agentleFS
Curious-KeeperCurious-Keeper/skills/implement/SKILL.md

implement

Skill1 starsChanged 57 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, 66 of them edited.

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

1 rule. 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Commit the map with the code.

    line 23

“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 the work described by the user in the spec or tickets.

Work to the project's anchors, the commands in .claude/harness.config.json that decide whether the work stands. Run the narrow ones (typecheck, the single test file you are touching) continuously, and the full set once at the end. Where a seam is worth a test first, write the test first.

Once done, review the work, then commit it to a branch, never to main or master, and stop before pushing.

In a repo with an APP_MAP.json

The item you are building came out of the map, so the map binds the work:

  1. Read invariants and evolutionTraps before touching code. Each invariant has already caused a real bug in this repo, and each trap is something that used to be true and no longer is. Both are cheaper to read than to rediscover.
  2. Verify the item's evidence before changing anything. An openDebt entry cites file:line. Confirm the citation still says what it claims; where it does not, report stale evidence and stop rather than quietly building against a moved target. Map rot is a finding, not an obstacle.
  3. Stay inside the item's file set. The paths in the item's evidence are what it claims; core/scope-gate.sh enforces it. Where the work genuinely needs a file the item does not name, say so and stop. A builder that reaches outside its set is the collision the graph exists to prevent.
  4. Never hand-edit a generated file. The map names each one and the command that produces it; run the generator.
  5. Close the item in one edit: add the shipped entry AND remove it from openDebt. The second edit is the one that gets skipped, and an item sitting in both places is re-dispatched next batch against work already on main. Record in how what the fix taught you, including anything it left open.

Commit the map with the code.

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.