Claude-skill-registry delegation-triggers

Guidelines for when to delegate tasks to sub-agents vs handle directly. Use when deciding whether to use Explore, Plan, or other specialized agents for a task.

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/delegation-triggers" ~/.claude/skills/majiayu000-claude-skill-registry-delegation-triggers && rm -rf "$T"

manifest: skills/data/delegation-triggers/SKILL.md

Delegation Triggers

Decision Tree

Is this task...
    │
    ├─ Multi-file, independent units? ─► Parallel Orchestration
    │                                     (see complex-orchestrator)
    │
    ├─ Deep analysis / reasoning? ─────► Advanced General Purpose (Opus)
    │   ⚠️ High cost - use sparingly
    │
    ├─ Exploration / Research? ────────► Explore Agent
    │
    ├─ Planning / Design? ─────────────► Plan Agent
    │
    ├─ Simple & Direct? ───────────────► Execute Directly
    │
    └─ Unclear scope? ─────────────────► Decompose First

Quick Reference

Signal	Agent	Trigger Phrases
Multi-file	Parallel (complex-orchestrator)	"all files", "across codebase", "every X"
Deep analysis	Advanced (Opus)	"thoroughly", "しっかり", "implications"
Find/Understand	Explore	"where is", "how does", "find all"
Design/Architect	Plan	"how should I", "design", "best approach"
Simple edit	Direct	"fix", "add field", "update text"

3-Question Test

Enough context? → No: Explore first
Multiple approaches? → Yes: Plan first
Touch 3+ unseen files? → Yes: Explore/Plan first

Parallel Execution

Launch in single message for parallel:

Task({ description: "A", ... })
Task({ description: "B", ... })  // runs parallel with A

For dependencies, use waves:

Wave 1: shared dependency
Wave 2: parallel consumers (after Wave 1)

For detailed examples and anti-patterns, see

reference.md