build-feature
Skill1 starsChanged 5 months agoMITView on GitHub
Implement one vertical slice (UI → server action/route handler → DB) for a single PRD user story. Obeys path-scoped rules. Ends by invoking /code-review. Draft/approve at every boundary.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- Doist/todoist-aitheir own version, first seen Nov 9, 2026
- Doist/todoist-clitheir own version, first seen Nov 8, 2026
- sbradl/claude-skillstheir own version, first seen Oct 15, 2026
- koruworks/skillstheir own version, first seen Oct 15, 2026
- zyggy-org/zyggytheir own version, first seen Oct 13, 2026
- sirakinb/claude-code-skillstheir own version, first seen Oct 11, 2026
Used with
Projects with it also use fix-bug and refactor.
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.
JetBrainsSkillfix-bug
End-to-end bug fix workflow for the Exposed project. Accepts a GitHub issue (#NUMBER), YouTrack issue (EXPOSED-NUMBER), or YouTrack URL (https://youtrack.jetbrains.com/issue/EXPOSED-NUMBER). Fetches the issue, creates a failing reproducer test, commits on a new branch, implements the fix, validates, and opens a PR. Use this skill whenever the user wants to fix a bug from an issue tracker, mentions a EXPOSED issue number, or references a GitHub issue to fix.
Also in 5 projects that use this
GitHubSkillrefactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Also in 3 projects that use this
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- signerlabs/ShipSwift★ 3.3ksame name
- Doist/todoist-ai★ 563same name
- Doist/todoist-cli★ 331same name
- AlemTuzlak/skills★ 45same name
- Guild-Agents/guild★ 4same name
- garthcodes/claude-skills★ 2same name
- MaximSTH/meta-layer-starter★ 2same name
- zyggy-org/zyggy★ 2same name
- sirakinb/claude-code-skills★ 1same name
- koruworks/skills★ 0same name
4 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 repository22 other files it gives its agents.
- code-reviewSkill
- compliance-checkSkill
- design-architectureSkill
- design-pricingSkill
- design-schemaSkill
- design-uiSkill
- helpSkill
- launch-checklistSkill
- map-flowsSkill
- qa-planSkill
- scope-checkSkill
- security-auditSkill
- setup-billingSkill
- setup-deploySkill
- setup-stackSkill
- startSkill
- studio-statusSkill
- test-setupSkill
- threat-modelSkill
- validate-ideaSkill
- write-prdSkill
- write-testsSkill
The file
Files
Implement a complete, shippable vertical slice for exactly one user story: from the UI component through the server action or route handler down to the database query, including error handling and loading states. Non-autonomous: a draft plan is approved before any code is written, and each layer boundary is a checkpoint.
Phases
- Scope the story — read
docs/specs/prd.mdto identify the target user story and its acceptance criteria. If no argument was given, ask the user to specify. Confirm the story is IN_SCOPE (run/scope-checkmentally) and that relevant schema tables exist insupabase/migrations/. If tables are missing, stop and direct to/design-schema. - Draft implementation plan — propose the files that will be created or modified: the Next.js page/component (path under
app/), any shared components undercomponents/, the server action or route handler, and the database query. Show the plan as a file tree with a one-line description for each file. Get approval before writing anything. - Implement UI layer — write the React server and/or client components using shadcn/ui components as defined in
docs/specs/ui.md. Include empty, loading, and error states. Underfullreview, show each component before writing; underlean/solo, write after the plan is approved. - Implement server layer — write the server action (preferred for mutations) or route handler. Validate all inputs with Zod. Enforce tenant scoping by reading the tenant ID from the authenticated session — never accept tenant ID from client input. Handle errors explicitly and return typed results.
- Implement data layer — write the Supabase query using the server-side client (
createServerClientfrom@supabase/ssr). Confirm that RLS policies cover the operation; if a service-role bypass is needed, document why in a code comment and flag for review. - Invoke code review — after all files are written, invoke
/code-reviewautomatically. Do not declare the feature done until the review passes or all findings are acknowledged by the user. Once core features exist, design monetization with/design-pricingthen/setup-billing.
Output
Code changes across app/, components/, and lib/ for the targeted user story. Nothing is written without the plan being approved.
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.

