agentleFS
rafapeixerrafapeixer/db-skills/.claude/skills/review-skill/SKILL.md

review-skill

Skill1 starsChanged 30 days agoMITView on GitHub

Review one db-skills skill against the repository rules and current official documentation. Use before opening a PR for a new or changed skill.

21 other projects use a version of this, 2 of them edited.

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

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 1

    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 fact matches the official docs for the versions the examples run on (postgresql.org, dev.mysql.com, docs.aws.amazon.com).

    line 14

“Common” is measured: kept by at least 6 in 10 of the 17 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 skill

Review skills/$ARGUMENTS/ against CLAUDE.md. Report findings, most severe first; do not edit unless asked.

  1. bash scripts/validate.sh and bash scripts/test-examples.sh pass on every supported version.
  2. One decision; a position for each rule; the Why says what breaks, with a number where possible.
  3. Every fact matches the official docs for the versions the examples run on (postgresql.org, dev.mysql.com, docs.aws.amazon.com). Version-specific rules carry an inline gate. Flag any claim sourced only from third-party material.
  4. The good example proves the rule (a plan, a row count, an error) and the bad example shows a mistake people actually make, each marked -- MISTAKE:.
  5. Schema changes are shown the online, non-blocking way first.
  6. Workflow skills: every query in queries/ is read-only, runs under a statement timeout, and does not expose row data or credentials in the report.
  7. Checklist items can be answered from the SQL or the plan.

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.