agentleFS
Sign inStart free
mahik504mahik504/orchestra-workflow/skills/humanizer/AGENTS.md

orchestra-workflow / humanizer

AGENTS.md1 starsChanged 18 days agoMITView on GitHub

This file explains how to change Humanizer without breaking its package or prompt. Humanizer is an agent skill written in Markdown. SKILL.md is the prompt that agents read. The repo has no build step. Keep the skill portable. Do not write instructions that limit it to one or two agent tools. Keep SKILL.md and README.md in sync. Use Plain Language in code comments, prompts, documentation, descriptions, validation messages, and progress reports.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

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

19 rules. About 0 are common, 13 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the skill portable. Do not write instructions that limit it to one or two agent tools.

    line 9
  2. Very specific:

    Keep SKILL.md and README.md in sync.

    line 24
  3. Very specific:

    Version: Keep the same version in SKILL.md under metadata.version, the first CHANGELOG.md heading, .claude-plugin/plugin.json, and …

    line 27
  4. Distinctive:

    Compatibility: Keep install and use instructions neutral across agents.

    line 28
  5. Very specific:

    Length: Every word of SKILL.md is read on each use.

    line 30
  6. Very specific:

    History: Add a short CHANGELOG.md note for any behavior change or non-obvious fix.

    line 31
  7. Very specific:

    Checks: Before publishing, run python3 scripts/validate-package.py, npx skills add .

    line 32
  8. Distinctive:

    Use Plain Language in code comments, prompts, documentation, descriptions, validation messages, and progress reports.

    line 36
  9. Distinctive:

    Use common words and active voice.

    line 39
  10. Distinctive:

    Keep sentences and paragraphs short.

    line 40
  11. Distinctive:

    Use one term for the same item.

    line 41
  12. Very specific:

    Use must for requirements.

    line 42
  13. Distinctive:

    Use headings, lists, and tables when they help the reader.

    line 43
  14. Distinctive:

    Remove repeated or unnecessary words.

    line 44
  15. Distinctive:

    Keep exact identifiers, commands, paths, schema fields, quotations, watched phrases, and behavior-bearing examples.

    line 47
  16. Distinctive:

    Keep the full technical meaning.

    line 48
  17. Distinctive:

    Keep the YAML metadata valid.

    line 52
  18. Distinctive:

    Treat the prompt below the metadata as the product.

    line 53
  19. Distinctive:

    Prefer a short, clear instruction over another exception or repeated explanation.

    line 54

≈ “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

Guide for agents

This file explains how to change Humanizer without breaking its package or prompt.

What this repo contains

Humanizer is an agent skill written in Markdown. SKILL.md is the prompt that agents read. The repo has no build step.

Keep the skill portable. Do not write instructions that limit it to one or two agent tools.

Key files

  • SKILL.md is the source of truth and the repo's only skill file. It contains portable YAML metadata, an account of why AI text sounds the way it does, and numbered patterns grouped in six sections and ordered by strength and frequency.
  • README.md explains installation, use, and patterns.
  • CHANGELOG.md holds the release notes, newest first. Old notes keep the pattern numbers their release used.
  • .claude-plugin/plugin.json describes the Claude plugin and points its skill loader at the root SKILL.md.
  • .claude-plugin/marketplace.json lets users add this repo as a Claude marketplace.
  • .cursor-plugin/plugin.json describes the Cursor plugin. Omit a skills path so Cursor loads the root SKILL.md.
  • agents/openai.yaml holds the display name, short description, and default prompt for OpenAI-compatible agents.
  • scripts/validate-package.py checks package files and shared values.

Rules for changes

Keep SKILL.md and README.md in sync.

  • Patterns: Patterns are numbered from 1 without gaps, strongest and most frequent first. A new tell earns a pattern only when no existing pattern already implies it; prefer folding it into an existing pattern. If you add, remove, or renumber a pattern, update the README tables, the README section title, and every §reference. The validator derives the count from the headings and checks that README pattern names match them.
  • Version: Keep the same version in SKILL.md under metadata.version, the first CHANGELOG.md heading, .claude-plugin/plugin.json, and .cursor-plugin/plugin.json. Do not add a top-level version field to the skill.
  • Compatibility: Keep install and use instructions neutral across agents. Names such as Claude Code, Cursor, OpenCode, and Codex are examples, not limits.
  • Description: The plugin manifests use the first sentence of the SKILL.md description.
  • Length: Every word of SKILL.md is read on each use. The validator caps it at 5,500 words; a change that adds words should earn them.
  • History: Add a short CHANGELOG.md note for any behavior change or non-obvious fix.
  • Checks: Before publishing, run python3 scripts/validate-package.py, npx skills add . --list, and claude plugin validate ..

Writing style

Use Plain Language in code comments, prompts, documentation, descriptions, validation messages, and progress reports.

  • Lead with the main point.
  • Use common words and active voice.
  • Keep sentences and paragraphs short.
  • Use one term for the same item.
  • Use must for requirements.
  • Use headings, lists, and tables when they help the reader.
  • Remove repeated or unnecessary words.
  • Limit acronyms and explain technical terms.
  • Avoid double negatives.
  • Keep exact identifiers, commands, paths, schema fields, quotations, watched phrases, and behavior-bearing examples.
  • Keep the full technical meaning.

Editing the skill

  • Keep the YAML metadata valid.
  • Treat the prompt below the metadata as the product.
  • Prefer a short, clear instruction over another exception or repeated explanation.

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