feature-spec
Skill4 starsChanged 46 days agoMITView on GitHub
Authors a feature specification (scenarios, rules, data, API operations, UI states, edge cases, security, accessibility, acceptance criteria) from the product spec. Produces docs/specs/features/F-NNN-name.md. Run per feature before stories.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- insight68/Skillstheir own version, first seen Nov 8, 2026
- CesarRivasP/feature-spectheir own version, first seen Oct 15, 2026
- PiloTracer/pilo.ai.logicbisontheir own version, first seen Oct 11, 2026
- akachandan1/proofstacktheir own version, first seen Oct 11, 2026
- edu6565/claude-skillstheir own version, first seen Oct 11, 2026
- Simone-Tarantino/godot-superpowerstheir own version, first seen Oct 11, 2026
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- WikiEducationFoundation/WikiEduDashboard★ 431same name
- PackmindHub/packmind★ 321same name
- https-deeplearning-ai/sc-spec-driven-development-files★ 310same name
- natnew/awesome-ai-scientists★ 20same name
- yasunori0418/skills★ 9same name
- insight68/Skills★ 5same name
- carreiras/claude-skills★ 4same name
- devexpert-io/harness-starter★ 4same name
- Simone-Tarantino/godot-superpowers★ 2same name
- CesarRivasP/feature-spec★ 1same name
10 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 repository52 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- testing/CLAUDE.mdCLAUDE.md
- a11y-auditSkill
- adoptSkill
- api-contractSkill
- architecture-decisionSkill
- architecture-reviewSkill
- backlogSkill
- brainstormSkill
- changelogSkill
- code-reviewSkill
- collaboration-protocolSkill
- create-storiesSkill
- data-modelSkill
- dependency-auditSkill
- deploySkill
- design-systemSkill
- dev-storySkill
- docsSkill
- game-conceptSkill
- hardenSkill
- helpSkill
- hotfixSkill
- impactSkill
- incidentSkill
- initSkill
- migrateSkill
- pentestSkill
- perf-auditSkill
- product-specSkill
- qa-planSkill
- refactorSkill
- release-checklistSkill
- retrospectiveSkill
- security-auditSkill
- setup-stackSkill
- skill-improveSkill
- skill-testSkill
- sprint-planSkill
- sprint-statusSkill
- stack-updateSkill
- startSkill
- story-doneSkill
- team-featureSkill
- team-gameSkill
- team-releaseSkill
- team-securitySkill
- tech-debtSkill
- test-setupSkill
- threat-modelSkill
- updateSkill
- ux-specSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
1
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 43
When HEAD is a story branch, name it and offer: switch to the default branch and commit there (Recommended — a pipeline-wide document) · …
“Common” is measured: kept by at least 6 in 10 of the 18 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
Feature Spec
Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.
Template .claude/docs/templates/feature-spec.md. Section by section; written after "May I write?". In the commands below, <hooks> is .claude/hooks/ in copy mode and ${CLAUDE_PLUGIN_ROOT}/hooks/ in plugin mode.
Phase 1: Context
docs/specs/product-spec.md. Missing → verdictBLOCKED (no product spec — run /product-spec first); write nothing. The feature must be in its scope; otherwise ask whether to add it.- Existing
docs/specs/features/*.md: F-NNN numbering, overlaps. technical-preferences.md: the API style (GraphQL or REST) shapes section 5.docs/architecture/api/api-contract.mdand the schema file atapi_contract_path(technical-preferences; defaultapi/schema.graphqlsfor a Go module,docs/architecture/api/schema.graphqlotherwise): existing types and operations.docs/architecture/threat-model.md.
Phase 2: Sections
1–3 Overview/scenarios/rules: questions to the user; formulas with a worked example.
4 Data: entities → propose what changes in data-model.md.
5 Contract: GraphQL — types/queries/mutations as SDL sketches; REST — endpoints; errors.
6 UI/states: the mandatory 5 states; copy (with the copy keys for a localised product); the product events the feature emits (name · trigger · properties, from the product spec §6 analytics list); for public pages, the SEO requirements (title/meta, structured data, canonical) that seo-specialist reviews in /dev-story.
7 Edge cases: a table, every row a concrete behaviour.
8 Security: object/field authorisation, limits, logging — ask security-lead via Task when the feature touches auth/money/files/personal data.
9 Accessibility/performance: concrete checks.
10 Dependencies: other features (by F-NNN), external services and packages this feature needs, each with how its health is checked (a health check, a status endpoint, a version pin); "none" is written as such.
11 Acceptance criteria: Given/When/Then, ≥ 1 per scenario and per risky edge case.
12 Open questions: what the sections above could not settle — each with who answers it and by when (a review, a spike, the user); a question that blocks a criterion is named next to that criterion. Empty is written as "none".
Phase 3: Review (per mode)
Mode from --review, else production/review-mode.txt, default lean. full: technical-director + design-lead + security-lead; lean: security-lead for sensitive features; solo: none. Verdict APPROVED / NEEDS REVISION. After NEEDS REVISION the edits go back to the same verifier for a short second pass, and the spec's verdict is the last review's; edits that were never re-checked are written down as NEEDS REVISION (edits unverified), never silently promoted to APPROVED.
Phase 4: Write
"May I write docs/specs/features/F-NNN-<slug>.md?" — one AskUserQuestion: write (Recommended) · show the draft/diff first · not now. Update the feature index in the product spec (section 5) with consent. After the "write" answer: touch .claude/.write-consent (rule 7 — the consent-guard hook checks the marker).
Phase 5: Commit (documents lane)
Right after the write, one commit gate (rule 7 (4), .claude/docs/git-workflow.md § Documents): one AskUserQuestion offering docs: feature spec F-NNN, staging exactly the written files — the feature spec and, when it was updated, the product spec's feature index. Record the gate before asking — <hooks>session-state.sh set Gate "/feature-spec Phase 5: commit?" — and clear it after the answer (<hooks>session-state.sh set Gate "—").
- On the default branch when no story work is in progress.
- When HEAD is a story branch, name it and offer: switch to the default branch and commit there (Recommended — a pipeline-wide document) · commit here (the document belongs to this story) · leave uncommitted.
- Code, configs, workflows and scripts never ride the
docs:commit.
Nothing is committed without the answer.
Verdict: APPROVED | NEEDS REVISION | BLOCKED. Next step — one AskUserQuestion: /create-stories F-NNN (Recommended) · /api-contract (if the contract changes) · /ux-spec; on BLOCKED: /product-spec (Recommended) · stop here.
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.

