agentleFS
Sign inStart free
sammcjsammcj/agentic-coding/Skills/rewrite-slop/CLAUDE.md

agentic-coding / rewrite-slop

CLAUDE.md167 starsChanged 10 days agoApache-2.0View on GitHub

When asked to update or improve this skill, check whichever of these are available before deciding what to change. Each moves on its own schedule. None is required: skip any that is missing rather than trying to obtain it. After making any change to this skill (SKILL.md, resources, scripts): You MUST update CHANGELOG.md:

We split this CLAUDE.md into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When asked to update or improve this skill, check whichever of these are available before deciding what to change.

    line 5
  2. Very specific:

    If the skill-creator-primer skill is installed, its scripts/validate_skill.py holds detection this skill borrows from (_FILLER_RULES, blob …

    line 7
  3. Very specific:

    After making any change to this skill (SKILL.md, resources, scripts): You MUST update CHANGELOG.md:

    line 19
  4. Very specific:

    Add a concise TLDR of the change(s) as bullet point(s) under today's date heading (## YYYY-MM-DD, newest first), creating the heading if it …

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md 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
CLAUDE.md

rewrite-slop Rules

Check the upstream sources when updating this skill

When asked to update or improve this skill, check whichever of these are available before deciding what to change. Each moves on its own schedule. None is required: skip any that is missing rather than trying to obtain it.

  • If the skill-creator-primer skill is installed, its scripts/validate_skill.py holds detection this skill borrows from (_FILLER_RULES, blob and structure analysis, grouped findings). Reconcile any rule that exists in both.
  • references/refresh-vocabulary.md carries the procedure and the traps. Follow it rather than re-deriving from scratch.
  • references/html-report.md instructs the agent on how to generate a static HTML report if requested.

External resources

  • github.com/louisabraham/load-bearing, the ranking behind Tier 2. Re-fits daily.
  • github.com/berenslab/llm-excess-vocab, the excess ratios behind Tier 3.

Update CHANGELOG.md after changes

After making any change to this skill (SKILL.md, resources, scripts): You MUST update CHANGELOG.md:

  • Add a concise TLDR of the change(s) as bullet point(s) under today's date heading (## YYYY-MM-DD, newest first), creating the heading if it doesn't exist. No versioning is required.
  • Squash changes within the same day (do not add changes to changes).

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