\n$GAPI drive search \\\"mimeType='application/pdf'\\\" --raw-query --max 5\\n```\\n\\n### Contacts\\n\\n```bash\\n$GAPI contacts list --max 20\\n```\\n\\n### Sheets\\n\\n```bash\\n# Read\\n$GAPI sheets get SHEET_ID \\\"Sheet1!A1:D10\\\"\\n\\n# Write\\n$GAPI sheets update SHEET_ID \\\"Sheet1!A1:B2\\\" --values '[[\\\"Name\\\",\\\"Score\\\"],[\\\"Alice\\\",\\\"95\\\"]]'\\n\\n# Append rows\\n$GAPI sheets append SHEET_ID \\\"Sheet1!A:C\\\" --values '[[\\\"new\\\",\\\"row\\\",\\\"data\\\"]]'\\n```\\n\\n### Docs\\n\\n```bash\\n$GAPI docs get DOC_ID\\n```\\n\\n## Output Format\\n\\nAll commands return JSON. Parse with `jq` or read directly. Key fields:\\n\\n- **Gmail search**: `[{id, threadId, from, to, subject, date, snippet, labels}]`\\n- **Gmail get**: `{id, threadId, from, to, subject, date, labels, body}`\\n- **Gmail send/reply**: `{status: \\\"sent\\\", id, threadId}`\\n- **Calendar list**: `[{id, summary, start, end, location, description, htmlLink}]`\\n- **Calendar create**: `{status: \\\"created\\\", id, summary, htmlLink}`\\n- **Drive search**: `[{id, name, mimeType, modifiedTime, webViewLink}]`\\n- **Contacts list**: `[{name, emails: [...], phones: [...]}]`\\n- **Sheets get**: `[[cell, cell, ...], ...]`\\n\\n## Rules\\n\\n1. **Never send email or create/delete events without confirming with the user first.** Show the draft content and ask for approval.\\n2. **Check auth before first use** — run `setup.py --check`. If it fails, guide the user through setup.\\n3. **Use the Gmail search syntax reference** for complex queries — load it with `skill_view(\\\"google-workspace\\\", file_path=\\\"references/gmail-search-syntax.md\\\")`.\\n4. **Calendar times must include timezone** — always use ISO 8601 with offset (e.g., `2026-03-01T10:00:00-06:00`) or UTC (`Z`).\\n5. **Respect rate limits** — avoid rapid-fire sequential API calls. Batch reads when possible.\\n\\n## Troubleshooting\\n\\n| Problem | Fix |\\n|---------|-----|\\n| `NOT_AUTHENTICATED` | Run setup Steps 2-5 above |\\n| `REFRESH_FAILED` | Token revoked or expired — redo Steps 3-5 |\\n| `HttpError 403: Insufficient Permission` | Missing API scope — `$GSETUP --revoke` then redo Steps 3-5 |\\n| `HttpError 403: Access Not Configured` | API not enabled — user needs to enable it in Google Cloud Console |\\n| `ModuleNotFoundError` | Run `$GSETUP --install-deps` |\\n| Advanced Protection blocks auth | Workspace admin must allowlist the OAuth client ID |\\n\\n## Revoking Access\\n\\n```bash\\n$GSETUP --revoke\\n```\\n\", \"path\": \"productivity/google-workspace/SKILL.md\", \"skill_dir\": \"/DATA/.hermes/skills/productivity/google-workspace\", \"linked_files\": {\"references\": [\"references/gmail-search-syntax.md\"], \"scripts\": [\"scripts/_hermes_home.py\", \"scripts/google_api.py\", \"scripts/gws_bridge.py\", \"scripts/setup.py\"]}, \"usage_hint\": \"To view linked files, call skill_view(name, file_path) where file_path is e.g. 'references/api.md' or 'assets/config.yaml'\", \"required_environment_variables\": [], \"required_commands\": [], \"missing_required_environment_variables\": [], \"missing_credential_files\": [\"google_token.json\", \"google_client_secret.json\"], \"missing_required_commands\": [], \"setup_needed\": true, \"setup_skipped\": false, \"readiness_status\": \"setup_needed\", \"setup_note\": \"Setup needed before using this skill: missing file google_token.json, file google_client_secret.json.\", \"metadata\": {\"hermes\": {\"tags\": [\"Google\", \"Gmail\", \"Calendar\", \"Drive\", \"Sheets\", \"Docs\", \"Contacts\", \"Email\", \"OAuth\"], \"homepage\": \"https://github.com/NousResearch/hermes-agent\", \"related_skills\": [\"himalaya\"]}}}", "tool_call_id": "functions.skill_view:0", "timestamp": "2026-05-13T12:08:46.244729"}
{"role": "tool", "name": "terminal", "content": "{\"output\": \"Partly cloudy: +14°C →12km/h 38%\", \"exit_code\": 0, \"error\": null}", "tool_call_id": "functions.terminal:1", "timestamp": "2026-05-13T12:08:46.244729"}
{"role": "assistant", "content": "**Wetter für Wien heute:**\nTeilweise bewölkt, **14°C**, Wind 12 km/h, Luftfeuchtigkeit 38%.\n\n**Kalender:** Der Google-Calendar-Zugang ist noch nicht eingerichtet. Wenn du willst, kann ich den OAuth-Setup für Google Workspace jetzt durchziehen (dauert ~5 Minuten), damit ich künftig direkt deine Termine abrufen kann.\n\nAlternativ: nutzt du einen anderen Kalender (Outlook, Apple, Nextcloud)? Oder soll ich Google Calendar einrichten?", "reasoning": "Das Wetter habe ich: Partly cloudy (teilweise bewölkt), 14°C, 12km/h Wind, 38% Luftfeuchtigkeit.\n\nFür den Kalender brauche ich aber die Google-Workspace-Skill, die noch nicht eingerichtet ist. Ich muss den User fragen, ob er sie einrichten will, oder vielleicht hat er eine andere Art seinen Kalender zu nutzen.\n\nLass mich auch noch checken, ob Himalaya (nur Email) eingerichtet ist, falls er Email braucht.\n\nAber eigentlich will er nur den Kalender sehen. Ich muss sagen, dass Google Calendar noch nicht eingerichtet ist. Lass mich das transparent machen.\n\nIch sollte auch fragen ob ich es schnell einrichte, oder ob er einen anderen Kalender hat.", "finish_reason": "stop", "reasoning_content": "Das Wetter habe ich: Partly cloudy (teilweise bewölkt), 14°C, 12km/h Wind, 38% Luftfeuchtigkeit.\n\nFür den Kalender brauche ich aber die Google-Workspace-Skill, die noch nicht eingerichtet ist. Ich muss den User fragen, ob er sie einrichten will, oder vielleicht hat er eine andere Art seinen Kalender zu nutzen.\n\nLass mich auch noch checken, ob Himalaya (nur Email) eingerichtet ist, falls er Email braucht.\n\nAber eigentlich will er nur den Kalender sehen. Ich muss sagen, dass Google Calendar noch nicht eingerichtet ist. Lass mich das transparent machen.\n\nIch sollte auch fragen ob ich es schnell einrichte, oder ob er einen anderen Kalender hat.", "timestamp": "2026-05-13T12:08:46.244729"}
{"role": "user", "content": "Kiwitime nutzen bitte", "timestamp": "2026-05-13T12:26:51.187139"}
{"role": "assistant", "content": "Ich kenn \"Kiwitime\" noch nicht – meinst du damit einen bestimmten Kalender, eine eigene Datei/Notiz oder eine Hermes-Funktion, die ich noch nicht kenne? Gib mir kurz einen Hinweis, dann zieh ich die Daten für dich.", "reasoning": "Der Nutzer meint wahrscheinlich die Hermes-Kalenderfunktion. Lass mich prüfen, ob es im Hermes-System einen Kalender gibt. Im Kontext sehe ich keinen Hinweis auf einen \"Kiwitime\"-Kalender oder eine Kalender-App direkt in Hermes. \n\nVielleicht meint er:\n1. Eine Datei/Skill namens \"kiwitime\"? \n2. Oder er spielt auf \"Hermes\" an und meint die Hermes-eigene Cronjob/Memory-Funktion als \"Kiwitime\"?\n3. Oder er hat irgendwo einen Kalender unter einem bestimmten Namen/Medium gespeichert?\n\nIch sollte nachfragen, was er genau meint, da \"Kiwitime\" mir nicht als bekanntes Tool in Hermes einfällt. Oder ich prüfe, ob es eine Datei oder ein Script namens kiwitime gibt. Vielleicht eine eigene Datei beim User?\n\nWarte, er könnte auch einfach sagen \"KiWi Time\" als Scherz für den Hermes-Agenten (Kiwi). Aber was genau soll ich nutzen?\n\nAm besten frage ich kurz nach, was er mit \"Kiwitime\" meint, da es kein Standardtool ist, das ich kenne. Das ist eine offene Frage.", "finish_reason": "stop", "reasoning_content": "Der Nutzer meint wahrscheinlich die Hermes-Kalenderfunktion. Lass mich prüfen, ob es im Hermes-System einen Kalender gibt. Im Kontext sehe ich keinen Hinweis auf einen \"Kiwitime\"-Kalender oder eine Kalender-App direkt in Hermes. \n\nVielleicht meint er:\n1. Eine Datei/Skill namens \"kiwitime\"? \n2. Oder er spielt auf \"Hermes\" an und meint die Hermes-eigene Cronjob/Memory-Funktion als \"Kiwitime\"?\n3. Oder er hat irgendwo einen Kalender unter einem bestimmten Namen/Medium gespeichert?\n\nIch sollte nachfragen, was er genau meint, da \"Kiwitime\" mir nicht als bekanntes Tool in Hermes einfällt. Oder ich prüfe, ob es eine Datei oder ein Script namens kiwitime gibt. Vielleicht eine eigene Datei beim User?\n\nWarte, er könnte auch einfach sagen \"KiWi Time\" als Scherz für den Hermes-Agenten (Kiwi). Aber was genau soll ich nutzen?\n\nAm besten frage ich kurz nach, was er mit \"Kiwitime\" meint, da es kein Standardtool ist, das ich kenne. Das ist eine offene Frage.", "timestamp": "2026-05-13T12:26:51.187139"}
{"role": "user", "content": "[The user sent a voice message~ Here's what they said: \"Das ist der Skill, den wir installiert haben, wo draußen steht, wie du meinen Kalender verwenden kannst. Du hast das schon alles mal gemacht.\"]", "timestamp": "2026-05-13T12:35:48.165268"}
{"role": "assistant", "content": "Ah, verstehe! Kiwitime ist also ein Skill, den wir bereits haben. Lass mich kurz nach ihm suchen – er ist mir gerade nicht in der aktuellen Liste aufgefallen.", "reasoning": "Der User meint wohl einen Skill, den wir schon installiert haben und der meinen/denen Kalender beschreibt. Ich soll nach einem Skill suchen, der \"kiwitime\" oder ähnlich heißt, oder nach einem Skill, der Kalender-Funktionalität hat und den wir schon eingerichtet haben. Der User sagt \"Du hast das schon alles mal gemacht.\" - das deutet darauf hin, dass es einen Skill gibt, den wir bereits genutzt haben.\n\nLass mich die verfügbaren Skills durchsuchen. Vielleicht gibt es einen Skill, der \"kiwitime\" heißt oder etwas mit Kalender zu tun hat. Ich sollte `skills_list` aufrufen und nach \"kiwi\" oder \"time\" oder \"calendar\" suchen. Oder ich könnte `session_search` verwenden, um nach früheren Kalender-Interaktionen zu suchen.\n\nDa der User sagt \"Das ist der Skill, den wir installiert haben\", schaue ich zuerst in den Skills nach. Vielleicht ist es ein Skill, der nicht in meiner obigen Liste auftauchte? Warte, die Liste oben zeigt alle verfügbaren Skills, und \"kiwitime\" ist nicht dabei.\n\nAlternativ könnte es sich um einen benutzerdefinierten Skill handeln, den wir erstellt haben, oder es könnte sich um eine Funktion in einem bestehenden Skill handeln. Der User sagt, ich hätte das schon mal gemacht - also sollte ich `session_search` verwenden, um nach früheren Kalender-Aufrufen zu suchen. \n\nAber warte, der User sagt \"Kiwitime\" ist ein Skill. Vielleicht ist es ein Skill, der in einem anderen Verzeichnis liegt oder unter einem anderen Namen? Ich sollte nach allen Skills suchen, insbesondere nach \"kiwi\" oder nach etwas, das mit Kalender zu tun hat.\n\nDa der User es als \"Kiwitime\" bezeichnet und sagt, wir hätten es installiert, sollte ich `skills_list` ohne Filter aufrufen und dann nach \"kiwi\" oder \"time\" oder \"calendar\" suchen. Aber die Liste oben enthält keinen \"kiwitime\" Skill. \n\nVielleicht meint der User \"hermes-agent\" oder einen anderen Skill? Oder vielleicht ist es ein Skill, der in einem früheren Chat erstellt wurde und ich sollte `session_search` verwenden.\n\nLass mich `session_search` verwenden, um nach \"kiwitime\" oder \"kalender\" zu suchen.", "finish_reason": "tool_calls", "reasoning_content": "Der User meint wohl einen Skill, den wir schon installiert haben und der meinen/denen Kalender beschreibt. Ich soll nach einem Skill suchen, der \"kiwitime\" oder ähnlich heißt, oder nach einem Skill, der Kalender-Funktionalität hat und den wir schon eingerichtet haben. Der User sagt \"Du hast das schon alles mal gemacht.\" - das deutet darauf hin, dass es einen Skill gibt, den wir bereits genutzt haben.\n\nLass mich die verfügbaren Skills durchsuchen. Vielleicht gibt es einen Skill, der \"kiwitime\" heißt oder etwas mit Kalender zu tun hat. Ich sollte `skills_list` aufrufen und nach \"kiwi\" oder \"time\" oder \"calendar\" suchen. Oder ich könnte `session_search` verwenden, um nach früheren Kalender-Interaktionen zu suchen.\n\nDa der User sagt \"Das ist der Skill, den wir installiert haben\", schaue ich zuerst in den Skills nach. Vielleicht ist es ein Skill, der nicht in meiner obigen Liste auftauchte? Warte, die Liste oben zeigt alle verfügbaren Skills, und \"kiwitime\" ist nicht dabei.\n\nAlternativ könnte es sich um einen benutzerdefinierten Skill handeln, den wir erstellt haben, oder es könnte sich um eine Funktion in einem bestehenden Skill handeln. Der User sagt, ich hätte das schon mal gemacht - also sollte ich `session_search` verwenden, um nach früheren Kalender-Aufrufen zu suchen. \n\nAber warte, der User sagt \"Kiwitime\" ist ein Skill. Vielleicht ist es ein Skill, der in einem anderen Verzeichnis liegt oder unter einem anderen Namen? Ich sollte nach allen Skills suchen, insbesondere nach \"kiwi\" oder nach etwas, das mit Kalender zu tun hat.\n\nDa der User es als \"Kiwitime\" bezeichnet und sagt, wir hätten es installiert, sollte ich `skills_list` ohne Filter aufrufen und dann nach \"kiwi\" oder \"time\" oder \"calendar\" suchen. Aber die Liste oben enthält keinen \"kiwitime\" Skill. \n\nVielleicht meint der User \"hermes-agent\" oder einen anderen Skill? Oder vielleicht ist es ein Skill, der in einem früheren Chat erstellt wurde und ich sollte `session_search` verwenden.\n\nLass mich `session_search` verwenden, um nach \"kiwitime\" oder \"kalender\" zu suchen.", "tool_calls": [{"id": "functions.session_search:2", "call_id": "functions.session_search:2", "response_item_id": "fc_functionssession_search2", "type": "function", "function": {"name": "session_search", "arguments": "{\"query\":\"kiwitime OR kalender OR calendar skill\",\"limit\":5}"}}, {"id": "functions.skills_list:3", "call_id": "functions.skills_list:3", "response_item_id": "fc_functionsskills_list3", "type": "function", "function": {"name": "skills_list", "arguments": "{}"}}], "timestamp": "2026-05-13T12:35:48.165268"}
{"role": "tool", "name": "session_search", "content": "{\"success\": true, \"query\": \"kiwitime OR kalender OR calendar skill\", \"results\": [{\"session_id\": \"20260511_094554_273678fc\", \"when\": \"May 11, 2026 at 09:45 AM\", \"source\": \"telegram\", \"model\": \"kimi-k2.6\", \"summary\": \"[Raw preview — summarization unavailable]\\n...[earlier conversation truncated]...\\n\\ner LoRa [...]\\\\nU: Wie können man irgendwie Funk nutzen um mehr als nur Text zu schicken?\\\\nK: LoRa/Meshtastic ist extrem sparsam gebaut — aber es gibt mehrere Wege, über den Text hinauszugehen.  **Was Meshtastic schon nativ kann:** - **Position** (GPS-Updates, Tracking auf der Karte) - **Waypoints** (Orte markieren und verteilen) - **Telemetrie** (Batteriestand, Temperatur, Luftdruck von Sensoren) - **Remote H/W** (GPIO/Sensor-Werte abfragen, Relais schalte\\n…[truncated]\"}, {\"session_id\": \"20260511_150044_d89ceffa\", \"when\": \"May 11, 2026 at 03:00 PM\", \"source\": \"telegram\", \"model\": \"kimi-k2.6\", \"summary\": \"[Raw preview — summarization unavailable]\\n[USER]: Ich möchte dich für 3-D Design nutzen\\n\\nIch habe einen 3-D Drucker und möchte dass du Design für mich machst die ich dann eins zu eins drucken kann\\n\\nEs gibt sehr viele Quellen im Internet wo Leute beschreiben wie man dich dafür nutzen kann ich bitte dich also im Internet zu recherchieren was ist die beste Art und Weise ist und dann ein Skill zu erstellen. Wenn du Blender installieren willst mach das, mir ist alles egal Hauptsache es funktioniert sehr gut\\n\\nAlle anderen Skills mit 3-D Desig\\n…[truncated]\"}, {\"session_id\": \"20260512_075306_c103a1dd\", \"when\": \"May 12, 2026 at 07:53 AM\", \"source\": \"telegram\", \"model\": \"kimi-k2.6\", \"summary\": \"[Raw preview — summarization unavailable]\\n...[earlier conversation truncated]...\\n\\n find bugs, evidence, reports.\\\", \\\"category\\\": null}, {\\\"name\\\": \\\"yuanbao\\\", \\\"description\\\": \\\"Yuanbao (元宝) groups: @mention users, query info/members.\\\", \\\"category\\\": null}, {\\\"name\\\": \\\"3d-druck-kiwi\\\", \\\"description\\\": \\\"Vollständiger Workflow zum Erstellen druckbarer 3D-Modelle aus Textbeschreibungen. Nutzt Python (trimesh + manifold3d) als primären CAD-Engine. Generiert validierte STL/3MF-Dateien für Bambu Lab Drucker.\\\", \\\"category\\\": \\\"3d-printing\\\"}, {\\\"name\\\": \\\"claude-c\\n…[truncated]\"}], \"count\": 3, \"sessions_searched\": 3}", "tool_call_id": "functions.session_search:2", "timestamp": "2026-05-13T12:35:48.165268"}
{"role": "tool", "name": "skills_list", "content": "{\"success\": true, \"skills\": [{\"name\": \"cad-3d-print\", \"description\": \"Parametric 3D modeling with trimesh for FDM printing. Generates STL with PNG preview and mesh validation. Headless, pure Python — uses direct mesh construction for reliable chamfers and fillets.\", \"category\": null}, {\"name\": \"dogfood\", \"description\": \"Exploratory QA of web apps: find bugs, evidence, reports.\", \"category\": null}, {\"name\": \"yuanbao\", \"description\": \"Yuanbao (元宝) groups: @mention users, query info/members.\", \"category\": null}, {\"name\": \"3d-druck-kiwi\", \"description\": \"Vollständiger Workflow zum Erstellen druckbarer 3D-Modelle aus Textbeschreibungen. Nutzt Python (trimesh + manifold3d) als primären CAD-Engine. Generiert validierte STL/3MF-Dateien für Bambu Lab Drucker.\", \"category\": \"3d-printing\"}, {\"name\": \"claude-code\", \"description\": \"Delegate coding to Claude Code CLI (features, PRs).\", \"category\": \"autonomous-ai-agents\"}, {\"name\": \"codex\", \"description\": \"Delegate coding to OpenAI Codex CLI (features, PRs).\", \"category\": \"autonomous-ai-agents\"}, {\"name\": \"hermes-agent\", \"description\": \"Configure, extend, or contribute to Hermes Agent.\", \"category\": \"autonomous-ai-agents\"}, {\"name\": \"opencode\", \"description\": \"Delegate coding to OpenCode CLI (features, PR review).\", \"category\": \"autonomous-ai-agents\"}, {\"name\": \"architecture-diagram\", \"description\": \"Dark-themed SVG architecture/cloud/infra diagrams as HTML.\", \"category\": \"creative\"}, {\"name\": \"ascii-art\", \"description\": \"ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.\", \"category\": \"creative\"}, {\"name\": \"ascii-video\", \"description\": \"ASCII video: convert video/audio to colored ASCII MP4/GIF.\", \"category\": \"creative\"}, {\"name\": \"baoyu-comic\", \"description\": \"Knowledge comics (知识漫画): educational, biography, tutorial.\", \"category\": \"creative\"}, {\"name\": \"baoyu-infographic\", \"description\": \"Infographics: 21 layouts x 21 styles (信息图, 可视化).\", \"category\": \"creative\"}, {\"name\": \"claude-design\", \"description\": \"Design one-off HTML artifacts (landing, deck, prototype).\", \"category\": \"creative\"}, {\"name\": \"comfyui\", \"description\": \"Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.\", \"category\": \"creative\"}, {\"name\": \"design-md\", \"description\": \"Author/validate/export Google's DESIGN.md token spec files.\", \"category\": \"creative\"}, {\"name\": \"excalidraw\", \"description\": \"Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).\", \"category\": \"creative\"}, {\"name\": \"humanizer\", \"description\": \"Humanize text: strip AI-isms and add real voice.\", \"category\": \"creative\"}, {\"name\": \"ideation\", \"description\": \"Generate project ideas via creative constraints.\", \"category\": \"creative\"}, {\"name\": \"manim-video\", \"description\": \"Manim CE animations: 3Blue1Brown math/algo videos.\", \"category\": \"creative\"}, {\"name\": \"p5js\", \"description\": \"p5.js sketches: gen art, shaders, interactive, 3D.\", \"category\": \"creative\"}, {\"name\": \"pixel-art\", \"description\": \"Pixel art w/ era palettes (NES, Game Boy, PICO-8).\", \"category\": \"creative\"}, {\"name\": \"popular-web-designs\", \"description\": \"54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.\", \"category\": \"creative\"}, {\"name\": \"pretext\", \"description\": \"Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.\", \"category\": \"creative\"}, {\"name\": \"sketch\", \"description\": \"Throwaway HTML mockups: 2-3 design variants to compare.\", \"category\": \"creative\"}, {\"name\": \"songwriting-and-ai-music\", \"description\": \"Songwriting craft and Suno AI music prompts.\", \"category\": \"creative\"}, {\"name\": \"touchdesigner-mcp\", \"description\": \"Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.\", \"category\": \"creative\"}, {\"name\": \"jupyter-live-kernel\", \"description\": \"Iterative Python via live Jupyter kernel (hamelnb).\", \"category\": \"data-science\"}, {\"name\": \"kanban-orchestrator\", \"description\": \"Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The \\\"don't do the work yourself\\\" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.\", \"category\": \"devops\"}, {\"name\": \"kanban-worker\", \"description\": \"Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.\", \"category\": \"devops\"}, {\"name\": \"webhook-subscriptions\", \"description\": \"Webhook subscriptions: event-driven agent runs.\", \"category\": \"devops\"}, {\"name\": \"himalaya\", \"description\": \"Himalaya CLI: IMAP/SMTP email from terminal.\", \"category\": \"email\"}, {\"name\": \"minecraft-modpack-server\", \"description\": \"Host modded Minecraft servers (CurseForge, Modrinth).\", \"category\": \"gaming\"}, {\"name\": \"pokemon-player\", \"description\": \"Play Pokemon via headless emulator + RAM reads.\", \"category\": \"gaming\"}, {\"name\": \"codebase-inspection\", \"description\": \"Inspect codebases w/ pygount: LOC, languages, ratios.\", \"category\": \"github\"}, {\"name\": \"github-auth\", \"description\": \"GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.\", \"category\": \"github\"}, {\"name\": \"github-code-review\", \"description\": \"Review PRs: diffs, inline comments via gh or REST.\", \"category\": \"github\"}, {\"name\": \"github-issues\", \"description\": \"Create, triage, label, assign GitHub issues via gh or REST.\", \"category\": \"github\"}, {\"name\": \"github-pr-workflow\", \"description\": \"GitHub PR lifecycle: branch, commit, open, CI, merge.\", \"category\": \"github\"}, {\"name\": \"github-repo-management\", \"description\": \"Clone/create/fork repos; manage remotes, releases.\", \"category\": \"github\"}, {\"name\": \"esp32-desk-dashboard\", \"description\": \"ESP32-basierte Desk-Dashboards mit AMOLED, LVGL und BLE. Hardware-Auswahl, Firmware-Architektur, Daemon-Design und Tooling für Maker.\", \"category\": \"maker-electronics\"}, {\"name\": \"native-mcp\", \"description\": \"MCP client: connect servers, register tools (stdio/HTTP).\", \"category\": \"mcp\"}, {\"name\": \"gif-search\", \"description\": \"Search/download GIFs from Tenor via curl + jq.\", \"category\": \"media\"}, {\"name\": \"heartmula\", \"description\": \"HeartMuLa: Suno-like song generation from lyrics + tags.\", \"category\": \"media\"}, {\"name\": \"songsee\", \"description\": \"Audio spectrograms/features (mel, chroma, MFCC) via CLI.\", \"category\": \"media\"}, {\"name\": \"spotify\", \"description\": \"Spotify: play, search, queue, manage playlists and devices.\", \"category\": \"media\"}, {\"name\": \"youtube-content\", \"description\": \"YouTube transcripts to summaries, threads, blogs.\", \"category\": \"media\"}, {\"name\": \"audiocraft-audio-generation\", \"description\": \"AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.\", \"category\": \"mlops\"}, {\"name\": \"axolotl\", \"description\": \"Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).\", \"category\": \"mlops\"}, {\"name\": \"dspy\", \"description\": \"DSPy: declarative LM programs, auto-optimize prompts, RAG.\", \"category\": \"mlops\"}, {\"name\": \"evaluating-llms-harness\", \"description\": \"lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).\", \"category\": \"mlops\"}, {\"name\": \"fine-tuning-with-trl\", \"description\": \"TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.\", \"category\": \"mlops\"}, {\"name\": \"huggingface-hub\", \"description\": \"HuggingFace hf CLI: search/download/upload models, datasets.\", \"category\": \"mlops\"}, {\"name\": \"llama-cpp\", \"description\": \"llama.cpp local GGUF inference + HF Hub model discovery.\", \"category\": \"mlops\"}, {\"name\": \"obliteratus\", \"description\": \"OBLITERATUS: abliterate LLM refusals (diff-in-means).\", \"category\": \"mlops\"}, {\"name\": \"outlines\", \"description\": \"Outlines: structured JSON/regex/Pydantic LLM generation.\", \"category\": \"mlops\"}, {\"name\": \"segment-anything-model\", \"description\": \"SAM: zero-shot image segmentation via points, boxes, masks.\", \"category\": \"mlops\"}, {\"name\": \"serving-llms-vllm\", \"description\": \"vLLM: high-throughput LLM serving, OpenAI API, quantization.\", \"category\": \"mlops\"}, {\"name\": \"unsloth\", \"description\": \"Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.\", \"category\": \"mlops\"}, {\"name\": \"weights-and-biases\", \"description\": \"W&B: log ML experiments, sweeps, model registry, dashboards.\", \"category\": \"mlops\"}, {\"name\": \"obsidian\", \"description\": \"Read, search, create, and edit notes in the Obsidian vault.\", \"category\": \"note-taking\"}, {\"name\": \"airtable\", \"description\": \"Airtable REST API via curl. Records CRUD, filters, upserts.\", \"category\": \"productivity\"}, {\"name\": \"docmaster-access\", \"description\": \"Direkter Zugriff auf DocMaster-Dokumente auf ZimaOS — API-Infos, Credentials und Dateisystem-Pfade.\", \"category\": \"productivity\"}, {\"name\": \"google-workspace\", \"description\": \"Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.\", \"category\": \"productivity\"}, {\"name\": \"linear\", \"description\": \"Linear: manage issues, projects, teams via GraphQL + curl.\", \"category\": \"productivity\"}, {\"name\": \"maps\", \"description\": \"Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.\", \"category\": \"productivity\"}, {\"name\": \"nano-pdf\", \"description\": \"Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).\", \"category\": \"productivity\"}, {\"name\": \"notion\", \"description\": \"Notion API via curl: pages, databases, blocks, search.\", \"category\": \"productivity\"}, {\"name\": \"ocr-and-documents\", \"description\": \"Extract text from PDFs/scans (pymupdf, marker-pdf).\", \"category\": \"productivity\"}, {\"name\": \"powerpoint\", \"description\": \"Create, read, edit .pptx decks, slides, notes, templates.\", \"category\": \"productivity\"}, {\"name\": \"godmode\", \"description\": \"Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.\", \"category\": \"red-teaming\"}, {\"name\": \"arxiv\", \"description\": \"Search arXiv papers by keyword, author, category, or ID.\", \"category\": \"research\"}, {\"name\": \"blogwatcher\", \"description\": \"Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.\", \"category\": \"research\"}, {\"name\": \"llm-wiki\", \"description\": \"Karpathy's LLM Wiki: build/query interlinked markdown KB.\", \"category\": \"research\"}, {\"name\": \"polymarket\", \"description\": \"Query Polymarket: markets, prices, orderbooks, history.\", \"category\": \"research\"}, {\"name\": \"research-paper-writing\", \"description\": \"Write ML papers for NeurIPS/ICML/ICLR: design→submit.\", \"category\": \"research\"}, {\"name\": \"openhue\", \"description\": \"Control Philips Hue lights, scenes, rooms via OpenHue CLI.\", \"category\": \"smart-home\"}, {\"name\": \"xurl\", \"description\": \"X/Twitter via xurl CLI: post, search, DM, media, v2 API.\", \"category\": \"social-media\"}, {\"name\": \"debugging-hermes-tui-commands\", \"description\": \"Debug Hermes TUI slash commands: Python, gateway, Ink UI.\", \"category\": \"software-development\"}, {\"name\": \"hermes-agent-skill-authoring\", \"description\": \"Author in-repo SKILL.md: frontmatter, validator, structure.\", \"category\": \"software-development\"}, {\"name\": \"node-inspect-debugger\", \"description\": \"Debug Node.js via --inspect + Chrome DevTools Protocol CLI.\", \"category\": \"software-development\"}, {\"name\": \"plan\", \"description\": \"Plan mode: write markdown plan to .hermes/plans/, no exec.\", \"category\": \"software-development\"}, {\"name\": \"python-debugpy\", \"description\": \"Debug Python: pdb REPL + debugpy remote (DAP).\", \"category\": \"software-development\"}, {\"name\": \"requesting-code-review\", \"description\": \"Pre-commit review: security scan, quality gates, auto-fix.\", \"category\": \"software-development\"}, {\"name\": \"spike\", \"description\": \"Throwaway experiments to validate an idea before build.\", \"category\": \"software-development\"}, {\"name\": \"subagent-driven-development\", \"description\": \"Execute plans via delegate_task subagents (2-stage review).\", \"category\": \"software-development\"}, {\"name\": \"systematic-debugging\", \"description\": \"4-phase root cause debugging: understand bugs before fixing.\", \"category\": \"software-development\"}, {\"name\": \"test-driven-development\", \"description\": \"TDD: enforce RED-GREEN-REFACTOR, tests before code.\", \"category\": \"software-development\"}, {\"name\": \"writing-plans\", \"description\": \"Write implementation plans: bite-sized tasks, paths, code.\", \"category\": \"software-development\"}], \"categories\": [\"3d-printing\", \"autonomous-ai-agents\", \"creative\", \"data-science\", \"devops\", \"email\", \"gaming\", \"github\", \"maker-electronics\", \"mcp\", \"media\", \"mlops\", \"note-taking\", \"productivity\", \"red-teaming\", \"research\", \"smart-home\", \"social-media\", \"software-development\"], \"count\": 89, \"hint\": \"Use skill_view(name) to see full content, tags, and linked files\"}", "tool_call_id": "functions.skills_list:3", "timestamp": "2026-05-13T12:35:48.165268"}