跳到正文
cccskills
免费在 GitHub 公开

agent-test-delegation

Test agent delegation patterns to verify hierarchy and escalation paths. Use after modifying agent structure.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md1.9 KB
  • metadata.json1.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Agent Delegation Testing

Verify agent hierarchy, delegation chains, and escalation paths.

When to Use

  • After modifying agent hierarchy
  • Verifying escalation paths work correctly
  • Troubleshooting delegation issues
  • CI/CD validation before merge

Quick Reference

# Test all delegation patterns
python3 tests/agents/test_delegation.py .claude/agents/

# Test specific agent delegation
./scripts/test_agent_delegation.sh implementation-specialist

# Visualize delegation tree
./scripts/visualize_delegation.sh

What Gets Tested

Hierarchy levels: Agents delegate to lower levels, escalate to higher levels

Delegation chains: L0 → L1 → L2 → L3 → L4 (proper tree structure)

Circular dependencies: Detect A → B → C → A patterns

Reference validity: All delegates_to/escalates_to targets exist

Level consistency: Level values correct and levels don't skip improperly

Validation Rules

RuleExample ✅Wrong ❌
Delegate downwardL2 → L3L3 → L2
Escalate upwardL3 → L2L3 → L4
No circlesA → B, A → CA → B → A
Valid refsExisting agentNonexistent agent

Common Issues

Circular dependency: Agent A → Agent B → Agent A

  • Fix: Break circle by restructuring delegation

Skip-level delegation: L2 → L4 (skips L3)

  • Fix: Document exception in agent description

Orphaned agent: No other agent delegates to it

  • Fix: Add delegation or remove if unused

References

  • /agents/delegation-rules.md - Complete delegation guidelines
  • .claude/agents/ - All agent configurations
  • CLAUDE.md - Hierarchy documentation

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mandates absolute deconstruction, mathematical proof chains, and ≥95% derived certainty. Zero-tolerance for heuristics or sentiment-based reasoning. Shortcuts are defined as intentional hallucinations.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

2agent

免费

Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

Appends relevant hashtags to journal entries based on content analysis. Intended for LLM execution.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

add-agent

免费

Add a new AI coding agent to Agent Sandbox. Creates all required files (Dockerfile, templates, CI, docs) and wires the agent into the CLI, proxy, and build system.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

Add a new property to the AI agents database. Use when the user wants to add, create, or introduce a new column, property, field, or feature to track across all agents in the comparison matrix. Handles all four required steps - database updates, groups.json, table display, and GitHub issue templates.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

Add new Agent templates to the meta-agent-skills framework.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

查看 diegosouzapw 的全部技能

报告此技能的问题