Skills Catalog

Browse AI-analyzed skills from the global registry. Every skill is graded for safety, quality, clarity, and completeness.

362 skills published·Built on the agentskills.io standard·Compatible with Cursor, Claude Code, VS Code, GitHub Copilot, and 25+ more

Sign up free to add skills to your library and connect via MCP.

Get Started

362 skills found

Generate architecture documentation using C4 model Mermaid diagrams. Use when asked to create architecture diagrams, document system architecture, visualize sof… more

0~2.6k

Use this skill to monitor a deployed URL for regressions after deploys, merges, or dependency upgrades.

0~595
Yeachan-Heocancelv1.1

Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline, team)

0~4.6k

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, d… more

0~3.0k

Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carri… more

0~5.9k

Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results

0~687

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, regist… more

0~4.9k

When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the… more

0~4.4k

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Comm… more

0~1.2k

Provision instant temporary Postgres databases via Claimable Postgres by Neon (neon.new) with no login, signup, or credit card. Supports REST API, CLI, and SDK.… more

0~2.8k

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claud… more

0~2.1k
anthropicsclaude-apiv1.0

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API,… more

0~4.5k

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured… more

0~1.4k

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user… more

0~2.6k

Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produ… more

0~2.0k
affaan-mclickhouse-iov1.0

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

0~2.6k
openaicloudflare-deployv1.0

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or se… more

0~1.8k

Create CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs… more

0~1.7k

Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use whe… more

0~2.0k
softaworkscodexv1.1

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2… more

0~1.3k

Page 3 of 19

Why SkillRepo

The registry your agents deserve

Every skill is standards-compliant, safety-graded, and optimized for how AI agents actually work.

One MCP Connection

Connect your IDE once and access every skill in your library. No plugins, no extensions — just one standard protocol.

Safety Graded

Every skill is AI-analyzed across four dimensions — safety, quality, clarity, and completeness — and assigned a letter grade.

Open Standard

Every skill conforms to the agentskills.io standard — adopted by Cursor, Claude Code, GitHub Copilot, OpenAI Codex, and 25+ more. Portable, interoperable, never locked in.

Progressive Disclosure

Skills load in tiers — metadata first, then instructions, then resources — so agents stay fast and token-efficient.

Private & Public

Keep skills internal to your team or publish them to the global registry. You control visibility at every level.

Ready to start?

Create a free account and connect your IDE in under two minutes.

Get Started Free
362

Published Skills

2

Publishers

Start building with better skills

Free to use. No credit card required. Connect your IDE and start activating skills in minutes.

Add skills to your library

Command Palette

Search for a command to run...