richtabor/agent-skills
Overview
This skill creates and refactors AGENTS.md files that are minimal, focused, and follow progressive disclosure. I keep the root file tiny—only what every agent needs—and move domain rules into linked docs or agent skills. The goal is better agent behavior by lowering instruction noise and token cost.
How this skill works
I detect whether AGENTS.md or CLAUDE.md exists and propose fixes (create, symlink, or merge). I read or build a one-sentence project description, record nonstandard package/build/test commands, estimate token cost, and extract only the essentials for the root file. I then produce the new AGENTS.md, any auxiliary docs for progressive disclosure, and a changelog of removed or relocated content with reasons.
When to use it
- Project has no AGENTS.md at the root (proactive check)
- Create a new AGENTS.md from scratch
- Refactor a bloated or contradictory AGENTS.md
- Review agent configuration when CLAUDE.md is missing or mis-symlinked
- Set up AGENTS.md for a monorepo with per-package rules
Best practices
- Keep root AGENTS.md minimal: project one-liner, package manager if nonstandard, and nonstandard build/test commands
- Use progressive disclosure: link to docs/ files or agent skills for domain specifics
- Never document file paths or exhaustive file trees in the root file
- Avoid obvious, vague, or opinionated rules—delete or move them
- Make CLAUDE.md a symlink to AGENTS.md; do not maintain a standalone CLAUDE.md
Example use cases
- Generate a 6-line AGENTS.md for a new repo (project purpose, package manager, special commands, pointers)
- Refactor an existing AGENTS.md into a minimal root plus docs/TYPESCRIPT.md and docs/TESTING.md
- Detect a standalone CLAUDE.md and replace it with a symlink to AGENTS.md
- Create nested AGENTS.md files for a monorepo root and per-package overrides
- Produce a list of removed/relocated items with rationale for a PR description
FAQ
Every token in AGENTS.md loads on every agent request; small files reduce noise and improve instruction consistency.
What belongs in separate docs instead of the root file?
Language conventions, workflow guides, detailed patterns, and file trees belong in docs/ files or agent skills—anything not relevant to every task.
10 skills
This skill creates and refactors AGENTS.md files using progressive disclosure to keep root docs minimal and focused.
This skill performs manual accessibility reviews against WCAG AA, identifying issues and suggesting practical fixes to improve inclusivity.
This skill runs the Ralph autonomous loop to execute prds using git worktrees, coordinating progress and dependencies.
This skill helps you generate OpenGraph and Twitter share images for Next.js by applying best-practice layout, fonts, and metadata.
This skill adds thorough alt text to markdown images by analyzing content and updating Obsidian or standard markdown embeds.
This skill helps you create a PRD interactively, asking clarifying questions and generating a detailed document for feature planning.
This skill helps you rewrite copy to remove AI patterns and sound more natural while preserving meaning and intent.
This skill validates agent skills against best practices, auditing structure, frontmatter, triggers, and anti-patterns to improve overall quality.
This skill re-reads your recent code changes with a fresh perspective to spot bugs, errors, and readability issues.
This skill provides motion design guidance for UI components, recommending easing, duration, and implementation to make interactions purposeful and delightful.
