fable-intake
Think like Claude Fable at the moment a request arrives — before the first tool call. Decides whether the deliverable is a change or an assessment (act or…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
skill-catalog-builder
Build a bounded Agent Skill catalog across explicit discovery scopes and report collisions before loading instruction bodies.
skill-invocation-router
Design and test explicit human, implicit model or agent, programmatic application, bounded skill-composition, and harness activation policies for an Agent…
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…
coverage-ratchet
Gate test coverage with a ratchet — a committed baseline that coverage may never drop below and only ever rises. Ships a coverage-gate script (xccov-based)…
infinitetalk
Generate and edit video with InfiniteTalk through RunAPI. Use when the user asks an agent to create, edit, or transform video with InfiniteTalk. Default to the…
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with…
list-templates
List the available harness templates and what each one ships with. Use when the user asks "what templates are available", "what verticals does the harness…
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…
anthropic-skill-creator
Design, review, and improve Claude/Codex skills based on Anthropic's "The Complete Guide to Building Skills for Claude". Use when creating a new skill,…
mcp-chrome-devtools
This skill provides guidance for using Chrome DevTools MCP for browser debugging and automation. Use when debugging web pages, analyzing performance,…
jev-use
Use Jev to choose the next step based on interface text, executed and verified by Codex Computer Use. Suitable for cases that explicitly require jev-use, Jev computer operation, or step-by-step decision comparison experiments; not for pure visual design and modeling.
agentic-product-prototyping
Build functional software prototypes and MVPs without deep technical skills by using AI agents as "developers in your pocket." Use this skill when you need to…
ai-app-performance-optimization
Shift focus from AI hype (latest models, vector DBs, agentic frameworks) to high-leverage activities that actually improve product quality. Use this when an AI…
ai-product-strategy-mapping
A framework to assess and integrate AI into your product strategy by mapping core customer problems to AI capabilities. Use this when your industry is facing a…
answer-engine-optimization-playbook
Strategies for getting products and content cited within LLM responses (ChatGPT, Perplexity, Claude). Use this when launching a new product, seeing referral…
building-with-ai-engineers
A framework for collaborating with AI software agents to build functional products. Use this skill when generating initial prototypes from natural language,…
deep-dive-portfolio-management
A high-leverage leadership framework for maintaining a high quality bar across a large volume of projects. Instead of staying "high-level" on everything,…
full-stack-ai-product-building
Use AI to transform product intent into production-ready software. Use this skill when you need to prototype a new feature, build a functional MVP without…
huggingface-playbook
Publishes a company's own models, datasets and Spaces demos on the Hugging Face Hub - org verification, repo-per-variant layout, card metadata, license and…
ai-multimodal
Multimodal AI processing via Google Gemini API (2M tokens context). Capabilities: audio (transcription, 9.5hr max, summarization, music analysis), images…
claude-code
Documentation and capabilities reference for claude-code
claude-extensibility
Claude Code extensibility: agents, skills, output styles. Capabilities: create/update/delete agents and skills, YAML frontmatter, system prompts, tool/model…
telegram-voice-group
Send voice messages to a specified Telegram group