A package manager for AI knowledge. Meta-skill for on-demand skill discovery and installation — search curated local repositories or the global skills.sh registry. Self-teaching capability that finds, evaluates, and installs relevant skills when the agent lacks expertise. Use when encountering unfamiliar frameworks, languages, tools, or domains. Use when you need to "learn a skill", "find skills for X", "search for skills", or when you lack expertise in a specific technology.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
A package manager for AI knowledge. Meta-skill for on-demand skill discovery and installation — search curated local repositories or the global skills.sh registry. Self-teaching capability that finds, evaluates, and installs relevant skills when the agent lacks expertise. Use when encountering unfamiliar frameworks, languages, tools, or domains. Use when you need to "learn a skill", "find skills for X", "search for skills", or when you lack expertise in a specific technology.
context
fork
Learning Skills
Overview
This skill runs in a forked context and helps you discover and install relevant skills for a given task using a two-tier approach:
Local repositories (preferred): Search through known, validated repositories in @./SKILL_REPOSITORIES.md
Remote search (fallback): Query the skills.sh API to discover skills from the broader ecosystem
Context: When invoked, use $ARGUMENTS to understand what skills are needed. For example, if invoked as /kung-fu Flask API with authentication, search for Flask and authentication-related skills.
First, run the add-skill CLI with the help flag to get a general understanding of what it does and how it works:
Install to user directory instead of project-level
-y, --yes
Skip confirmation prompts
-h, --help
Show help information
Reading
Read from the list of repositories in @./SKILL_REPOSITORIES.md and run each one:
npx -y add-skill <repository> --list
This displays a list of skill names and their associated descriptions.
Example
> npx -y add-skill vercel-labs/agent-skills --list
┌ skills
│
◇ Source: https://github.com/vercel-labs/agent-skills.git
│
◇ Repository cloned
│
◇ Found 2 skills
│
◇ Available Skills
│
│ vercel-react-best-practices
│
│ React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
│
│ web-design-guidelines
│
│ Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Do this for all known skill repositories.
Remote Search (skills.sh)
If no relevant skills are found in the known repositories, or if the user explicitly requests a remote search, use the skills.sh API to discover skills from the broader ecosystem.
When to use remote search:
User explicitly asks to "search for skills" or "find skills remotely"
No relevant skills found in @./SKILL_REPOSITORIES.md for the task at hand
Working with an unfamiliar technology or domain
Important: Before searching remotely, ask the user for confirmation unless they explicitly requested it.
