
Official Anthropic Agent Skills repo with document and example packs
Send every non-trivial decision through a fresh-context adversarial review before it stands
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
Another one from Addy Osmani's agent-skills pack, built around the idea that a confident answer is cheaper to check now than to debug later.
Before a decision is accepted, the agent hands it to a reviewer with a clean context whose job is to poke holes in it: hidden assumptions, failure modes, edge cases. It is meant for high-stakes work such as auth changes, risky migrations, irreversible operations, or code you don't know well.
Slower than shipping straight through, on purpose.
Used it? Write the first review.

Official Anthropic Agent Skills repo with document and example packs

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

Official OpenAI Agent Skills for Codex and ChatGPT workflows

Translate Figma into production code at 1:1 fidelity