agentleFS
Sign inStart free
edisonzerolamedisonzerolam/openclaw-skills/debug/SKILL.md

debug

Skill0 starsChanged 4 months agoMITView on GitHub

Trace errors in log files, parse stack traces, detect memory leaks, profile commands, and debug HTTP. 触发词：debug, diag, trace, stacktrace, crash, log. 不适用：非错误诊断类查询、代码审查。

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-discord, add-slack and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • +10 more from microsoft

The file

Create a free account to mount
Files
SKILL.md

需求路由

需求类型路由说明
trace /var/log/sysloglocaldebug-core.js trace
分析堆栈根本原因llmLLM 根因诊断
对比两个日志文件localdebug-core.js diff-logs
内存泄漏根因llmLLM 诊断

命令概览

命令路径用途
tracescripts/script.sh trace <file>日志错误模式分析
stacktracescripts/script.sh stacktrace <file>堆栈解析
leaksscripts/script.sh leaks --pid <id>内存泄漏检测
profilescripts/script.sh profile <cmd>性能剖析
diff-logsscripts/script.sh diff-logs <a> <b>日志差异对比
httpscripts/script.sh http <url>HTTP 调试（含 SSL/重定向/耗时）
selfcheckscripts/script.sh selfcheck脚本自检（语法/依赖/退出码）
formatscripts/script.sh format --output json|csv|md结构化输出

退出码：0=OK / 1=ERR_FOUND / 2=WARN / 3=PERM / 4=TIMEOUT / 5=CONFIG / 64=USAGE

详见 _knowledge/references/commands-detail.md。

模块化架构

scripts/
  script.sh          # 主路由器（~50行）
  config.toml        # 默认配置
  lib/               # exit_codes.sh, config.sh, common.sh
  cmd/               # 各命令独立 .sh 文件

config.toml 可调整默认值（pattern/max_depth/timeout 等），无需改代码。 详见 _knowledge/references/commands-detail.md#configtoml。

增强层索引

层级文件加载时机
L1SKILL.md（核心命令）首次加载
L2_knowledge/knowledge-health-check.mdSKILL.md 后
L2_knowledge/knowledge-error-patterns.md诊断/错误/修复触发
L3_knowledge/scripts/批量验证/调试触发
L3_knowledge/knowledge-windows-debug.mdwindows/powershell/bsod
L4_knowledge/references/专家模式（--expert / 复杂/长尾）

并行支持（[[PARALLEL]]）：leaks 多进程、profile 多命令、http 多端点、trace 多模式

参考文件

文件用途
_knowledge/references/commands-detail.md命令详细语法 + config.toml
_knowledge/references/self-learning.md自学习 + 事实核查 + 跨 skill 反馈
_knowledge/knowledge-error-patterns.md12 类错误模式库
_knowledge/knowledge-health-check.md健康检查标准
_knowledge/knowledge-windows-debug.mdWindows 调试
_knowledge/references/专家知识池（按领域）

故障与降级

场景处理
script.sh 自检失败跳过本地执行，回退到 LLM 诊断
fact_check.py 不可达回退到 exec 验证
专家知识库不可读跳过 L4 加载，使用 L1-L3 能力

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free