agentleFS
sourjyasourjya/kiro-rails/.claude/skills/spec-implement/SKILL.md

spec-implement

Skill9 starsChanged 4 months agoMITView on GitHub

Implement a proposed spec. Reads the spec folder, follows the task checklist, writes code using TDD. Use after spec-propose is complete and approved.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 8

    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
  1. Distinctive:

    Confirm readiness: - all artifacts exist and tasks are defined

    line 13
  2. Distinctive:

    Update design.md: if implementation deviates from plan (document WHY)

    line 19
  3. Distinctive:

    Before writing any code, verify:

    line 23
  4. Very specific:

    Mark progress: - update - [ ] to - [x] in tasks.md after each task passes tests

    line 34
  5. Distinctive:

    Stay in scope: - if you discover needed work not in the spec, note it but don't implement it.

    line 35
  6. Distinctive:

    Document deviations: - if the implementation differs from design.md, update design.md with the actual approach and rationale

    line 37
  7. Distinctive:

    When all tasks are checked off:

    line 41
  8. Distinctive:

    Run the full test suite

    line 42
  9. Distinctive:

    Verify all acceptance criteria in requirements.md are met

    line 43

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

Spec Implement Workflow

Implement a feature that has an approved spec in .kiro/specs/<feature-name>/.

Steps

  1. Read the full spec - proposal.md, requirements.md, design.md, tasks.md
  2. Confirm readiness - all artifacts exist and tasks are defined
  3. Implement using TDD - for each task:
    • RED: Write a failing test
    • GREEN: Write minimal code to pass
    • REFACTOR: Clean up while tests pass
  4. Check off tasks as completed in tasks.md
  5. Update design.md if implementation deviates from plan (document WHY)

Pre-Implementation Checklist

Before writing any code, verify:

  • proposal.md exists and is approved (user confirmed)
  • requirements.md has testable acceptance criteria
  • design.md describes the approach
  • tasks.md has atomic, ordered tasks
  • No open questions remain in proposal.md (or they've been answered)

Implementation Rules

  1. Follow task order - implement tasks in the sequence defined in tasks.md
  2. One task at a time - complete and verify each task before starting the next
  3. Mark progress - update - [ ] to - [x] in tasks.md after each task passes tests
  4. Stay in scope - if you discover needed work not in the spec, note it but don't implement it. Add it as a new task or flag it for a follow-up spec.
  5. Test against acceptance criteria - each requirement's criteria must have a corresponding test
  6. Document deviations - if the implementation differs from design.md, update design.md with the actual approach and rationale

Completion

When all tasks are checked off:

  1. Run the full test suite
  2. Verify all acceptance criteria in requirements.md are met
  3. Inform the user the spec is ready for verification (use spec-verify)

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.