做什么
利用捕获、诊断、包含恢复和内检报告,对AI代理故障进行结构化自我调试工作流程
技能库 智客分类:Agent 工作流 agent-introspection-debugging
结构化自调试工作流程,用于AI代理故障,使用捕获,诊断,包含恢复,和内测报告. 当代理运行失败时使用,您需要可复制的诊断而不是重试.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
利用捕获、诊断、包含恢复和内检报告,对AI代理故障进行结构化自我调试工作流程
代理运行失败, 您需要可复制的诊断而不是重试
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Agent Introspection Debugging、When to Activate、Scope Boundaries、Four-Phase Loop、Phase 1: Failure Capture、Failure Capture。
文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.
Agent Introspection DebuggingWhen to ActivateScope BoundariesFour-Phase LoopPhase 1: Failure CaptureFailure CapturePhase 2: Root-Cause DiagnosisPhase 3: Contained RecoveryRecovery ActionPhase 4: Introspection ReportAgent Self-Debug ReportRecovery Heuristics
来源分类:skills.sh agent-skill
nameagent-introspection-debuggingdescription具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「agent-introspection-debugging」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-74c9c93510a3d100-%E4%BB%A3%E7%90%86%E5%86%85%E6%A3%80%E8%B0%83%E8%AF%95.html 请存为 .cursor/skills/agent-introspection-debugging/SKILL.md 或 .claude/skills/agent-introspection-debugging/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。
npx skills add 'https://github.com/affaan-m/ecc' --list
npx skills add 'https://github.com/affaan-m/ecc' --skill 'agent-introspection-debugging'
CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。
Use this skill when an agent run is failing repeatedly, consuming tokens without progress, looping on the same tools, or drifting away from the intended task.
This is a workflow skill, not a hidden runtime. It teaches the agent to debug itself systematically before escalating to a human.
Activate this skill for:
Do not use this skill as the primary source for:
verification-loopBefore trying to recover, record the failure precisely.
Capture:
Minimum capture template:
## Failure Capture
- Session / task:
- Goal in progress:
- Error:
- Last successful step:
- Last failed tool / command:
- Repeated pattern seen:
- Environment assumptions to verify:
Match the failure to a known pattern before changing anything.
| Pattern | Likely Cause | Check |
| --- | --- | --- |
| Maximum tool calls / repeated same command | loop or no-exit observer path | inspect the last N tool calls for repetition |
| Context overflow / degraded reasoning | unbounded notes, repeated plans, oversized logs | inspect recent context for duplication and low-signal bulk |
| ECONNREFUSED / timeout | service unavailable or wrong port | verify service health, URL, and port assumptions |
| 429 / quota exhaustion | retry storm or missing backoff | count repeated calls and inspect retry spacing |
| file missing after write / stale diff | race, wrong cwd, or branch drift | re-check path, cwd, git status, and actual file existence |
| tests still failing after “fix” | wrong hypothesis | isolate the exact failing test and re-derive the bug |
Diagnosis questions:
Recover with the smallest action that changes the diagnosis surface.
Safe recovery actions:
Do not claim unsupported auto-healing actions like “reset agent state” or “update harness config” unless you are actually doing them through real tools in the current environment.
Contained recovery checklist:
## Recovery Action
- Diagnosis chosen:
- Smallest action taken:
- Why this is safe:
- What evidence would prove the fix worked:
End with a report that makes the recovery legible to the next agent or human.
## Agent Self-Debug Report
- Session / task:
- Failure:
- Root cause:
- Recovery action:
- Result: success | partial | blocked
- Token / time burn risk:
- Follow-up needed:
- Preventive change to encode later:
Prefer these interventions in order:
Bad pattern:
Good pattern:
verification-loop after recovery if code was changed.continuous-learning-v2 when the failure pattern is worth turning into an instinct or later skill.council when the issue is not technical failure but decision ambiguity.workspace-surface-audit if the failure came from conflicting local state or repo drift.When this skill is active, do not end with “I fixed it” alone.
Always provide:
Agent 工作流
创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.
Agent 工作流
使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.
Agent 工作流
管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.
Agent 工作流
Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…