Roast a codebase with a brutally honest, funny code quality audit and a shareable report card. Analyzes the repo for shame commits, TODO graveyards, debug leftovers, god files, empty error handlers, deep nesting, and test-coverage gaps — then grades it A+ to F with a witty narrative and actionable fixes. Use when the user says: "roast my code", "roast this repo", "audit my codebase", "how bad is my code", "code roast", "grade my code", or anything implying a humorous or brutally honest code quality review.
EnglishGenerate a shareable Developer Identity Card from any git repo. Analyzes commit history, language breakdown, coding hours, and commit patterns to assign a developer archetype (e.g. "The Midnight Architect", "The Dawn Deployer", "The Firefighter") with a personality tagline and stats. Use when the user says: "make my dev card", "generate my dev card", "what's my developer archetype", "analyze my coding patterns", "dev card", "who am I as a developer", or anything implying a shareable developer identity or personality profile.
EnglishGenerate and publish a daily AI/LLM newsletter called "LLM Daily" that curates content from top sources (ArXiv, GitHub Trending, HuggingFace, VentureBeat, TechCrunch, Product Hunt). Use when user asks to: generate a newsletter, create today's LLM Daily, collect AI news, build an AI newsletter, publish newsletter, or run the daily newsletter pipeline. Also triggers on: "llm daily", "daily briefing", "AI newsletter", "generate newsletter", "collect news", "publish newsletter".
EnglishMonitior technology trends (GitHub, etc.), contextualize them against the user's project, and autonomously verify them through installation and testing. Use when the user asks about trending repositories, new tools, or wants to stay updated on tech relevant to their current work.
EnglishUse when a user wants a trust decision before installing from a skill URL, marketplace, or GitHub repo. It checks a compact allowlist of trusted distribution channels and returns whether the source should be trusted under the current TrustSkills policy, without drifting into explaining what the skill itself does unless the user asks.
English
AGENT SKILLS ATLASIncludes Code Roast, Sync Trending, Trustskills, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Code Roast
Roast a codebase with a brutally honest, funny code quality audit and a shareable report card. Analyzes the repo for shame commits, TODO graveyards, debug leftovers, god files, empty error handlers, deep nesting, and test-coverage gaps — then grades it A+ to F with a witty narrative and actionable fixes. Use when the user says: "roast my code", "roast this repo", "audit my codebase", "how bad is my code", "code roast", "grade my code", or anything implying a humorous or brutally honest code quality review.
Dev Card
Generate a shareable Developer Identity Card from any git repo. Analyzes commit history, language breakdown, coding hours, and commit patterns to assign a developer archetype (e.g. "The Midnight Architect", "The Dawn Deployer", "The Firefighter") with a personality tagline and stats. Use when the user says: "make my dev card", "generate my dev card", "what's my developer archetype", "analyze my coding patterns", "dev card", "who am I as a developer", or anything implying a shareable developer identity or personality profile.
LLM Daily
Generate and publish a daily AI/LLM newsletter called "LLM Daily" that curates content from top sources (ArXiv, GitHub Trending, HuggingFace, VentureBeat, TechCrunch, Product Hunt). Use when user asks to: generate a newsletter, create today's LLM Daily, collect AI news, build an AI newsletter, publish newsletter, or run the daily newsletter pipeline. Also triggers on: "llm daily", "daily briefing", "AI newsletter", "generate newsletter", "collect news", "publish newsletter".
Sync Trending
Monitior technology trends (GitHub, etc.), contextualize them against the user's project, and autonomously verify them through installation and testing. Use when the user asks about trending repositories, new tools, or wants to stay updated on tech relevant to their current work.
Trustskills
Use when a user wants a trust decision before installing from a skill URL, marketplace, or GitHub repo. It checks a compact allowlist of trusted distribution channels and returns whether the source should be trusted under the current TrustSkills policy, without drifting into explaining what the skill itself does unless the user asks.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Code Roast skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.