Decide where to save any piece of information — monday.com, local file, daily notes, or MEMORY.md. Use this skill before saving anything to ensure the right destination. Prevents local clutter and ensures the owner can access all relevant content in monday.com.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
2026.4.10 update: With Active Memory + Dreaming enabled, the default flow is now: raw fact → daily note first, Dreaming promotes later.
MEMORY.mdis for curated long-term rules, confirmed preferences, and critical exceptions.
Before saving anything, route it to the correct destination.
| Content Type | Destination | Notes |
|---|---|---|
| Competitor research | monday.com — Competitive Analysis doc | your monday.com workspace |
| Product briefs, strategy docs | monday.com — relevant doc | your monday.com workspace |
| Meeting notes | monday.com — Notetaker / item update | |
| Project tasks / tracking | monday.com — board item | |
| PA rules & preferences | MEMORY.md | Long-term only, distilled |
| Lessons learned | memory/daily/YYYY-MM-DD.md first | Dreaming promotes later if strong/repeated |
| Daily event log | memory/daily/YYYY-MM-DD.md | Raw log, not curated |
| WhatsApp conversation context | memory/whatsapp/groups/ or dms/ | Per-conversation, local |
| Cron state / job state | local JSON (data/ or inbox/) | Runtime state only |
| PA contact list | PA_LIST.md (local) | Source of truth for PA sync |
| Config / credentials | local only, never monday | Security |
| Skill files | workspace/skills/ | Never monday |
| Layer | Best for | Why |
|---|---|---|
| GitHub (private repo) | Agent state, memory, skills, .context | Version history, automated backup, private |
| monday.com | Research, docs, tasks, strategy | Searchable, shareable, owner-accessible |
| Local only | Runtime state, credentials, cron state | Speed, security, no sync needed |
Rule of thumb:
Load agent-specific IDs from .context file in this skill's directory:
CONTEXT_FILE="/path/to/workspace/skills/storage-router/.context"
[ -f "$CONTEXT_FILE" ] && source "$CONTEXT_FILE"
# Then use: $WORKSPACE_ID, $FOLDER_RESEARCH, $DOC_COMPETITIVE_ANALYSIS, etc.
If .context doesn't exist — use Structure Index doc (DOC_STRUCTURE_INDEX) from monday.com to find current IDs.
Workspace: your monday.com workspace Structure Index Doc: 39993682 (always check here for latest IDs)
| Content | Folder | Board/Doc ID |
|---|---|---|
| Competitor analysis | 📁 Research (20077300) | Board: 18406632346 / Doc: 39808656 |
| Market research | 📁 Research (20077300) | Board: 18406632334 |
| Technology deep dives | 📁 Research (20077300) | Per-tool board (see index) |
| Product brief | 📁 Product (20077301) | Board: 18406632301 / Doc: 39808645 |
| MVP planning | 📁 Product (20077301) | Board: 18406632217 |
| GTM strategy | 📁 GTM (20077298) | Board: 18406632223 |
| PA Rollout tracking | 📁 Operations (20077299) | Board: 18407159006 |
| Skills guide | 📁 Operations (20077299) | Board: 18407110746 |
For full index with all IDs: read doc 39993682 in monday.com before saving anything new.
Before saving any file or content, ask:
memory/daily/YYYY-MM-DD.mdWhen in doubt → monday.com for content, local for state, daily note before MEMORY.md for new learnings.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
AI Personal Assistant network skill. Use when: contacting another PA, coordinating with peer agents, scheduling meetings between owners, broadcasting messages, looking up contacts from the local PA directory, or performing any cross-PA task. Reads contact data from data/pa-directory.json in the workspace. Does NOT contain hardcoded contact data — each PA maintains their own directory file.
中文简介正在准备中。当前显示原文说明。
AI Personal Assistant network skill for multi-agent PA coordination. Use when: contacting another PA, coordinating with peer agents, scheduling meetings between owners, broadcasting messages to PA groups, or looking up contacts from the local PA directory. Reads contact data from data/pa-directory.json in the workspace.
中文简介正在准备中。当前显示原文说明。
Route and execute inter-PA coordination tasks in the OpenClaw multi-agent PA network. Triggers when: contacting another PA, passing a message between owners, broadcasting to a PA group, handling group lead/silence rules, or adding a new PA to the directory. NOT for: contact lookups (use contact-list skill), calendar invites (use meetings skill), or billing issues (use billing-monitor skill).
中文简介正在准备中。当前显示原文说明。
OpenClaw API gateway proxy for authenticated SaaS calls (100+ services in references/SERVICES.md). Use ONLY when making an HTTP request to a third-party service that requires the gateway's stored credentials. NOT for direct API calls with bearer tokens already in scope, NOT for monday.com (use monday-for-agents), NOT for WhatsApp (use heleni-whatsapp). Triggers: "call the X API", "fetch from <service>", "send to Slack via gateway", "use the gateway for".
中文简介正在准备中。当前显示原文说明。
Automatically creates new skills from complex problem-solving sessions. Triggers at the end of multi-step tasks that required novel approaches, debugging sessions, or workflow creation. Use when: a task took 3+ tool calls, involved a non-obvious solution, or established a pattern likely to recur. Also triggers on: "create a skill from this", "save this as a skill", "this should be a skill".
中文简介正在准备中。当前显示原文说明。
Monitor for API billing errors and alert the owner and admin immediately. Use when: an API billing error is detected, a peer PA reports a billing error, or during routine health checks. Handles detection, notification, and fallback model switching. Model-agnostic: works with any LLM provider (Anthropic, OpenAI, Google, etc.).
中文简介正在准备中。当前显示原文说明。