Official Anthropic Agent Skills repo with document and example packs
Intended vs Implemented
SkillAudit AI-built code for gaps between what the docs promise and what the code does
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Product badge
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
About Intended vs Implemented
A method for the bugs linters miss because they have no idea what you meant: a permission that's documented but never enforced, an endpoint that's supposed to be internal but isn't. It defines what counts as intent, what counts as evidence in the code, and how to report concrete mismatches instead of vague worries.
Good for reviewing vibe-coded apps before real users arrive. From phuryn's pm-skills collection.
No reviews yet
Used it? Write the first review.
Similar skills
Official Browserbase skills for cloud browser automation
Production agent skills from Matt Pocock's .agents directory
Build and review ASP.NET Core apps with current official guidance
39 editorial HTML/SVG diagram types for Claude Code and Codex
Official OpenAI Agent Skills for Codex and ChatGPT workflows