agentleFS
Sign inStart free
mgiovanimgiovani/cc-arsenal/skills/stopslop/SKILL.md

stopslop

Skill8 starsChanged 49 days agoMITView on GitHub

Run the stopslop AI-slop linter with every rule, report findings, and render them for review. Use for "run stopslop", "slop report", "check for AI slop". Not for code review (use review-code).

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Distinctive:

    Run the linter with every rule on, summarize from its JSON, and optionally turn the findings into a page the user marks up.

    line 10
  2. Very specific:

    Never edit a file the user did not mark fix.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

stopslop

Run the linter with every rule on, summarize from its JSON, and optionally turn the findings into a page the user marks up.

Checklist

Copy this list and tick each step. A gate means stop and report if it fails.

  • 1. Install or verify the binary. Gate: no stopslop and no cargo means print the install line and stop. See references/install.md.
  • 2. Pick the scope: paths, --staged, --changed, or --since <ref>. See references/cli.md, and references/config-file.md for a repo stopslop.toml.
  • 3. Run the full report and save the JSON. Gate: exit 2 means show stderr and stop. See references/full-report.md.
  • 4. Summarize by tier, rule and file from the JSON. See references/full-report.md, and references/rules.md for rule groups.
  • 5. Offer to render the findings (opt-in). See references/render-and-fix.md.
  • 6. After the user marks the page, fix only the items marked fix, then re-run stopslop on the touched files. See references/render-and-fix.md, and references/suppressions.md for accepted findings.

Rules

  • Quote counts only from the JSON the run printed. Never estimate a number.
  • Take rule names and codes only from stopslop --list-rules. Never invent one.
  • Exit 0 under default settings does not mean clean: Tier B findings do not fail by default. The full report uses --fail-on-tier C.
  • Never edit a file the user did not mark fix.

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.

Check your setup, free