why
Skill1 starsChanged 3 months agoMITView on GitHub
Investigate why code or a design has its current shape using source history and available organizational evidence. Use for rationale, trade-offs, regressions, postmortems, thresholds, and historical design questions.
112 other projects use a version of this.
Adopted by
Most recently taken up by
- Yeachan-Heo/oh-my-claude-sisyphustheir own version, first seen Nov 8, 2026
- Loner1024/skillstheir own version, first seen Nov 8, 2026
- caidanw/skillstheir own version, first seen Nov 8, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 8, 2026
- endqwerty/endstacktheir own version, first seen Nov 8, 2026
- tristanphvn/keeltheir own version, first seen Nov 8, 2026
Used with
Projects with it also use addskill, apply-firmware 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.
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
- ryanportfolioSkill
apply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +10 more from ryanportfolio
Other versions112 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 112
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- backnotprop/pstack★ 3.8ksame name
- moeru-ai/xsai★ 667same name
- jtaroreh/agystack★ 128same name
- uzairansaruzi/p3-stack★ 126same name
- Dimon94/dverity★ 107same name
- Dimon94/skills★ 107same name
- dsebban/skills★ 71same name
- Anuj7411/sipcode★ 46same name
102 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 repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- blast-radiusSkill
- broSkill
- codebase-designSkill
- code-reviewSkill
- confluence-workflowSkill
- creating-a-pr-mrSkill
- defuddleSkill
- diagram-designSkill
- docxSkill
- domain-modelingSkill
- engineering-principlesSkill
- forgejo-cliSkill
- frontend-designSkill
- gh-cliSkill
- git-conventional-commitsSkill
- git-working-agreementSkill
- glab-cliSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- howSkill
- improve-codebase-architectureSkill
- jira-workflowSkill
- json-canvasSkill
- k8s-opsSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-markdownSkill
- openspec-workflowSkill
- pdfSkill
- pptxSkill
- prototypeSkill
- researchSkill
- setup-matt-pocock-skillsSkill
- skill-minerSkill
- technical-writingSkill
- theme-factorySkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- unslopSkill
- wayfinderSkill
- writing-for-agentsSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 106 edited versions we read keep these.
5
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 18
Treat the user's suggested rationale as a hypothesis to test, not a conclusion to confirm.
- Distinctive: line 32
Search every available and relevant category.
- Distinctive: line 39
Verify high-value citations and synthesize without strengthening confidence language.
- Distinctive: line 42
Use git for local history and the repository host CLI for pull requests when available.
- Distinctive: line 64
If the investigation informs a change, finish with Preserve / Change / Avoid / Risk constraints.
“Common” is measured: kept by at least 6 in 10 of the 106 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
Why
Investigate intent as a historical question. Code proves mechanics, not motive.
Evidence Rules
- Collect evidence before choosing a narrative.
- Cite claims about intent to commits, pull requests, issues, documents, chat links, incidents, dashboards, or comments.
- Label uncited claims as inference.
- Surface contradictions and competing hypotheses.
- Treat the user's suggested rationale as a hypothesis to test, not a conclusion to confirm. Seek evidence for and against it, and report when the record does not support it.
- State unavailable sources and unanswered questions.
- Match wording to confidence; reserve "because" for direct evidence.
Process
- Identify the target, question, files, line ranges, and key symbols.
- Build a code anchor with blame and history through renames. Extract related commits, pull requests, ticket IDs, comments, and tests.
- Discover evidence sources available in the current environment. Consider: source control, issue trackers, long-form documents, team chat, observability, error tracking, analytics, and incident records.
- Search every available and relevant category. Use one narrowly scoped read-only investigator per category when parallel delegation is available; otherwise search sequentially. Record queries and null results.
- Give investigators the same code anchor and question. Present any user-suggested rationale as one candidate and require evidence for and against it. Require direct evidence, indirect evidence, contradictions, gaps, and leads. They must not mutate external systems.
- Verify high-value citations and synthesize without strengthening confidence language.
Use git for local history and the repository host CLI for pull requests when
available. Use specialized issue, document, or observability tools only when
the current environment exposes them and the user's access permits it.
Confidence
- Direct: a source explicitly states the rationale.
- Supported: several indirect sources agree and no evidence contradicts it.
- Inferred: plausible from the record but never stated.
- Speculative: weak evidence or several equally plausible explanations.
- Unknown: the searched record does not answer the question.
Output
- Question and code anchor
- Direct evidence, with citations
- Reasonable inferences, with the inference chain
- Competing hypotheses, including evidence for and against
- Unknowns and contradictions
- Sources consulted, including empty, unavailable, and irrelevant categories
- Confidence summary
If the investigation informs a change, finish with Preserve / Change / Avoid / Risk constraints. The task is complete when every available relevant source has a recorded outcome and every rationale claim has a confidence tier.
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.