review-agents-md
AGENTS.md Skill
Overview
Creates and refactors AGENTS.md files following progressive disclosure principles. Keeps files minimal and focused—avoiding the "ball of mud" that hurts agent performance.
When to Use
- Proactively when a project has no
AGENTS.mdat the root — check for this when starting work in a new project - Creating a new AGENTS.md from scratch
- Refactoring a bloated AGENTS.md
- Reviewing an existing file for best practices
- Setting up AGENTS.md for a monorepo
- When
AGENTS.mdexists butCLAUDE.mdis missing (should be symlinked)
Core Principles
- Minimal by default: Only include what's relevant to every single task
- Progressive disclosure: Point to separate files, external docs, or agent skills for domain-specific rules
More from richtabor/agent-skills
humanize
Reviews and edits copy to remove AI-generated patterns and make text sound natural. Use when editing drafts, reviewing copy, "humanize this", "make it less AI", "sounds too AI", "remove AI patterns", "edit my copy", "this sounds robotic", or when text feels machine-generated.
108technical-writing
Writes technical blog posts about features being built. Triggers when user asks to write about development progress, implementations, or project updates.
43create-prd
Plan features interactively. Asks clarifying questions, then generates a detailed PRD document.
36motion-design
Provides motion design guidance for UI components. Triggers on animation requests ("animate this", "add transition", "motion for"), refinement requests ("clean up this animation", "clean up the motion", "this feels too fast/slow", "make this feel more alive/natural"), and questions about easing, timing, or micro-interactions.
28ralph-json-start-loop
Runs the Ralph autonomous loop. Executes stories from prds/*.json using git worktrees.
26ralph-json-create-issues
Converts a PRD or plan markdown file into prd.json format for ralph-json-start-loop to execute autonomously. Use when user wants to convert a PRD or plan to JSON stories.
23