agentleFS
jakkarin-promseejakkarin-promsee/my-harness/.claude/skills/implement-feature/SKILL.md

implement-feature

Skill1 starsChanged 4 months agoMITView on GitHub

Add or change a feature in the researcher-harness following the project constitution (design note → implement → tests → acceptance). Use for any non-trivial change to code under src/harness/.

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use prepare-release, create-skill and 4 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.
  • ShopifySkill

    prepare-release

    Prepare the changeset-release/main branch for release by syncing version.ts files and running pnpm install

    Also in 3 projects that use this

  • ElasticSkill

    create-skill

    Interactively create a new Claude Code skill and add it to the elastic-docs-skills catalog. Use when the user wants to generate a new skill, scaffold a slash command, or build automation for docs tasks.

    Also in 3 projects that use this

  • MicrosoftSkill

    playwright-cli

    Automate browser interactions, test web pages and work with Playwright tests.

    Also in 3 projects that use this

  • VercelSkill

    find-skills

    Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    One feature at a time: If something else is in flight, stop (rule 2).

    line 12
  2. Very specific:

    Add a FakeModel test in tests/ (see tests/README.md) — the loop's contract, zero tokens.

    line 20
  3. Very specific:

    If the change touches the full stack, run the exit gate: uv run python acceptance/run.py <provider> (see acceptance/README.md).

    line 26
  4. Distinctive:

    Update the folder's README.md: if you added, removed, or renamed a file — the README is that folder's live map, and this step is how the …

    line 30
  5. Distinctive:

    Update the status line in the root CLAUDE.md if a stage milestone completed.

    line 31
  6. Distinctive:

    Ask the owner: when a decision changes scope or direction (rule 7).

    line 32

“Common” is measured: kept by at least 6 in 10 of the 25 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 a feature (the constitution's mini-cycle)

The working rules in the root CLAUDE.md are law. This skill is those rules, as steps.

Before code

  1. One feature at a time. If something else is in flight, stop (rule 2).
  2. Study 2–3 seniors — mini-swe-agent, opencode, aider, Claude Code — for how they do this thing. Copy first, invent later; custom ideas wait for Stage 3 (rule 1).
  3. Write the design note docs/notes/NN-name.md (next number): one page — what the seniors do → what we'll build → how we'll know it works. No note, no code (rule 6).

Code

  1. Implement under src/harness/. Match the surrounding style and comment density. No line you can't explain (rule 3).
  2. Respect the invariants in src/harness/CLAUDE.md: the loop stays pure/injected; adapters translate both directions; tools return strings; errors become text, never crashes.
  3. Add a FakeModel test in tests/ (see tests/README.md) — the loop's contract, zero tokens.

Prove it

  1. uv run pytest -q — must stay green (rule 5).
  2. Debug loop logic on ollama (a runaway loop costs $0); validate quality on gemini. Never point a possibly-buggy loop at a paid endpoint (the budget rule).
  3. If the change touches the full stack, run the exit gate: uv run python acceptance/run.py <provider> (see acceptance/README.md).

Finish

  1. Update the folder's README.md if you added, removed, or renamed a file — the README is that folder's live map, and this step is how the hierarchy stays un-rotten (note 15).
  2. Update the status line in the root CLAUDE.md if a stage milestone completed.
  3. Ask the owner when a decision changes scope or direction (rule 7).

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.