Configures autonomous heartbeat and cron-based proactive routines (e.g., morning briefing setup, unanswered-message scan cadence). Invoke when user is SETTING UP or MODIFYING a proactive routine, not when the routine itself fires. Cron crons execute their own logic — they do NOT load this skill. Triggers: "set up proactive check", "configure heartbeat", "add morning briefing", "tune cron cadence".
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Patterns and protocols for autonomous, proactive PA behavior.
Proactive > Reactive. Don't wait to be asked. Identify what the owner would want to know and surface it before he asks.
unanswered-messages skill)DREAMS.md + openclaw memory status --deep, then prune MEMORY.md only if Dreaming promoted stale/noisy itemserror status?2026.4.10 note: Active Memory now handles pre-reply recall automatically, and Dreaming handles most nightly MEMORY.md promotion. Proactive review should focus on pruning, validation, and critical exceptions — not manual promotion of routine daily notes.
Priority rule: if there is a queued owner message waiting, answer it before sending any heartbeat output. Owner DM beats heartbeat every time.
During heartbeats, rotate through these checks (2-4x per day):
1. Unanswered messages (last 30min)
2. Upcoming calendar events (<2h)
3. Cron job status (any errors?)
4. Email (urgent unread?)
Track last-checked in memory/heartbeat-state.json:
{
"lastChecks": {
"unanswered": 1700000000,
"calendar": 1700000000,
"crons": 1700000000,
"email": null
}
}
Only run each check if >25min since last run.
openclaw cron add \
--name "<check-name>" \
--every <interval> \
--session isolated \
--message "<what to check and what to do if found>" \
--to "<OWNER_PHONE>" \
--channel whatsapp \
--announce \
--timeout-seconds 60
| Name | Interval | Purpose |
|---|---|---|
unanswered-messages-check | 5m | Find unanswered messages |
morning-briefing | daily 7:00 IL | Morning summary to the owner |
ai-digest | daily 8:00 IL | AI news to Internal AI group |
billing-health-check | hourly | API key / billing status |
⚠️ [Issue type]
[1-line summary of what happened]
[Action taken or recommendation]
Before ending any task, ask: "Is there anything the owner would want to know that I haven't surfaced?"
Every proactive action taken (alert sent, issue caught, auto-fix applied) gets silently logged:
python3 /path/to/workspace/tools/eval_tracker.py log proactive_action "<description>" 2
This builds the quantitative record that proves proactive value over time.
After completing a task, identify and execute the obvious next step:
After completing a multi-step task (3+ tool calls, novel solution, likely to recur), trigger auto-skill-creator to capture it as a reusable skill before closing the task.
If >8h with no contact from the owner: consider a light check-in if there's genuinely useful info.
When reading a group message or DM:
Track when people (including PAs) say "I'll do X" or "אשלח" or "אעדכן". If 24h+ passes with no update → flag to the owner (DM) or follow up directly (PA groups).
When the owner opens a DM conversation:
Proactive ≠ verbose. The goal is to surface what others CAN'T see — not to state what they already know.
Never:
Always:
DO take initiative on:
ALWAYS ask before:
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
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).
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
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".
日本語の概要は準備中です。原文の説明を表示しています。
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".
日本語の概要は準備中です。原文の説明を表示しています。
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.).
日本語の概要は準備中です。原文の説明を表示しています。