agentleFS
m3uem3ue/m3u-editor/.claude/skills/pr-review-standards/SKILL.md

pr-review-standards

Skill893 starsChanged 3 months agoLicence not identifiedView on GitHub

Project-specific PR review standards for m3u-editor, supplementing the general-purpose /code-review skill. Apply whenever reviewing a diff, PR, or branch in this project (via /code-review, /review, or a direct request to review changes). Enforces five rules: (1) memory-efficient queries — no ->all()/->get() on large/unbounded datasets, prefer ->cursor() or generators; (2) no unnecessary complexity — no hand-rolled DB::statement() over Eloquent, no new function where an existing one could be extended, no duplicated logic where a centralized Service or Filament Action exists (including stragglers a PR's own new helper should have replaced but didn't); (3) framework-first UI — Filament/Livewire built-ins over hand-rolled Blade/Alpine, except in explicitly approved custom surfaces (EPG Viewer, in-app player); (4) no regressions — existing behavioral defaults must not change unless the user explicitly opted in, or the change fixes a real bug/gap; (5) migration/schema safety — DDL that locks tables the Process*/Sync job chains write to continuously (e.g. plain CREATE INDEX instead of CONCURRENTLY on Postgres) must be called out explicitly. This is a project convention kept in its own skill directory (not under laravel-best-practices/rules) so `php artisan boost:update` cannot overwrite it.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

The licence could not be identified — 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.