agentleFS
Sign inStart free
rpraharajrpraharaj/ai-sdlc/skills/implement-change/SKILL.md

implement-change

Skill0 starsChanged 16 days agoMITView on GitHub

Implement a scoped change in this repository using existing patterns. Use when the user wants a feature, bug fix, or code change applied and the ask is already shaped or is a clear small change. Do not claim done without command output.

17 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use audit-test-suite, change-data-safely and 9 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 6 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

  • +6 more from yaohuangguan

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 1

    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:

    Read AGENTS.md. Use its commands.

    line 43
  2. Very specific:

    If the workspace has no product (only bootstrap files), stop and run start-project.

    line 44
  3. Very specific:

    If the request is vague, run shape-work and stop unless they already told you to implement the result.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 16 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

Apply the smallest change that satisfies the request. Do not orchestrate other agents unless the user asked.

Is this the right skill?

SignalDo this instead
Empty tree / no appstart-project
Vague ask, several product decisionsshape-work first
Production incidentincident-triage
Known failure, find the causedebug

A clear small change (one behavior, likely files obvious) does not need a shape document.

Required inputs

  • A shaped task or a clear small change
  • AGENTS.md commands
  • Applicable requirement/defect or shaped-work acceptance references and approved baseline when the program requires it

Human decisions (do not invent)

  • Adding a new dependency when a lower rung would do (say why if you add one)
  • Waiving an engineering-bar fail

Procedure

  1. Read AGENTS.md. Use its commands.
  2. If the workspace has no product (only bootstrap files), stop and run start-project.
  3. If the request is vague, run shape-work and stop unless they already told you to implement the result.
  4. Load ../engineering-bar/SKILL.md. Climb Minimum path. Search this repo for an existing helper first.
  5. Bug fix: find every caller; fix the shared cause once.
  6. Touch only files the request and its tests need. No drive-by refactors. Do not edit generated paths in AGENTS.md. Preserve requirement/defect or shaped-work acceptance references through implementation and tests. Stop if the applicable approved baseline is missing, stale, or has unresolved blocking findings; check evidence using context/decision-rights.md when installed.
  7. Prove: focused test, then Test, then Lint / Typecheck if known. Never claim pass without this session’s output. Missing tests → write-tests. UI → verify-ui.
  8. Walk the diff against engineering-bar. Fix fails or get an explicit waiver.

Output

  • Path: the product diff
  • Template: references/implement-report.md

Quality bar

  • Acceptance checks pass or were not specified
  • Commands run are listed with exit status
  • No secrets
  • Engineering-bar fails are fixed or waived

Done

Fill the report template. Do not commit unless asked. Next: write-tests / verify-ui / ready-to-merge.

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