ci-triage
Skill2 starsChanged 8 days agoMITView on GitHub
定位远程 CI 流水线失败;仅在根因未明时转本地调试。
17 other projects use a version of this.
Adopted by
Most recently taken up by
- TanKaizokuO/claude-skillstheir own version, first seen Nov 8, 2026
- me-cedric/agent-compasstheir own version, first seen Nov 1, 2026
- juzorei/ci-autopsytheir own version, first seen Nov 1, 2026
- andymai/brepjstheir own version, first seen Oct 9, 2026
- hyperledger-cacti/cactitheir own version, first seen Oct 9, 2026
- hyperledger-labs/splicetheir own version, first seen Oct 9, 2026
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- NewFuture/DDNS★ 4.7ksame name
- nubjs/nub★ 4.4ksame name
- Mentra-Community/MentraOS★ 2.4ksame name
- levy-street/world-of-claudecraft★ 2.3ksame name
- ls1intum/Artemis★ 829same name
- hyperledger-cacti/cacti★ 412same name
- andymai/brepjs★ 140same name
- hyperledger-labs/splice★ 122same name
- fair-acc/gnuradio4★ 117same name
- 5throck/ai-workspace-standards★ 25same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- ai-engineering-collaborationSkill
- aitasks-maintenanceSkill
- change-impact-analysisSkill
- code-reviewSkill
- frontend-ui-uxSkill
- plan-executionSkill
- requirements-framingSkill
- systematic-debuggingSkill
- test-driven-changeSkill
- verification-gateSkill
The file
Files
CI/构建流水线失败定位
定位 CI 或构建失败的类型、根因和修复计划。未获实施授权时只读分析。
流程
- 识别 provider:核对 GitHub Actions、GitLab CI 或 Jenkins 等远程 provider;仅不熟悉该 provider 的日志获取方式时读取 references/providers.md。本地构建失败且根因未明时才需要
systematic-debugging,根因已明时在已有授权内直接处理。 - 获取失败证据:先读取失败步骤、完整异常链及必要前后文,记录 job/stage、命令、commit、环境和退出码;证据不足再扩大日志范围,不只看折叠摘要。
- 分类失败:区分代码(编译/测试/Lint/类型)、环境(runner/工具链/资源/缓存/超时)、依赖(解析/冲突/registry/锁文件)和外部服务(API/数据库/网络/凭证)。
- 提取证据:保留失败命令、错误消息和最小上下文,避免只凭最后一行判断。
- 给出计划:说明根因依据、修改点、验证命令和回滚边界;证据不足时标记待确认。
授权边界
纯归因请求只读;用户已要求修复时在原范围内继续最小修复,不重复询问实施授权。证据不足的结论标记未验证;只有仍需本地复现或根因实验时需要 systematic-debugging,未知共享行为或契约影响才需要影响分析。由入口统一安排下一阶段;独立使用时以当前能力推进,不因规则引用自动加载专项。不得为诊断擅自重跑部署或其他有外部副作用的 job。
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
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.

