agentleFS
Sign inStart free
patmeh1patmeh1/product-docs-kit/.claude/skills/implement-feature/SKILL.md

implement-feature

Skill0 starsChanged 2 months agoMITView on GitHub

Implement a fully specified requirement in code with tests, working from the PRD and downstream documents. Use after /add-feature has propagated a feature through the documentation and the user is ready to build it. Also use for "build FR-", "implement the requirement", "code this feature", or "write the feature and its tests".

  • Reads credentials

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use prepare-release, create-skill and 4 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.
  • ShopifySkill

    prepare-release

    Prepare the changeset-release/main branch for release by syncing version.ts files and running pnpm install

    Also in 3 projects that use this

  • ElasticSkill

    create-skill

    Interactively create a new Claude Code skill and add it to the elastic-docs-skills catalog. Use when the user wants to generate a new skill, scaffold a slash command, or build automation for docs tasks.

    Also in 3 projects that use this

  • MicrosoftSkill

    playwright-cli

    Automate browser interactions, test web pages and work with Playwright tests.

    Also in 3 projects that use this

  • VercelSkill

    find-skills

    Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read, in this order:

    line 12
  2. Distinctive:

    Check authorisation per resource, not just per route.

    line 49
  3. Very specific:

    Commit secrets or .env files

    line 59
  4. Distinctive:

    Run and show actual output for: lint, typecheck, unit, integration, e2e, build.

    line 64
  5. Very specific:

    Update docs/09-traceability-matrix.md with the code paths and test IDs, set the requirement to In Progress, and confirm the CHANGELOG.md …

    line 66

“Common” is measured: kept by at least 6 in 10 of the 25 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Implement a Feature From the Specification

Build a requirement that is already specified. The spec is the contract.

Before writing any code

Read, in this order:

  1. AGENTS.md
  2. docs/01-prd.md → the requirement and its acceptance criteria
  3. docs/02-user-flows.md → flows and screens
  4. docs/03-design-system.md → tokens and components you must reuse
  5. docs/04-architecture.md → structure and layering
  6. docs/12-tech-stack.md → what is installed, and at which versions
  7. docs/05-data-model.md → schema and migration policy
  8. docs/06-api-contract.md → the contract you must honour
  9. docs/07-security-privacy.md → authorisation rules
  10. docs/08-test-plan.md → the test cases you must satisfy
  11. docs/adr/ → decisions you must not contradict

Then read the full procedure in prompts/04-implement-feature.md.

Confirm to the user: the requirement, the acceptance criteria, the TC- cases you will write, and your implementation plan. Wait for their go-ahead.

If the specification is inadequate, stop and say so. Do not fill gaps by invention — send the user back to /add-feature.

Order of work

  1. Data layer — schema and migration, additive only
  2. Business logic in lib/ — with unit tests
  3. API endpoints — matching the contract exactly, with integration tests
  4. UI components — reusing existing design system components and tokens
  5. Screens — with all cross-cutting states: loading, empty, error, unauthorised, not-found
  6. E2E test covering the user flow

Non-negotiables

  • Reuse existing components. Extend rather than duplicate — and update the design system document if you extend.
  • Never hard-code a colour, spacing value, font size, or duration. Use tokens.
  • Validate on the server with the shared schema. Client validation is a convenience, never a control.
  • Check authorisation per resource, not just per route.
  • Name tests with their IDs: test('FR-014 / TC-058: ...')
  • Any new dependency needs a TECH- row; any new env var needs a CFG- row plus an .env.example line — both in docs/12-tech-stack.md.

Never

  • Modify an existing passing test to accommodate new code
  • Weaken or skip a CI check
  • Bump a dependency or runtime version as a side effect — that is a separate UPG- PR
  • Commit secrets or .env files
  • Implement anything outside the requirement's scope — list it at the end instead

Before reporting done

Run and show actual output for: lint, typecheck, unit, integration, e2e, build.

Update docs/09-traceability-matrix.md with the code paths and test IDs, set the requirement to In Progress, and confirm the CHANGELOG.md entry.

Then produce a PR description and the exact manual steps for the user to verify on the Vercel preview URL — not localhost.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free