spec
Skill871 starsChanged 5 months agoMITView on GitHub
Turn a fuzzy feature idea into a self-contained SPEC.md by interviewing you first. Claude asks about scope, behavior, edge cases, and verification, then writes a spec a fresh implementation session can execute. Use before building anything non-trivial.
168 other projects use a version of this.
Adopted by
Most recently taken up by
- thistleknot/skillstheir own version, first seen Nov 8, 2026
- varelaia/claude-skills-publictheir own version, first seen Nov 8, 2026
- mrlemoos/galiciatheir own version, first seen Nov 8, 2026
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- standardagents/skillstheir own version, first seen Nov 8, 2026
- Surething-io/cockpittheir own version, first seen Nov 8, 2026
Used with
Projects with it also use backprop, ios-clean 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.
JuliusBrusseeSkillbackprop
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
Also in 4 projects that use this
Saqlain-811Skillios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Also in 5 projects that use this
Saqlain-811Skillios-fix
Autonomous iOS bug fixer. (gstack)
Also in 5 projects that use this
bastosSkillios-design-review
Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".
Also in 5 projects that use this
ShreyRaviSkillplan-tune
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.
Also in 7 projects that use this
timurgaleevSkilldocument-generate
Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.
Also in 6 projects that use this
- +2 more from Saqlain-811
Other versions168 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 168
- garrytan/gstack★ 141ksame name
- getsentry/sentry-react-native★ 1.8ksame name
- JuliusBrussee/cavekit★ 1.1ksame name
- kdlbs/kandev★ 1.1ksame name
- getsentry/sentry-dart★ 878same name
- codewithmukesh/dotnet-claude-kit★ 808same name
- SparkDevNetwork/Rock★ 701same name
- hyperlink-academy/leaflet★ 527same name
- strands-agents/box★ 503same name
- openclaw/openclaw-enterprise★ 454same name
158 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 repository14 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- catchupSkill
- claude-mdSkill
- context-budgetSkill
- debug-fixSkill
- explainSkill
- fix-issueSkill
- onboardSkill
- pr-reviewSkill
- refactorSkill
- setupdotclaudeSkill
- shipSkill
- tddSkill
- test-writerSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 145 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Run this in a session that already has the repo open, so the questions are informed by real code.
- Distinctive: line 25
Ask only what you can't answer from the code, in focused rounds (use AskUserQuestion.
- Very specific: line 37
Write SPEC.md at the project root (NOT in .claude/).
- Distinctive: line 72
Every spec states its verification step.
“Common” is measured: kept by at least 6 in 10 of the 145 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
Separate deciding WHAT to build from building it. Interview the user, ground the answers in the actual codebase, then write a self-contained SPEC.md a fresh session can execute without you in the room. $ARGUMENTS is an optional starting description.
Run this in a session that already has the repo open, so the questions are informed by real code.
Step 1: Explore enough to ask good questions
Skim the codebase for what the feature will touch: the relevant modules, existing patterns to match, the test setup, and any similar feature to model after. Read only — you're gathering context to interview well, not building.
Step 2: Interview with AskUserQuestion
Ask only what you can't answer from the code, in focused rounds (use AskUserQuestion; batch related questions). Cover:
- Scope & outcome — what does "done" look like from the user's side, and what's the smallest version worth shipping?
- Behavior — the happy path, then the edge cases (empty, error, concurrent, permission-denied) that actually matter here.
- Boundaries — what is explicitly OUT of scope for this iteration.
- Constraints — compatibility, performance, data/migration concerns, security-sensitive surfaces.
- Verification — how will we confirm it works end to end (a command, a test, an observable behavior)?
Where the code implies an answer, propose it as the default in the question rather than asking cold.
Step 3: Write SPEC.md
Write SPEC.md at the project root (NOT in .claude/). Make it self-contained — a fresh session with no memory of this conversation should be able to execute it:
# Spec: <feature>
## Goal
<what and why, 2-3 sentences>
## Scope
- In: <what this iteration delivers>
- Out: <explicitly deferred>
## Behavior
- <happy path>
- <edge cases and how each should behave>
## Touch points
- <exact files / modules / interfaces involved, as file:path — named, not vague>
## Constraints
- <compat, performance, security, data/migration>
## Verification
- <the exact end-to-end check: command to run, test to pass, or behavior to observe>
## Open questions
- <anything still undecided — none is ideal>Show the draft and confirm before writing. Then tell the user to run the implementation in a fresh session (/clear first) so it starts with a clean context and the spec as its brief.
Rules
- Interview before writing — do not skip Step 2 and guess the spec.
- Name real files and interfaces from the codebase; a spec full of placeholders isn't self-contained.
- Every spec states its verification step. If you can't name one, say so and ask the user how they'll check.
- One feature per spec. If the idea is really three features, say so and spec the one that was asked.
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.

