agentleFS
Sign inStart free
YuliangXiuYuliangXiu/de-ai-router/skills/humanize/AGENTS.md

de-ai-router / humanize

AGENTS.md9 starsChanged 49 days agoMITView on GitHub

Guidance for AI coding agents working in this repository. A kit for keeping AI-flavored writing out of prose and repos. Three artifacts matter:

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. unknownking07/claude-skills★ 1100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository11 other files it gives its agents.

The file

We split this AGENTS.md 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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Every new rule in slop-rules.json gets a test in tests/sloplint.test.js.

    line 18
  2. Distinctive:

    Keep install and usage language harness-neutral.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
AGENTS.md

AGENTS.md

Guidance for AI coding agents working in this repository.

What this repo is

A kit for keeping AI-flavored writing out of prose and repos. Three artifacts matter:

  • SKILL.md: the humanizer skill. Portable YAML frontmatter followed by the numbered pattern catalog. Source of truth for the 41 patterns. Edit it like a careful instruction document, not code.
  • rules/slop-rules.json: the machine-readable rule pack. Source of truth for what sloplint flags. Vocabulary tiers, phrases (with optional fix), and regex detectors.
  • bin/sloplint.js: the zero-dependency scanner. Keep it dependency-free and Node 18 compatible.

The maintenance contract

  • The skill currently defines 41 numbered patterns. If you add, remove, or renumber any, update the README, the skill frontmatter description, and every cross-reference in the same change.
  • The pattern catalog (SKILL.md) and the rule pack (slop-rules.json) overlap but are not mirrors: the skill holds judgment calls a regex can't make; the rule pack holds only what a machine can check without heavy false positives. When you add a mechanically checkable pattern to one, consider the other.
  • Version lives in three places: SKILL.md frontmatter (metadata.version), package.json, and .claude-plugin/plugin.json. Bump them together.
  • Every new rule in slop-rules.json gets a test in tests/sloplint.test.js. Run npm test before finishing.
  • Keep install and usage language harness-neutral. The skill should work anywhere markdown skills load.
  • This repo's own prose follows its own rules: no em dashes, sentence-case headings, no filler. Run sloplint score README.md after editing docs. The references/ files are exempt where they quote slop as examples.

Watch out for

  • prepareText blanks regions instead of deleting them so line numbers stay correct. Preserve that invariant.
  • Tier 2 vocabulary only flags when two or more distinct terms appear; tier 3 only above a density threshold. Don't "fix" that into always-flag; it exists to avoid false positives on human writing.
  • applyFixes must stay conservative: only mechanical, meaning-preserving replacements belong there. Judgment calls belong in the skill.

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