agentleFS
Sign inStart free
Codagent-AICodagent-AI/agent-skills/skills/implement-change/SKILL.md

implement-change

Skill31 starsChanged 6 months agoMITView on GitHub

Implements an approved change in one continuous session, with tiered test runs. Use when asked to implement a change from its approved definition, or to invoke codagent:implement-change.

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 15 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:

    Keep tests fast. Prefer unit and component tests, and write integration or end-to-end tests only where the test plan or checklist calls for …

    line 21
  2. Very specific:

    Write automated tests for code only, never for prompts.

    line 24
  3. Very specific:

    Use three tiers, each kept inside its time limit with a timeout (for example timeout 180 <command>).

    line 29
  4. Distinctive:

    If it times out, run a smaller set.

    line 39
  5. Distinctive:

    Do a maintainability pass yourself, without a /simplify skill or reviewer sub-agents: remove duplication and logic at the wrong layer.

    line 46
  6. Distinctive:

    Commit following the project's commit message conventions.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 15 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 Change

Implement the approved change (its proposal, specs, design, and test plan) in this session. Even if it is a very large task, you must finish all of it yourself. Keep working until it is finished. Do not use the codagent:orchestrate-change, codagent:plan-tasks, or codagent:simple-plan skills. You may use sub-agents if they would help, but you are not required to.

Building

  • Get a working, integrated path through the main interacting deliverables early, before polishing any one of them.
  • Work in increments you choose, writing each increment's code and tests together in whatever order suits it. Do not follow test-driven development as a method unless the project's instructions require it.
  • Keep tests fast. Prefer unit and component tests, and write integration or end-to-end tests only where the test plan or checklist calls for them. In those, share expensive setup, such as a production build, a server, or a browser, across a file's cases instead of repeating it per test.
  • Write automated tests for code only, never for prompts. Do not write a test that checks whether a prompt, such as a SKILL.md, contains certain text.

Running tests

Use three tiers, each kept inside its time limit with a timeout (for example timeout 180 <command>). The limits are defaults the user may change. A tool call may stop after 10 minutes, so start any run that may take longer detached, with its output going to a log file, then wait for it and read the log. Never restart a run only because a call timed out, and reuse a result when nothing relevant has changed since it ran.

  1. Unit tests your change affects: run these while you work, as often as you need, within 3 minutes. If a run times out, run a smaller set.
  2. A broader run: the whole suite, or a subset you choose that includes the integration and end-to-end tests relevant to the change. Run it once, when the work is ready, within 15 minutes. If it times out, run a smaller set. If tests fail, fix them and rerun only the failing tests and those covering what you changed; do not repeat the broader run.
  3. Anything beyond that is left to CI. Do not run it, even if project instructions ask for the full suite, and name the tests you left unrun.

Before finishing

  • Do a maintainability pass yourself, without a /simplify skill or reviewer sub-agents: remove duplication and logic at the wrong layer. Cleanups must preserve behavior exactly and must not grow the code; commit them separately.
  • Commit following the project's commit message conventions.

Download now (ZIP)

  • Other versions16 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 16

    1. pnpm/pnpm★ 37ksame name
    2. verdaccio/verdaccio★ 18ksame name
    3. manhds82/claude-code-anyllm★ 16same name
    4. taljeon/plzdo★ 9same name
    5. Remote-Arc/remote-arc★ 5same name
    6. yaohuangguan/remote-arc★ 5same name
    7. CsHeng/agent-skills★ 3same name
    8. otaviobarros/agent-engineering★ 3same name
    9. EJRyan89/coding-agent-skills★ 2same name
    10. SaKaNa-Y/skills★ 2same name

    6 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use audit-test-suite, change-data-safely 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.
    • yaohuangguanSkill

      audit-test-suite

      Find where an existing test suite is weak and decide what to test next, ranked by risk. Use this when asked to add missing tests, find gaps, raise coverage, assess test quality or see which areas are thin, even if the request only mentions a coverage percentage.

      Also in 3 projects that use this

    • yaohuangguanSkill

      change-data-safely

      Change a database schema or stored data without breaking running code or losing data. Use this for any migration, new or changed column, backfill, bulk update, delete, index, or change to a stored format, including in small projects. Data mistakes are often impossible to undo.

      Also in 3 projects that use this

    • BanKnightSkill

      plan-change

      将已完成 spec/design 的 change 拆成可执行 plan 与 tasks。用户要把设计落成执行计划、任务清单或实现步骤时使用。

      Also in 5 projects that use this

    • SauravSrivastavSkill

      debug-failure

      Diagnose a failing test, command, or runtime behavior using evidence and produce a minimal verified fix.

      Also in 3 projects that use this

    • MicrosoftSkill

      fix-flaky-test

      Reproduces and fixes flaky or quarantined tests. Tries local reproduction first (fast), then falls back to CI reproduce workflow (reproduce-flaky-tests.yml). Use this when asked to investigate, reproduce, debug, or fix a flaky test, a quarantined test, or an intermittently failing test.

      Also in 3 projects that use this

    • dabstractorSkill

      write-pull-request

      Write a pull request to an open source repository. Lead with the user-facing problem in a personal voice, then a scannable technical fix. Use when opening or drafting a PR or contribution.

      Also in 3 projects that use this

    • +5 more from yaohuangguan
  • In this repository30 other files it gives its agents.

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