agentleFS
Sign inStart free
qyndexqyndex/claude-init/.claude/skills/implement/SKILL.md

implement

Skill2 starsChanged 5 months agoMITView on GitHub

Execute tasks from tasks/TASKS.md one at a time using strict TDD. Phase 5 of the eight-phase workflow. Delegate each task to the implementer agent. Walks the DAG, respects deps, fans out [P] tasks if requested.

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

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 4

    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:

    One task at a time per agent: Don't pile tasks into one invocation.

    line 39
  2. Very specific:

    Respect deps: Never start a task whose deps are not [x].

    line 41
  3. Distinctive:

    Read parent spec, plan, task.

    line 47
  4. Distinctive:

    Run broader test suite.

    line 52
  5. Distinctive:

    After loop ends: "Implementation complete.

    line 65

“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

Walk the task DAG and execute each task with strict TDD discipline.

Process

1. Read tasks/TASKS.md.
2. If arg is a task id, work on that task only.
   If arg is "next", nominate via the canonical picker — `bash .claude/scripts/next-task.sh`
   (dep-aware, priority-ordered, skips operator-owned/RESOLVE lines and the Format
   template; rc 1 = backlog empty, rc 3 = all blocked → run `--why` and report).
   NEVER hand-pick with grep — the picker is the single nomination grammar shared
   with loop-iteration.sh and workflow-state.sh.
   Analyze gate (spec-pipeline-1): before working any task of spec N, check
   `.claude/state/analyze-<N>.json` exists with verdict PASS (spec:HOTFIX exempt).
   Missing → run /analyze first. verdict BLOCK → refuse and surface the blockers.
   If arg is "all", loop: call `next-task.sh` before each task until rc ≠ 0 or a task fails.
3. For each task:
   a. Mark in_progress in TodoWrite.
   b. Delegate to the implementer agent (which uses the tdd-loop skill).
   c. On agent return, mark completed and refresh the DAG.
4. If a task fails, stop the loop, report, and hand back to the user.

Hard rules

  • One task at a time per agent. Don't pile tasks into one invocation.
  • Strict TDD inside each task. The implementer agent uses .claude/skills/tdd-loop/SKILL.md non-negotiably.
  • Respect deps. Never start a task whose deps are not [x].
  • Fan out only for [P] tasks. And only if the user opted in.
  • Stop on failure. Cascading failures are worse than a clean halt.

Per-task workflow (handled by implementer agent)

  1. Read parent spec, plan, task.
  2. Write failing test.
  3. Watch it fail (paste output).
  4. Implement minimum code.
  5. Watch it pass (paste output).
  6. Run broader test suite.
  7. Lint + format.
  8. Commit (Conventional Commits).
  9. Flip status: bash .claude/scripts/task-status.sh T-<id> done (lock-safe sanctioned path — Write/Edit on TASKS.md is denied) + TodoWrite.

Output

Each completed task → 1 commit in git history.
tasks/TASKS.md → [x] mark via `task-status.sh` (never Write/Edit), completed-at timestamp.
TodoWrite → completed.

After loop ends: "Implementation complete. <N> tasks done, <M> commits. Ready for /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.

Check your setup, free