agentleFS
fnayoufnayou/dotfiles/.claude/skills/review-change/SKILL.md

review-change

Skill3 starsChanged 5 months agoMITView on GitHub

Produces a numbered review report under docs/reviews/. List every file that was created or modified. For each file, verify: For each file, verify: For each documentation file, verify: Categorize each finding as: Issue explicit verdicts: All three must be PASS before recommending commit. If this is an implementation review (reviewing Builder output) and all three verdicts are PASS: If any verdict is FAIL, leave the plan status as Approved. See docs/claude/DOCUMENT-LIFECYCLE.md for the full lifecycle rules. Write the report to…

  • Reads credentials

32 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 8 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

  • Sagargupta16Skill

    upgrade-dependencies

    Upgrade a project's dependencies one at a time, running the test suite after each bump and reverting the ones that break it. Use it during routine dependency maintenance, when a batch of updates has accumulated; before a major release, to go into it on current and patched dependencies; when Renovate or Dependabot PRs have piled up and you want them resolved locally in one sitting; when a security advisory means you need the patched version in, and you need to know what it breaks.

    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

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All three must be PASS before recommending commit.

    line 80
  2. Distinctive:

    If this is an implementation review (reviewing Builder output) and all three verdicts are PASS:

    line 84
  3. Distinctive:

    If any verdict is FAIL, leave the plan status as Approved.

    line 90
  4. Distinctive:

    Write the report to a numbered file:

    line 96
  5. Distinctive:

    Use the next available number in the sequence.

    line 103

“Common” is measured: kept by at least 6 in 10 of the 27 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

Skill: review-change

Produces a numbered review report under docs/reviews/.

When to use

  • Builder has completed a set of changes.
  • User wants validation before committing.
  • Any significant change to the repository that touches dotfiles, scripts, or config.

Process

Step 1 — Inspect changed files

Run:

git status
git diff
git diff --staged

List every file that was created or modified.

Step 2 — Check safety

For each file, verify:

  • No stow --adopt command present as automated behavior.
  • No rm targeting $HOME or paths outside the repository.
  • No mv targeting $HOME or paths outside the repository.
  • No ln -s creating symlinks in $HOME without clear manual-step markers.
  • No modification of files outside the repository root.
  • Risky commands are shown with ⚠️ MANUAL STEP markers, not executed automatically.

Step 3 — Check privacy

For each file, verify:

  • No API keys, tokens, or access credentials.
  • No passwords or passphrases.
  • No SSH private key content.
  • No private hostnames or internal IP addresses.
  • No work-specific secrets or environment variables.
  • All examples use placeholder values (YOUR_API_KEY, your-token-here).

Step 4 — Check documentation

For each documentation file, verify:

  • Commands are copy-pasteable and correct.
  • Dangerous commands have ⚠️ MANUAL STEP markers.
  • Platform-specific commands clearly specify the target OS.
  • PRD, architecture, and plan references are accurate.

Step 5 — Check macOS / Arch separation

Verify:

  • macOS-specific content is not placed in Arch directories or docs.
  • Arch-specific content is not placed in macOS directories or docs.
  • Common packages genuinely work on both platforms.
  • Platform detection is used in any multi-platform scripts.

Step 6 — Produce findings

Categorize each finding as:

  • Blocking — must be fixed before commit.
  • Non-blocking — improvement, does not block commit.

Step 7 — Produce verdicts

Issue explicit verdicts:

  • Safety: PASS or FAIL
  • Privacy: PASS or FAIL
  • Documentation: PASS or FAIL

All three must be PASS before recommending commit.

Step 7a — Mark the Plan Complete (implementation reviews only)

If this is an implementation review (reviewing Builder output) and all three verdicts are PASS:

  1. Open the plan file referenced in the review (under docs/plans/).
  2. Change **Status:** Approved to **Status:** Complete.
  3. Record the plan number and title in the Summary of the review report.

If any verdict is FAIL, leave the plan status as Approved.

See docs/claude/DOCUMENT-LIFECYCLE.md for the full lifecycle rules.

Step 8 — Produce the review report

Write the report to a numbered file:

docs/reviews/0001-claude-operating-layer-review.md
docs/reviews/0002-zsh-package-review.md

Use the next available number in the sequence.

Review report template

# Review: [Title]

**Number:** 0001
**Status:** Complete
**Date:** YYYY-MM-DD
**Plan reviewed:** [number] — [title]
**Files reviewed:** [list]

## Summary

[What was reviewed — name the Plan completed, e.g. "Plan 0007 — Implement Zsh Configuration Foundation"]

## Blocking Issues

- [issue — file:line if applicable]

## Non-Blocking Suggestions

- [suggestion]

## Safety Verdict

PASS / FAIL — [reason]

## Privacy Verdict

PASS / FAIL — [reason]

## Documentation Verdict

PASS / FAIL — [reason]

## Recommended Next Action

[Fix blocking issues and re-review / Approve and commit]

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.