Claude Code
Claude Code skills are designed for Anthropic's terminal-first coding agent workflow. Developers usually browse this page for repo-aware prompts, debugging helpers, refactoring guidance, setup automations, and other skills that fit command-line software work.
Skills compatible with Claude Code
langchain
Framework for building LLM applications with agents, chains, RAG, and 500+ integrations.
autonomous-agent-patterns
Design patterns for building autonomous coding agents with tool integration, permissions, and human oversight.
dbs-unblock
你是 dontbesilent 的执行力诊断 AI。你的任务是帮用户搞清楚：为什么他知道该做什么，但就是不做。
frontend-design
Distinctive, production-grade frontend interfaces that reject generic AI aesthetics.
agent-browser
Fast, persistent browser automation with session continuity across sequential agent commands.
agent-browser
Fast, persistent browser automation with session continuity across sequential agent commands.
agent-browser
Fast, persistent browser automation with session continuity across sequential agent commands.
agent-browser
Fast, persistent browser automation with session continuity across sequential agent commands.
agent-browser
Fast, persistent browser automation with session continuity across sequential agent commands.
agent-browser
Fast, persistent browser automation with session continuity across sequential agent commands.
skill-creator
Create, test, and iteratively improve AI agent skills with structured evaluation and benchmarking.
Comprehensive PDF processing with text extraction, merging, splitting, form filling, and OCR capabilities.
pptx
Create, edit, read, and manipulate PowerPoint presentations with design guidance and quality assurance workflows.
critique
Evaluate design effectiveness across visual hierarchy, information architecture, emotional resonance, and user experience quality.
running-claude-code-via-litellm-copilot
Use this skill for the specific workaround where Claude Code keeps its Anthropic-shaped client behavior, but the actual backend traffic is sent to a local LiteLLM proxy and then forwarded to GitHub Copilot.
skills-cli
Use this skill to help users work with the open Agent Skills ecosystem through the skills CLI.
using-superpowers
Source details, install context, and public review data are available on the full page.
docx
Create, read, edit, and manipulate Word documents (.docx files) with full formatting control.
xlsx
Create, edit, and analyze Excel spreadsheets with formulas, formatting, and error-free calculations.
executing-plans
Execute a written implementation plan with critical review and task checkpoints.
webapp-testing
Native Python Playwright scripts for testing local web applications with server lifecycle management.
receiving-code-review
Evaluate code review feedback with technical rigor before implementing, avoiding performative agreement and blind implementation.
writing-skills
Test-driven documentation for creating reusable agent techniques, patterns, and reference guides.
teach-impeccable
One-time setup that gathers design context and persists it to your AI config file.