agentleFS
Sign inStart free
BinayakDotelBinayakDotel/skills-marketplace/skills/implement/SKILL.md

implement

Skill1 starsChanged 34 days agoMITView on GitHub

Implement the in-progress ticket test-first, run the project's checks and a two-axis code review, write the Outcome, open the PR and move the ticket to review. Part of the dev-flow lifecycle (take, implement, address, done).

  • Reads credentials
  • Commits and pushes

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-ts-deep-modules, ask-matt and 10 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

    to-spec

    Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 168 projects that use this

  • +3 more from google

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Scope: Read only the files under ## Files.

    line 14
  2. Very specific:

    Outcome: Add ## Outcome to the issue body: what changed, why, one risk, how to verify.

    line 17
  3. Very specific:

    Never commit to the base branch.

    line 26
  4. Very specific:

    Never edit files listed in another status:in-progress or status:in-review issue.

    line 27
  5. Distinctive:

    Never bundle a refactor with a feature.

    line 28
  6. Very specific:

    Never read or print .env* files.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 171 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 [#N]

Project facts (commands, tracker, git tool, base branch, models) live in AGENTS.md. Read it first.

  1. Load. The named issue, else the one labelled status:in-progress: gh issue view <n> --json title,body. No ## Decisions section → stop and say /take must run first. If the issue is not labelled status:in-progress, run just task <n> in-progress first.
  2. Scope. Read only the files under ## Files. Needs more than ~5 files → propose a split and stop.
  3. Build with the tdd skill: red → green with just test-q only; the repo is green after every step. If the ticket touches screens, components or styles, also follow ui-from-reference.
  4. Gates. just check passes. Then code-review with fixed point = the base branch and spec = this issue. Fix the real findings; list the rest in the Outcome.
  5. Outcome. Add ## Outcome to the issue body: what changed, why, one risk, how to verify. Temp file + gh issue edit <n> --body-file <tmp>.
  6. Ship.
    • Graphite: gt create -am "<type(scope): subject>", then gt submit --no-edit (if rejected, --no-interactive).
    • Plain git: git switch -c <n>-<slug> before step 3; now git add -A, git commit -m "<type(scope): subject>", git push -u origin HEAD, gh pr create --fill.
    • PR body in the pr skill's format, written to a temp file, ending with Closes #<n>: gh pr edit <pr> --body-file <tmp>.
  7. Hand over. just task <n> in-review. Report the PR link and the Outcome. No pasted diffs.

Rules

  • Never commit to the base branch. Never reset, rebase, force-push or merge; the human merges.
  • Never edit files listed in another status:in-progress or status:in-review issue.
  • Never bundle a refactor with a feature. Never add a dependency without one sentence of why.
  • Never read or print .env* files.
  • Two failed attempts at the same problem: stop, add a dated lesson to docs/DECISIONS.md, ask.

Shortest complete answer. End with one line: Next: /address on <model> (after review comments) or /done (after merge).

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