agentsclimarketplace

Agent rules

Skill ComeOnOliver/skillshub/skills/netresearch/agent-rules-skill/agent-rules

🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.From the repository description

Install
npx -y skills add ComeOnOliver/skillshub --skill agent-rules

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

3.6 KB, 855 tokens by cl100k_base, as published. Nobody here has run it

AGENTS.md Generator Skill

Overview

Generate and maintain AGENTS.md files following the agents.md convention. AGENTS.md is FOR AGENTS, not humans.

When to Use

  • Creating a new project and establishing baseline AGENTS.md
  • Standardizing existing projects with consistent agent documentation
  • Ensuring multi-repo consistency across repositories
  • Checking if AGENTS.md files are current with recent code changes
  • Onboarding AI agents to an unfamiliar codebase

Quick Reference

ScriptPurpose
scripts/generate-agents.sh PATHGenerate AGENTS.md files
scripts/validate-structure.sh PATHValidate structure compliance
scripts/check-freshness.sh PATHCheck if files are outdated vs git commits
scripts/verify-content.sh PATHVerify documented files/commands match codebase
scripts/verify-commands.sh PATHVerify documented commands execute
scripts/detect-project.sh PATHDetect language, version, build tools
scripts/detect-scopes.sh PATHIdentify directories needing scoped files
scripts/extract-commands.sh PATHExtract commands from build configs

See references/scripts-guide.md for full options and validation checklist.

Core Principles

  • Structured over Prose -- tables and maps parse faster than paragraphs
  • Verified Commands -- commands that don't work waste 500+ tokens debugging
  • Pointer Principle -- point to files, don't duplicate content
  • Golden Samples -- one example file beats pages of explanation
  • Audit Before Generating -- discover existing docs and pain points before running scripts

Language Choice

Default to English. Exception: match your code's naming language to prevent agents mixing languages.

Prerequisites

RequirementVersionNotes
Bash4.3+Nameref variables (local -n). macOS: brew install bash
jq1.5+JSON processing
git2.0+For git history analysis

References

Detailed documentation in references/:

FileContents
verification-guide.mdVerification steps, name matching, command verification, design principles
scripts-guide.mdScript options, post-generation validation checklist
ai-tool-compatibility.mdClaude Code shim, Codex stacking, Copilot integration
output-structure.mdRoot/scoped sections, auto-generate vs manual curation
analysis.mdAnalysis of 21 real-world AGENTS.md files
directory-coverage.mdCoverage guidance for PHP/TYPO3, Go, TypeScript
examples/Complete examples (coding-agent-cli, ldap-selfservice, simple-ldap-go, t3x-rte-ckeditor-image)

Asset Templates

Root templates in assets/: root-thin.md (~30 lines, default), root-verbose.md (~100 lines).

Scoped templates in assets/scoped/: backend-go.md, backend-php.md, typo3.md, oro.md, cli.md, frontend-typescript.md.

Supported Project Types

LanguageProject Types
GoLibraries, web apps (Fiber/Echo/Gin), CLI (Cobra/urfave)
PHPComposer packages, Laravel/Symfony
PHP/TYPO3TYPO3 extensions (auto-detected via ext_emconf.php)
PHP/OroOroCommerce, OroPlatform, OroCRM bundles
TypeScriptReact, Next.js, Vue, Node.js
Pythonpip, poetry, Django, Flask, FastAPI
HybridMulti-language projects (auto-creates scoped files per stack)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,546. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.