此内容尚未提供您的语言版本,正在以英文显示。

Agent Introspection Debugging

技能已验证活跃

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

目的

To enable AI agents to systematically debug and recover from failures, improving reliability and reducing token waste on repeated errors.

功能

Structured self-debugging workflow
Failure capture and state recording
Root-cause diagnosis based on known patterns
Contained recovery actions
Introspection report generation

使用场景

When an agent run fails repeatedly or loops
When an agent consumes tokens without progress
When context growth or prompt drift degrades output quality
To diagnose and recover from file-system or environment state mismatches

非目标

Feature verification after code changes (use verification-loop)
Framework-specific debugging when narrower skills exist
Runtime promises the current harness cannot enforce

安装

npx skills add affaan-m/everything-claude-code

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

质量评分

已验证

99 /100

1 day ago 分析

信任信号

最近提交1 day ago

GitHub 所有者 affaan-m

星标181k

下载量 7k

许可证MIT

网站ecc.tools

状态

查看源代码

类似扩展

Node Connect

100

Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.

技能

steipete

Openclaw Debugging

100

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code.

技能

steipete

Systematic Debugging

100

Systematic debugging methodology emphasizing root cause analysis over quick fixes

技能

bobmatnyc

Troubleshooting

100

使用 Chrome DevTools MCP 和文档来排查连接和目标问题。当 list_pages、new_page 或 navigate_page 失败，或服务器初始化失败时，触发此技能。

技能

ChromeDevTools

Root Cause Tracing

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

技能

NeoLabHQ

Query Agent Events

Bug-investigation tool for the Netdata agent-events ingestion namespace -- triage crashes, panics, fatals across the fleet by downloading events of interest and clustering locally. Covers the three transports (Cloud API and direct agent API are primary; ssh is operator-only), the verified AE_* field map and enum meanings, the dedup model (23h client-side per agent and event signature), the after-the-fact event timing (POST only on agent restart), and the Netdata systemd-journal plugin multi-value filter syntax (FIELD in A, B, C) AND ... Use when investigating crashes / panics / fatals; when grepping for events touching a specific function or file or version; when looking for regressions across versions; when an agent is reported crashing in a way you want to triage. Ships scripts get-events.sh and analyze-events.sh that fetch events with index-friendly filters and compute group-by stats. Defaults to last 24 hours and to the latest stable plus latest 2-3 nightlies.

技能

netdata