{"id":50708128,"url":"https://github.com/meiiie/structured-root-cause-research-skill","last_synced_at":"2026-06-09T13:02:18.076Z","repository":{"id":356947790,"uuid":"1234719524","full_name":"meiiie/structured-root-cause-research-skill","owner":"meiiie","description":"Portable SKILL.md for evidence-based root-cause analysis across Claude Code, Codex, and AI coding agents","archived":false,"fork":false,"pushed_at":"2026-05-10T14:59:20.000Z","size":8,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-10T16:35:43.542Z","etag":null,"topics":["5-whys","agent-skills","ai-agents","claude-code","codex","debugging","postmortem","root-cause-analysis","security-review","skill-md","software-engineering","sre"],"latest_commit_sha":null,"homepage":"https://github.com/meiiie/structured-root-cause-research-skill","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/meiiie.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-10T14:56:19.000Z","updated_at":"2026-05-10T14:59:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/meiiie/structured-root-cause-research-skill","commit_stats":null,"previous_names":["meiiie/structured-root-cause-research-skill"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/meiiie/structured-root-cause-research-skill","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meiiie%2Fstructured-root-cause-research-skill","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meiiie%2Fstructured-root-cause-research-skill/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meiiie%2Fstructured-root-cause-research-skill/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meiiie%2Fstructured-root-cause-research-skill/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/meiiie","download_url":"https://codeload.github.com/meiiie/structured-root-cause-research-skill/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meiiie%2Fstructured-root-cause-research-skill/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34107866,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-09T02:00:06.510Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["5-whys","agent-skills","ai-agents","claude-code","codex","debugging","postmortem","root-cause-analysis","security-review","skill-md","software-engineering","sre"],"created_at":"2026-06-09T13:02:18.018Z","updated_at":"2026-06-09T13:02:18.068Z","avatar_url":"https://github.com/meiiie.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Structured Root-Cause Research Skill\n\nPortable `SKILL.md` for evidence-based root-cause analysis in AI coding agents.\n\nIt helps Codex, Claude Code, and other file-based agents avoid patch fixes by forcing a lightweight research loop:\n\n1. frame the problem\n2. gather an evidence ledger\n3. summarize root cause with evidence-based 5 Whys\n4. map data, control, error, and trust flows\n5. compare against named practices or standards\n6. produce a verifiable recommendation\n\nThis is not a \"show chain-of-thought\" prompt. It asks agents to provide concise reasoning summaries, assumptions, evidence, confidence levels, and verification plans.\n\n## Install\n\n### Claude Code\n\n```bash\nmkdir -p ~/.claude/skills/structured-root-cause-research\ncp SKILL.md ~/.claude/skills/structured-root-cause-research/SKILL.md\n```\n\n### Codex\n\n```bash\nmkdir -p ~/.codex/skills/structured-root-cause-research\ncp SKILL.md ~/.codex/skills/structured-root-cause-research/SKILL.md\ncp -r agents ~/.codex/skills/structured-root-cause-research/\n```\n\n### Project-local\n\n```bash\nmkdir -p .agents/skills/structured-root-cause-research\ncp SKILL.md .agents/skills/structured-root-cause-research/SKILL.md\ncp -r agents .agents/skills/structured-root-cause-research/\n```\n\n## Use\n\nAsk your agent:\n\n```text\nUse $structured-root-cause-research to analyze why this bug keeps coming back and propose the smallest durable fix.\n```\n\nOther good triggers:\n\n- \"find the root cause\"\n- \"do not patch around this\"\n- \"run 5 Whys\"\n- \"compare against best practices\"\n- \"map the data/control/error flow\"\n- \"analyze the trust boundary\"\n\n## When It Helps\n\n- Complex bugs where a quick patch keeps failing\n- Architecture reviews before a refactor\n- Security reviews that need source-control-sink-impact clarity\n- Incident analysis and postmortem prep\n- Product or offer research where the next decision needs evidence\n\n## Example Outputs\n\nSee:\n\n- [examples/backend-bug.md](examples/backend-bug.md)\n- [examples/security-review.md](examples/security-review.md)\n- [examples/customer-offer-research.md](examples/customer-offer-research.md)\n\n## Design Principles\n\n- Evidence before recommendations\n- Reasoning summary, not private chain-of-thought\n- Smallest durable change over broad rewrites\n- Named practices over vague \"SOTA\" claims\n- Explicit confidence when evidence is incomplete\n\n## Why This Exists\n\nAI coding agents are good at generating fixes quickly. They are less reliable when the task needs disciplined investigation before action. This skill gives the agent a compact operating procedure for thinking like a careful engineer: gather evidence, identify the root cause, compare against better practice, and verify the outcome.\n\n## License\n\nMIT\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmeiiie%2Fstructured-root-cause-research-skill","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmeiiie%2Fstructured-root-cause-research-skill","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmeiiie%2Fstructured-root-cause-research-skill/lists"}