L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Productivité · SKILL.md

Delegate

Delegate

Route tasks to sub-agents with optimal model selection, error recovery, and result verification.

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: Delegate slug: delegate version: 1.0.0 description: Route tasks to sub-agents with optimal model selection, error recovery, and result verification. homepage: https://clawic.com/skills/delegate metadata: clawdbot: emoji: 📤 displayName: Delegate

Core Rule

Spawn cost < task cost → delegate. Otherwise, do it yourself.

Model Tiers

TierModelsCostUse for
SmallHaiku, GPT-4o-mini, Gemini Flash~$0.25/1MSearch, summarize, format, classify
MediumSonnet, GPT-4o, Gemini Pro~$3/1MCode, analysis, synthesis
LargeOpus, o1, Gemini Ultra~$15/1MArchitecture, complex reasoning

Rule of thumb: Start with smallest tier. Escalate only if output quality insufficient.

Spawn Checklist

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 Recovery

Error TypeAction
Sub-agent timeout (>5 min no response)Kill and retry once
Wrong output formatRetry with stricter instructions
Task too complex for tierEscalate: Small→Medium→Large
Repeated failures (3x)Abort, report to user

Check errors.md for recovery patterns and escalation logic.

Verification

Never trust "done" without checking:

  • Code: Run tests, check syntax
  • Files: Verify they exist and have content
  • Data: Spot-check 2-3 items
  • Research: Confirm sources exist

Don't Delegate

  • Quick tasks (<30 seconds to do yourself)
  • Tasks needing conversation context
  • Anything requiring user clarification mid-task
Skills enregistrées