agentleFS
christofferbergjchristofferbergj/agent-skills/skills/engineering/implement/SKILL.md

implement

Skill1 starsChanged 21 days agoMITView on GitHub

Implement a piece of work based on a spec or set of tickets.

191 other projects use a version of this, 60 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ask-matt, claude-handoff and 2 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.
  • 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

  • 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

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 47 projects that use this

The file

Files
SKILL.md

Implement

  1. Read the requested spec or tickets and state their identity, accepted scope, and test seams. If a reference is ambiguous, ask. Resolve the project's shared artifacts through /domain-modeling; consume them without reopening settled decisions. Invoke /principles for implementation before code changes. Complete when the work, applicable design constraints, and its done predicate are grounded in the existing source of truth.
  2. Implement vertical slices through /tdd where a useful test path exists. Reuse agreed seams and repository checks; run typechecking and single test files regularly. Use /swarm only for useful bounded delegation, with isolated writers and one coordinator for canonical docs; explicitly pass /principles and the resolved applicable owners to writers. Recheck selection when the work reveals a new branch. Complete each slice when its observed behavior satisfies its acceptance criteria and applicable rules.
  3. Reconcile accepted domain changes through /domain-modeling and inspect the full diff. Recheck /principles for verification, run the full test suite once and other relevant checks, and invoke /review-loop for the final artifact, reusing valid review evidence supplied by the caller. Resolve actionable findings; when a fix changes the reviewed artifact, refresh the affected review coverage and checks. Complete when implementation, docs, acceptance evidence against the actual artifact, and review findings agree at the delivered revision or a gap is explicit.
  4. Commit the scoped result to the current branch when authorized and prepare a draft PR when requested or part of the existing grant. Invoke /pr for its description. Keep tracker closure tied to the project's actual completion boundary. Complete when the result is reviewable and delivery state is truthful.

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.