Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
25 skills
Matt Pocock· Community
A meta-skill designed to force an agent to re-evaluate and re-pitch its previous output using specific linguistic constraints.
Addy Osmani· Community
A framework for curating and structuring information to improve AI agent performance and output accuracy.
Seth Hobson· Community
A collection of patterns and techniques for designing, optimizing, and structuring LLM prompts.
Seth Hobson· Community
An expert prompt engineer providing structured, production-ready prompt designs and optimization strategies for LLMs.
GitHubOfficial
A generator for creating comprehensive, technology-agnostic prompts to document application workflows and architectural patterns.
GitHubOfficial
An interactive workflow for refining and structuring high-quality AI prompts.
GitHubOfficial
Automate GitHub Copilot CLI personalization by analyzing conversation history to extract and apply user-specific behavioral patterns.
GitHubOfficial
A persona that forces the AI to provide responses using minimal, token-efficient language.
GitHubOfficial
A specialized chat mode that analyzes and refines user inputs into structured, high-quality system prompts.
GitHubOfficial
A system prompt designed to enforce rigorous, transparent, and autonomous reasoning processes for AI agents.
GitHubOfficial
A persistent shorthand mode for AI agents to reduce token usage while maintaining technical precision.
GitHubOfficial
An expert dual-persona system for engineering, researching, and validating high-quality AI prompts.
GitHubOfficial
Refine and polish AI agent prompt files using proven structural and linguistic best practices.
GitHubOfficial
A translation layer that makes Copilot CLI accessible to non-technical users through plain-English explanations and risk-aware guidance.
GitHubOfficial
Generates concise, actionable tldr-style summaries for GitHub Copilot customization files, MCP servers, and documentation.
GitHubOfficial
Transforms rough ideas or draft prompts into polished, ready-to-use prompts for chat-based LLM interactions.
GitHubOfficial
A systematic framework for auditing and refining AI prompts for safety, bias, security, and effectiveness.
Trail of BitsOfficial
Drafts and formats copy-paste-ready /goal commands for Claude Code and Codex to ensure precise, verifiable long-running agent tasks.
Meng To· Community
Draft, refine, and manage X posts in the voice of Meng To using a verified corpus of his authored content.
HumanLayerOfficial
A methodology for optimizing CLAUDE.md files using conditional XML blocks to improve agent instruction adherence.
Builder.ioOfficial
A mandatory protocol for grounding AI responses in authoritative, up-to-date documentation rather than model memory.
Builder.ioOfficial
A standardized convention for providing clear, color-coded status updates at the end of AI agent responses.
MicrosoftOfficial
An opt-in response style that compresses assistant prose to reduce token count while maintaining technical precision.
SentryOfficial
A structured, evidence-based workflow for creating, refining, and optimizing AI agent prompts using evaluation-driven iteration.