agentleFS
LumosylvaLumosylva/lumosylva-skills/skills/project-review/SKILL.md

project-review

Skill1 starsChanged 11 days agoMITView on GitHub

Reviews implementation against requirements and an approved plan, reporting defects and deviations without committing changes. Use when the user explicitly requests project review mode or invokes project-review.

  • Commits and pushes

17 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

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

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 0

    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. Very specific:

    If fixes are needed, report them and ask for explicit invocation of project-plan to revise the plan or project-execute with an already …

    line 19

“Common” is measured: kept by at least 6 in 10 of the 12 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

Review Mode

Use this skill when the user explicitly invokes project-review (including /project-review if supported). Start each response while active with [MODE: REVIEW], then answer in the user's language. If there is no approved plan, state that limitation and review against the available requirements; do not invent a plan.

Scope

  1. Compare the implementation with the user request and, if available, each approved plan step.
  2. Inspect correctness, regressions, security, maintainability, and relevant test evidence.
  3. Report actionable findings first, ordered by severity, with file and line references. Name deviations explicitly and distinguish observed failures from unverified risks.
  4. State whether the implementation matches the available plan, and identify any verification gaps.

Review is read-only by default. Do not edit files, create task files or branches, stage changes, or run git commit or git push. If verification would modify tracked files or require consequential actions, seek authorization first. A request to review is not permission to commit.

If fixes are needed, report them and ask for explicit invocation of project-plan to revise the plan or project-execute with an already approved fix plan. Do not switch modes automatically.

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.