القائمة
Route tasks to sub-agents with optimal model selection, error recovery, and result verification.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Generate Ian-style English article illustrations. Use for user requests that need weird, clean, hand-drawn body images, article illustrations, shot lists, or edit/remove-title tasks for English articles, posts, blogs, Notion docs, workflows, methods, structures, states, metaphors, or viewpoints. Default to the Xiaohei IP, pure white hand-drawn look, sparse red/orange/blue annotations, and a clean but imaginative visual style. Do not use for generic illustration, PPT, commercial brand art, children's cartoons, or non-Xiaohei image requests unless the user explicitly asks for Ian/Xiaohei style.
Robust BMKG (Indonesian Meteorological Agency) monitoring for weather and earthquake alerts. Track conditions in project locations across Indonesia, especially Balikpapan and Kalimantan region.
Draft Gmail replies in Fanani's real email style using Gog CLI + OpenClaw. Uses thread-aware triage, no extra Gmail labels, and mandatory Telegram notification after draft creation.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Generate and send automated morning briefing reports via Telegram. Combines Gmail, Calendar, Tasks, Gold prices, Server health, Weather, and optional Livescore into a single daily summary.
Use when installing, configuring, troubleshooting, securing, or performing a health check on OpenClaw gateway setups — including channel integrations, exec approvals, cron jobs, agent sessions, and operational maintenance.
| name | Delegate |
| description | Route tasks to sub-agents with optimal model selection, error recovery, and result verification. |
Spawn cost < task cost → delegate. Otherwise, do it yourself.
| Tier | Models | Cost | Use for |
|---|---|---|---|
| Small | Haiku, GPT-4o-mini, Gemini Flash | ~$0.25/1M | Search, summarize, format, classify |
| Medium | Sonnet, GPT-4o, Gemini Pro | ~$3/1M | Code, analysis, synthesis |
| Large | Opus, o1, Gemini Ultra | ~$15/1M | Architecture, complex reasoning |
Rule of thumb: Start with smallest tier. Escalate only if output quality insufficient.
Every spawn must include:
1. TASK: Single clear deliverable (not "help with X")
2. MODEL: Explicit tier choice
3. CONTEXT: Only files/info needed (never full history)
4. OUTPUT: Expected format ("return JSON with...", "write to file X")
5. DONE: How to signal completion
Check templates.md for copy-paste spawn templates.
| Error Type | Action |
|---|---|
| Sub-agent timeout (>5 min no response) | Kill and retry once |
| Wrong output format | Retry with stricter instructions |
| Task too complex for tier | Escalate: Small→Medium→Large |
| Repeated failures (3x) | Abort, report to user |
Check errors.md for recovery patterns and escalation logic.
Never trust "done" without checking: