netresearch/agent-rules-skill / skills/agent-rules
agent-rules
UnverifiedUse when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.
AGENTS.md Generator Skill
Generate and maintain AGENTS.md files following the agents.md convention. AGENTS.md is FOR AGENTS, not humans.
When to Use
- Creating or updating AGENTS.md for new/existing projects
- Scaffolding a new repository — ship AGENTS.md with the initial commits; retrofitting later needs full re-verification
- Standardizing agent documentation across repositories
- Checking AGENTS.md freshness after code changes
- Onboarding AI agents to an unfamiliar codebase
Scripts
Call every script by its full path: bash ${CLAUDE_SKILL_DIR}/scripts/<name> PATH. Calling one relative to the working directory is not covered by the frontmatter rule and raises a permission prompt per call.
| Script | Purpose |
|---|---|
generate-agents.sh PATH | Generate AGENTS.md files |
validate-structure.sh PATH | Validate structure compliance |
check-freshness.sh PATH | Check if files are outdated |
verify-content.sh PATH | Verify documented files/commands match codebase |
verify-commands.sh PATH | Verify documented commands execute |
score-agents.sh PATH | Grade AGENTS.md quality, worst-first |
detect-project.sh PATH | Detect language, version, build tools |
detect-scopes.sh PATH | Identify directories needing scoped files |
extract-commands.sh PATH | Extract commands from build configs |
extract-ci-rules.sh PATH | Extract CI quality gates and version matrix |
extract-architecture-rules.sh PATH | Extract module boundaries |
extract-adrs.sh PATH | Extract architectural decision records |
extract-github-rulesets.sh PATH | Extract GitHub rulesets and merge rules |
See references/scripts-guide.md for full options.
Workflow
- Detect:
detect-project.sh+detect-scopes.sh— stacks and subsystems - Extract:
extract-commands.sh,extract-ci-rules.sh— gather facts - Generate:
generate-agents.sh --style=thin(default) or--verbose - Verify:
verify-content.sh+verify-commands.sh-- MANDATORY before done. Replace the generated**Changelog:**TODO: name the file, its format and which PR writes the entry, read from the last merged PRs (AG-32, AG-33) - Line cap: before committing any root AGENTS.md edit,
wc -l AGENTS.mdmust be under 150 (harnessAH-02); run the repo'sverify-harness.shwhere it exists -- CI's harness check fails otherwise
--update preserves curated content outside <!-- GENERATED --> markers.
Core Principles
- Structured over Prose -- tables parse faster than paragraphs
- Never Fabricate -- only document what exists; verify every command and path
- Pointer Principle -- point to files, don't duplicate content
- Auto Symlinks -- CLAUDE.md/GEMINI.md by default (
ai-tool-compatibility.md)
References
| File | Contents |
|---|---|
verification-guide.md | Verification steps, anti-bloat, preservation check |
fleet-sync-sweep.md | Fleet-wide AGENTS.md sweeps |
scripts-guide.md | Script options, validation checklist |
quality-rubric.md | Grading rubric |
ai-tool-compatibility.md | 16-agent compatibility matrix |
output-structure.md | Root/scoped sections |
git-hooks-setup.md | Hook framework setup |
examples/ | Complete examples |
ai-contribution-guidelines.md | "3 Cs" AI-contribution framework |
directory-coverage.md | Scoped-file coverage rationale |
feedback-memory-schema.md | Approved-learning file format |
Templates
Root: assets/root-thin.md (default) or root-verbose.md. Scoped: assets/scoped/, one per stack (Go/PHP/Python/TYPO3/Symfony/Oro/CLI/TS/skill-repo).
Supported Projects
Go, PHP (Composer/Laravel/Symfony/TYPO3/Oro), TypeScript (React/Next/Vue/Node), Python (pip/poetry/ruff/mypy), skill repos, hybrid.
See Also
agent-harness-skill— agent-readiness harness (CI enforcement).skill-repo-skill— skill-repo structure (plugin.json, licensing, releases).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 464k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 196k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |