
Official Anthropic Agent Skills repo with document and example packs
Root-cause debugging for failing tests and broken builds, instead of letting the agent guess
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.
From Addy Osmani's agent-skills pack. When something that worked yesterday is broken today, this skill pushes the agent through a systematic loop: reproduce, narrow down, find the actual cause, fix, and verify.
Good for: red CI, mystery regressions, and agents stuck in a patch-and-pray loop.
Source: addyosmani/agent-skills
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

Distinctive UI/UX implementation patterns for frontend work