agentleFS
zaphod72zaphod72/claude-skills/skills/dual-scoped-review-plans/SKILL.md

dual-scoped-review-plans

Skill1 starsChanged 2 months agoNo licenceView on GitHub

Author two review plans for one change, each scoped from a different source, so two review passes find different things: one scoped from what the work already worried about, one from the repo's documented standards with no memory of it. Use when a large or long-running change needs reviewing, when one review pass is not enough, when a plan-rollout run reaches close-out, when deciding what a review pass may look at, when briefing a review-plan author or a reviewer running one of these plans, when writing a review plan that a Claude agent rather than a person will execute, or when two passes have both reported and need synthesising. Checks for the repo's standards docs first and stops if there are none, since a second scope needs a second source. Not the prose a finding is written in (review), grouping findings into a fix plan (root-cause-fix), the review rounds inside a run (plan-rollout), or verifying one finding before acting on it (claims-and-scope-discipline).

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

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.