agentleFS
Greg-KleinGreg-Klein/implementation-factory/skills/review-change/SKILL.md

review-change

Skill1 starsChanged 34 days agoMITView on GitHub

Independently challenge an implementation from its specification and diff, looking for counterexamples, regressions, untested consumers and tests that pass for the wrong reason. Use for code review or independent QA, not author self-checks. Returns findings without fixing code.

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plan-change, implement-change 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.
  • 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 7 projects that use this

  • Codagent-AISkill

    implement-change

    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.

    Also in 7 projects that use this

  • MaheshAwasareSkill

    write-runbook

    Generate an operational runbook for a service from its code, config, and dependencies — what to do when it breaks, where to look, how to roll back, who to escalate to. Use proactively before a service goes to production, after a major incident, or when handing off operational ownership.

    Also in 3 projects that use this

  • testified-ossSkill

    incident-triage

    Triage production incidents with severity assessment, root cause hypothesis, impact analysis, and escalation recommendations. Use when analyzing outages, errors, or production issues.

    Also in 4 projects that use this

  • srclightSkill

    refactor-safely

    This skill should be used when the user asks to "refactor", "rename", "move", "change a function signature", "extract a method", "delete unused code", "clean up", or any modification that could break callers or dependents. Provides a pre-change safety checklist using srclight's graph tools to assess blast radius before touching code.

    Also in 3 projects that use this

  • Google CloudSkill

    open-pr

    Commits local changes to a new Git branch and opens a GitHub pull request through the configured GitHub MCP server. Use when proposing code changes in a new pull request. Don't use for local-only commits without a remote GitHub repository.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 1

    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:

    After the initial analysis, consult author reports to reconcile omissions, reuse setup and check claimed results.

    line 16
  2. Very specific:

    Use collect-evidence only for execution mechanics after independently choosing checks.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 24 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

Independent review

Input: authoritative requirements and decisions, diff or changed scope, current code, review depth, and permitted tools. Return an evidence-backed review. Do not modify product code, fix tests, publish comments or infer permission to do so.

Establish an independent basis

Before reading developer conclusions, self-check reports, prior verdicts or an author-provided mental model, derive your own expected behavior and plausible failure cases from the specification, consumers and current code. Record this initial basis in the eventual review report. A planner's solution is not a specification. If the caller already disclosed the diagnosis, state that exposure and deliberately test an alternative explanation; do not claim a blind review.

Choose the applicable method: code-review.md for code review, behavioral-qa.md for independent QA. Do not run both by default.

After the initial analysis, consult author reports to reconcile omissions, reuse setup and check claimed results. Inspect their sources rather than treating their agreement as corroboration. Reusing a fixture does not require trusting its oracle; challenge stubs that predetermine the result.

You may use how for an unfamiliar behavior, or why before treating unusual compatibility as unnecessary. Their results explain behavior and history; they do not decide correctness. Independently check consequential anchors. Respect why's required how dependency.

Evidence and completion

Use collect-evidence only for execution mechanics after independently choosing checks. A passed author-selected suite is useful evidence, not a complete review. Do not use the author's self-check method as your review plan.

Each finding states the violated requirement or contract, concrete trigger, expected and actual behavior, affected consumer, evidence and impact. Distinguish reproduced defects from static findings and unknowns. Do not invent findings to meet a quota; no findings is a valid outcome.

Follow the caller's severity and output contract, and write findings with implementation-factory:unslop. Return initial review basis, findings, checks and limits. When the caller is a corrective reviewer, finish this diagnostic phase before it applies fixes under its own role. A correction requires fresh validation; it does not prove its own correctness.

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.