agentleFS
syangasyanga/astack/skills/implement/SKILL.md

implement

Skill0 starsChanged 53 days agoMITView on GitHub

Implement a feature, spec, or set of tickets with design ownership, independent review, and verified slices.

191 other projects use a version of this, 57 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

    to-tickets

    Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

    Also in 161 projects that use this

  • +1 more from google

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 5

    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. Very specific:

    Write the throughput checkpoint as four todo items.

    line 21
  2. Distinctive:

    Shared mutable state: Default to splitting the target (the separate-before-serializing-shared-state principle skill).

    line 24
  3. Distinctive:

    Smallest safe decomposition: If one worker is best, name why.

    line 25
  4. Distinctive:

    Use tdd where possible, at the testing boundaries established for the task.

    line 27
  5. Distinctive:

    Verify on the matching surface.

    line 28
  6. Distinctive:

    Use the sequence-verifiable-units principle skill, building, verifying, and committing each small unit before the next.

    line 30

“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

Implement the work described by the user in the spec or tickets. Carry forward designs and decisions already made. For non-trivial UI changes, follow prototype before editing real components.

For a substantial behavior-preserving phase, follow refactoring, reusing the design and evidence already established. Keep incidental cleanup within this workflow. Apply TypeScript guidance when writing or reviewing TypeScript.

When executing a multi-phase plan, read the shared execution-state convention. A sequential execution owner initializes or resumes the plan's existing store, checkpoints progress, and leaves its next action there before ending a session. At completion, follow the store's close procedure, including the show-me-your-work audit. A delegated worker returns receipts to its coordinator, which owns the shared state updates and final audit.

For a requested pause or transfer to another session, read handoff. Reuse the execution store when present; standalone implementation needs only a handoff note.

You own the design. Plan, review, verify. Delegate implementation. Stay in the lead.

  1. how over the affected subsystem.
  2. architect for parallel design exploration. Skipping stays as architect skipped: <reason>. Do not fold the design decision silently into implementation. If the user pushes back on a design's shape because of an unstated constraint, follow architect's pushback rule.
  3. Write the throughput checkpoint as four todo items. A dimension that genuinely does not apply (single file, no fan-out) keeps its item with n/a: <reason> rather than being dropped:
    • Blocking first steps. Gates run before fan-out.
    • Independent workstreams. Disjoint files, services, or layers parallelize. Shared writes serialize.
    • Shared mutable state. Default to splitting the target (the separate-before-serializing-shared-state principle skill). Serialize only for real invariants.
    • Smallest safe decomposition. If one worker is best, name why.
  4. Delegate code-writing to a subagent using the active environment's available tools and model configuration, with a specific scope (file paths, named data shape and its organizing structure per model-the-domain, a state machine over scattered booleans, a table/registry over branching, a typed model over repeated shape assumptions, chosen before the delegate writes logic, and success criteria). Review its diff yourself. When the implementation admits multiple valid shapes, use architect's candidate exploration before assigning the implementation. The purpose of delegation is review separation. If delegation is unavailable, own the diff directly and make the separate review pass explicit. Comments follow no-comments. Make surgical edits and re-ground against the source for upstream-derived files. Port shared-primitive improvements to all in-scope consumers and verify each. Use tdd where possible, at the testing boundaries established for the task. Run typechecking and single test files regularly. Leave the covering suites from test results for delivery, where they run once.
  5. Verify on the matching surface. "Inconclusive" or wrong-surface is not a pass. Flag it.
  6. Rebase into small, ordered commits. Stack follow-ups. Use the sequence-verifiable-units principle skill, building, verifying, and committing each small unit before the next.
  7. Commit the work and use open-pr for PR delivery within the task's authorized scope. When that scope stops short of a PR, such as a request to stop at local edits, run the covering suites picked under test results instead of open-pr. Then run review-pr in fix-and-review mode. For explicitly requested adversarial hardening, run harden-pr instead of review-pr. Merging and deployment are separate actions.

Code-coupled work (one feature, one migration) goes to a single owner with the checkpoint inline. That owner fans out internally after the blocking phase. Parent-level fan-out is for slices that produce independent artifacts (audits, cross-subsystem investigations, competing experiments). Rewrite the checkpoint at phase boundaries. Spawn a fresh owner rather than chaining interrupts.

Reply: what you built, what you chose and why, the throughput checkpoint, open decisions. Tables for design alternatives.

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.