agentleFS
lutzseverinolutzseverino/repo-standards/.agents/skills/implement/SKILL.md

implement

Skill0 starsChanged 5 days agoMITView on GitHub

Implement a spec or ticket, or address review findings on its existing pull request.

193 other projects use a version of this, 61 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-ts-deep-modules, ask-matt and 7 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.
  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 43 projects that use this

  • GoogleSkill

    ask-matt

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    Also in 91 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 50 projects that use this

  • AWSSkill

    to-questionnaire

    Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

    Also in 88 projects that use this

  • ryotaroh180105Skill

    claude-handoff

    Hand the current conversation off to a fresh background agent that picks up the work immediately.

    Also in 42 projects that use this

  • GoogleSkill

    resolving-merge-conflicts

    Use when you need to resolve an in-progress git merge/rebase conflict.

    Also in 83 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before editing, read CONTRIBUTING.md for the repository's branch and validation requirements.

    line 8
  2. Distinctive:

    When the input is review findings on an existing pull request, read the findings and continue on that pull request's branch.

    line 10
  3. Distinctive:

    Use /tdd where possible, at pre-agreed seams.

    line 15
  4. Distinctive:

    Run typechecking regularly, single test files regularly, and the repository's required validation on the final commit.

    line 17
  5. Very specific:

    Before delivery in a factory repository, read the installed factory-workflow rules' Run kinds section and .scriptorium/config.json's …

    line 20
  6. Very specific:

    Before reporting success, satisfy CONTRIBUTING.md's Worker handoff condition and include its head, trusted required-check authority, …

    line 25
  7. Very specific:

    Before reporting success, satisfy CONTRIBUTING.md's Worker handoff condition.

    line 35
  8. Distinctive:

    When it is missing, follow the contribution guide's comment requirements.

    line 51
  9. Distinctive:

    When it is missing, use the draft handoff above.

    line 54
  10. Distinctive:

    When it is missing in a factory repository, no review run is configured.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 175 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

A prompt or brief naming this skill is its invocation.

Before editing, read CONTRIBUTING.md for the repository's branch and validation requirements. Implement the work described in the spec or tickets. When the input is review findings on an existing pull request, read the findings and continue on that pull request's branch.

Apply codebase-design's Ownership check to the change, including its contract-disagreement route.

Use /tdd where possible, at pre-agreed seams.

Run typechecking regularly, single test files regularly, and the repository's required validation on the final commit.

Before delivery in a factory repository, read the installed factory-workflow rules' Run kinds section and .scriptorium/config.json's runKinds. When no review run is configured, commit and push the work, write the PR body with pr, open a ready pull request (or mark its existing draft ready), and invoke babysit to deliver it under those rules, including any prescribed worker handoff. Before reporting success, satisfy CONTRIBUTING.md's Worker handoff condition and include its head, trusted required-check authority, check-location, command and outcome record. That route retains babysit's applicable internal reviews and merge conditions.

Otherwise, for new work, commit and push the branch, write the body with pr, and open one draft pull request as CONTRIBUTING.md directs. For review findings, commit and push the fixes to the same pull request and leave it a draft; before replying to findings, read the installed comments rules' Review-thread replies section and answer there as it directs. Before reporting success, satisfy CONTRIBUTING.md's Worker handoff condition. Report the pull request and its required head, trusted required-check authority, check-location, command and outcome record, then stop. Leave review, marking ready, babysitting and merging to the separate agent running review; do not run a self-review.

<!-- Seam (deferred): Scriptorium configuration reads; consumers: 6; extraction proposed in https://github.com/lutzseverino/repo-canon/issues/967. -->

Reads

Paths are relative to the repository root.

  • CONTRIBUTING.md: branch, validation and pull request requirements. When it is missing, work on a branch dedicated to the change, run the available checks, and open a draft pull request with pr as above.
  • .repo-standards/rules/comments.md: how to reply to review findings. When it is missing, follow the contribution guide's comment requirements; without either source, report the fixes in the handoff.
  • .repo-standards/rules/factory-workflow.md: the factory's delivery route. When it is missing, use the draft handoff above.
  • .scriptorium/config.json: the configured review run under runKinds.review. When it is missing in a factory repository, no review run is configured; follow the installed factory rules' delivery route.
  • The codebase-design skill: the check applied above. When missing, report the gap through the contribution guide's Findings route, or in the handoff when the guide is missing; retain the recorded contract.

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.