why
Skill0 starsChanged 4 months agoMITView on GitHub
Use when someone asks why the code is the way it is - "why do we do it this way", "who decided this", "is this intentional or an accident". Recovers the reasoning behind a decision from the ADRs first, then git history, the tracker, and the out-of-scope record. Read-only.
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 repository18 other files it gives its agents.
- brainstormSkill
- buildSkill
- code-reviewSkill
- howSkill
- improve-codebase-architectureSkill
- inceptionSkill
- interview-loopSkill
- quickSkill
- recallSkill
- setupSkill
- surveySkill
- tddSkill
- to-issuesSkill
- to-prdSkill
- triageSkill
- validateSkill
- verifySkill
- worktreeSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.
0
Common
Most of the 106 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Look in the ADRs before anything else:
- Very specific: line 28
prd.md: - if the answer is "because the product needs it", this is where that lives - Very specific: line 29
.out-of-scope/: - if the question is why something *isn't* there, this is the record of concepts that were deliberately rejected, and it … - Very specific: line 34
glossary.md: - when the confusion is really about what a term means - Very specific: line 49
If the answer turns out to be "decided, but the decision was never written down", offer to capture it as an ADR through survey.
“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
groundwork:why
Recover the reasoning behind something, and be honest when the reasoning is not recoverable.
This is cheap in a groundwork repository because the artifacts already exist. Recording decisions is what ADRs are for; this is the skill that spends them.
1. Read the decisions first
Look in the ADRs before anything else:
docs/groundwork/adr/- project-wide decisions, including the implementation stackdocs/groundwork/features/NNNN-slug/adr/- decisions scoped to one feature
An ADR's Context is usually the actual answer, and its Consequences say what the project
signed up for. Check the Status: a Superseded ADR explains what someone used to think, and
the ADR that superseded it explains what changed their mind. Both are worth reporting, in that
order - the reversal is often the most useful part.
2. Then the rest, in descending order of reliability
prd.md- if the answer is "because the product needs it", this is where that lives.out-of-scope/- if the question is why something isn't there, this is the record of concepts that were deliberately rejected, and it exists precisely so the same idea does not get re-litigatedgit logandgit blame- the commit that introduced it, and the PR it came from- the tracker - the issue behind that PR, and any discussion on it
glossary.md- when the confusion is really about what a term means
3. Answer, and grade your own certainty
Say what the reason was and where you found it. Then say how confident you are, in these terms:
- Decided - an accepted ADR says so. Quote it.
- Recorded - a PRD, issue, or commit message states it, though nobody wrote it up as a decision.
- Inferred - you reconstructed it from the code and the history. Say so plainly, and say what would confirm it.
- Lost - nothing explains it. Say that instead of constructing a plausible story. An invented rationale is worse than an admitted gap, because it gets repeated.
If the answer turns out to be "decided, but the decision was never written down", offer to
capture it as an ADR through survey. That is how a Lost becomes a Decided for the next
person to ask.
This skill writes nothing on its own.
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.