rca
Skill1 starsChanged 8 months agoMITView on GitHub
Root cause analysis for bugs, incidents, failed tests, build errors, outages, and unexpected behavior. Use when the user asks for RCA, root cause, why something failed, or asks to diagnose a problem from code, logs, tests, traces, tickets, or terminal output.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- korya/swd-skillstheir own version, first seen Nov 1, 2026
- ashe-li/agent-skillstheir own version, first seen Oct 29, 2026
- matthull/my-skillstheir own version, first seen Oct 20, 2026
- rubixkube-io/rubixkube-for-aitheir own version, first seen Oct 20, 2026
- udecode/dotaitheir own version, first seen Oct 13, 2026
- google/adk-samplestheir own version, first seen Oct 13, 2026
Used with
Projects with it also use handoff and tdd.
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.
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 4 projects that use this
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 3 projects that use this
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- google/adk-recipes★ 11ksame name
- google/adk-samples★ 11ksame name
- udecode/dotai★ 1.2ksame name
- kagenti/kagenti★ 303same name
- rsml/tutor★ 4same name
- PatriotAgenticLLC/better_claude_skillz★ 3same name
- allanbian1017/skills★ 2same name
- ashe-li/agent-skills★ 2same name
- korya/swd-skills★ 2same name
- ssv445/claude-skills★ 2same name
5 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 repository33 other files it gives its agents.
- argocdSkill
- c-cpp-compilersSkill
- coding-guidelinesSkill
- devops-iac-engineerSkill
- dag-flowdSkill
- flowd-rules-authorSkill
- frontend-designSkill
- ghSkill
- grafana-dashboardsSkill
- helmSkill
- kustomizeSkill
- legalizerSkill
- lua-projectsSkill
- markdown-documentationSkill
- mermaid-diagramsSkill
- meta-cognition-parallelSkill
- podmasterSkill
- practical-haskellSkill
- researcherSkill
- security-auditSkill
- solidity-securitySkill
- svg-genSkill
- tdd-red-green-refactorSkill
- tmux-masterySkill
- tokenomics-designSkill
- ultimate-dbSkill
- ultimate-nixosSkill
- ultimate-rustSkill
- ultimate-web3Skill
- web3-frontendSkill
- web3-testingSkill
- web3-whitepaperSkill
- ziglangSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Prefer causes supported by code, logs, tests, config, version changes, or reproducible behavior.
- Distinctive: line 18
If evidence is incomplete, say what is unknown and name the next smallest check.
- Distinctive: line 22
Use this format unless the user asks otherwise:
- Distinctive: line 40
Do not speculate beyond the evidence.
- Distinctive: line 41
Do not recommend broad rewrites unless the evidence points there.
- Distinctive: line 42
Do not hide uncertainty.
- Distinctive: line 43
When multiple causes are plausible, rank them by evidence and propose one discriminating check.
“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Root Cause Analysis
Goal
Find the most likely root cause from available evidence. Stay brief, explicit, and falsifiable.
Method
- Identify the context: language, framework, runtime, toolchain, environment, and failure mode.
- Separate observed facts from assumptions. Do not invent missing logs, code paths, services, timings, or user actions.
- Trace backward from the symptom to the earliest credible cause.
- Prefer causes supported by code, logs, tests, config, version changes, or reproducible behavior.
- If evidence is incomplete, say what is unknown and name the next smallest check.
Output
Use this format unless the user asks otherwise:
Root cause: <one concise sentence>
Evidence:
- <fact that supports the cause>
- <fact that supports the cause>
Fix:
- <smallest corrective action>
Confidence: <high|medium|low> because <short reason>Rules
- Be concise. Do not pad with process language.
- Do not speculate beyond the evidence. Label hypotheses as hypotheses.
- Do not recommend broad rewrites unless the evidence points there.
- Do not hide uncertainty.
- When multiple causes are plausible, rank them by evidence and propose one discriminating check.
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.