agentleFS
egoxx1egoxx1/unified-master-harness/.agents/skills/dev-review/SKILL.md

dev-review

Skill1 starsChanged 17 days agoMITView on GitHub

Perform one focused independent review when explicitly requested or when a completed change has high risk involving auth/security, payments, destructive data migration, public API/protocol, concurrency/shared-state, production deployment logic, or large cross-system change. Do not invoke for routine work.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    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:

    Every finding must include severity (Critical / Important / Minor), concrete affected path/behavior, why it can fail, evidence, and the …

    line 29
  2. Distinctive:

    Do not report unrelated cleanup, speculative extensibility, equivalent style preferences, or generic requests for more tests without a …

    line 31

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

Focused Independent Review

Review concrete correctness and risk, not stylistic preference.

Scope

Review the complete task diff against requested behavior and existing contracts. Do not turn it into a repository-wide audit.

High-value checks

Prioritize:

  • requirement mismatch,
  • data loss or unsafe migration behavior,
  • security/trust-boundary mistakes,
  • public API/protocol compatibility,
  • concurrency, cancellation, retry, cleanup, and shared-state ownership,
  • error-path resource leaks,
  • persistence/resume mismatches,
  • missing verification at the caller-visible boundary,
  • UI regressions that contradict the accepted design contract.

Findings

Every finding must include severity (Critical / Important / Minor), concrete affected path/behavior, why it can fail, evidence, and the narrowest useful fix direction.

Do not report unrelated cleanup, speculative extensibility, equivalent style preferences, or generic requests for more tests without a concrete uncovered failure mode.

Normally perform one cold pass. If fixes are applied, recheck the specific findings and directly affected paths. Do not automatically restart a full review unless fixes materially changed design or blast radius.

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.