Agent skill

agents-md-authoring-majo

Write effective AGENTS.md files for AI coding agents.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill agents-md-authoring-majo --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 12 KB
Bundled scripts: none
Version: 2026.2.2
Declared author: Mark Joshwel <mark@joshwel.co>
Path: skills/agent/agents-md-authoring-majo/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# AGENTS.md Authoring Guide (Mark) **Goal**: Write effective, high-signal-to-noise AGENTS.md files that outperform skills-based approaches (100% vs 79% pass rate based on Vercel research). ## When to Use This Skill - **Creating a new AGENTS.md file** - **Updating an existing AGENTS.md** - **Optimizing agent context** for better performance - **Converting from skills-based approach to AGENTS.md** - **Setting up project documentation for AI agents** - **Monorepo with nested AGENTS.md files** ## When NOT to Use This Skill - **Writing end-user documentation** (use `writing-docs-majo`) - **Creating a new skill** (use `skill-authoring-majo`) - **Small project with obvious conventions** (AGENTS.md may be overkill) - **Documentation for non-agent consumption** ## Process 1. **Check existing AGENTS.md** - Read current file if it exists 2. **Measure current token count** - Target root file ≤ 800 tokens 3. **Apply 6-Core-Areas Framework**: - Commands (~80 tokens) - Exact copy-paste commands - Testing (~50 tokens) - Framework, location, coverage, run command - Project Structure (~50 tokens) - Strategic hints only - Code Style (~75 tokens) - One real example with positive & negative - Git Workf

What's inside
Steps it walks through
  1. When to Use This Skill
  2. When NOT to Use This Skill
  3. Process
  4. Constraints
  5. Core Principle
  6. AGENTS.md vs Skills: When to Use Each
  7. Six-Core-Areas Framework
  8. 1. Commands (~80 tokens)
  9. 2. Testing (~50 tokens)
  10. 3. Project Structure (~50 tokens)
  11. 4. Code Style (~75 tokens)
  12. 5. Git Workflow (~40 tokens)
  13. 6. Boundaries (~50 tokens)
  14. Token Efficiency Techniques
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the agents-md-authoring-majo skill do?

Write effective AGENTS.md files for AI coding agents.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill agents-md-authoring-majo --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going