awesome-claude-skills
Wrapper/index for the awesome-claude-skills collection repository.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,657 results
building-livekit-agents
Builds voice and chat AI agents with LiveKit Agents on LiveKit Cloud or a self-hosted server. Use when the user asks to "build a voice agent", "create a…
testing-livekit-agents
Writes turn-level tests for a LiveKit agent in the user's normal test suite: pytest (Python) or Vitest (Node.js). Use when the user asks to "write tests for my…
night-park
Parks the current Claude Code session as a day-over close. Analyzes the conversation, writes a handoff document to docs/handoffs/ (versioned in git), mirrors…
cursor-cli
Run Cursor Agent headlessly and delegate work to another Cursor agent over the CLI. Use when the user asks to call, ask, invoke, run, or delegate to Cursor…
gpt-5.6-terra
Use when the user wants balanced general-purpose reasoning, production workflows, conversational intelligence, and enterprise tasks using OpenAI GPT-5.6 Terra…
firecrawl-agent
Autonomous multi-page extraction into structured JSON. Use when the user wants website data matching a schema — pricing tiers, product listings — beyond a…
handoff-create
Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current…
plan-pipeline
Orchestrates the complete planning pipeline: product direction (ceo-review) -> architecture (eng-review) -> implementation plan (start) -> validation…
scaffold
Interactive coach that asks 4-5 questions to determine whether you need an agent, command, skill, hook, or rule, then generates a ready-to-use template. Usage:…
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
loop-orchestrator
Operate a fleet of durable agent loops under .loop/ — schedule which loop runs next, assign agents to roles (maker vs checker), enforce promotion gates from…
agent-behavior-audit
Audits agent execution records for instruction compliance, outcome quality, and wasted work using source-backed evidence. Use when asked to audit or analyze…
openspec-workspace-gates
Shared OpenSpec workspace gates for OPSX workflows: locate project root, verify openspec/, and require exact native OPSX skills before delegation. Triggers —…
pdca-review-orchestration
Shared orchestration for PDCA solution-review stages: requires full decision review, code-design review for code-affecting solutions, binary pass/fail, bounded…
blender-mcp-setup
Set up or diagnose the plugin-owned Blender MCP connection when Blender is missing, the Add-on is disabled, Start MCP Server has not been clicked, or no…
dreamina-canvas-cli-ref2video
Use when the user requests a Dreamina canvas reference material video; only responsible for input, parameter validation, drafts, and scene acceptance for m2v / first_last_frame modes; public canvas materials, paid runs, and recovery are maintained by dreamina-canvas-cli.
bt-mcp-setup
MCP protocol integration guide for Baota Linux Panel 13.0. Covers installation prerequisites, opening port 8765, IP whitelist, MCP client configuration examples for Codex/ZCode/Kimi/Claude Code, Bearer Token authentication, HTTPS certificate requirements, and troubleshooting table. When users want to integrate AI...
bt-mcp-tools
Quick reference for the 98 tools of the MCP protocol of Baota Linux Panel 13.0. Organized into 19 categories (Basic/Website/Network/Database/Service/Docker/System/Software/Firewall/Java/Node/Python/Go/Reverse Proxy/HTML/SSH/Security/Scheduled Tasks/Notification), with each line noting the tool name, risk level, one-sentence function, key parameters, and mapping to general tools. When…
bt-panel-ops
Comprehensive BT Panel Linux operations: full-scenario comprehensive diagnostics for websites/databases/services/Docker/firewall/SSL/scheduled tasks/notifications. When users need to troubleshoot operations issues in a BT Panel deployment environment, this skill integrates the diagnostic key points of 14 built-in BT Panel skill agents, providing a structured diagnostic process, command checklist, and cross-domain correlation analysis. Read this skill...
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through…
fuse-browser-usage
Use when about to call any mcp__fuse-browser__* tool. Routes fetch/crawl/SERP vs live browser session vs screenshot capture, and enforces the 4 ZERO-TOLERANCE…