docs/skills.mdx
Skills are reusable prompt templates that extend the capabilities of your AI coding assistants. They allow you to share and install common workflows like React best practices, web design guidelines, PDF processing, and more across projects and teams.
Context7 maintains a registry of skills at context7.com/skills that can be installed directly into your AI coding assistant with a single command.
Skills follow the Agent Skills open standard — a specification that works across multiple AI coding tools. A skill is a directory containing a SKILL.md file with instructions that your AI assistant loads when relevant.
Why use skills?
Popular skills:
| Skill | What it does |
|---|---|
vercel-react-best-practices | Teaches Claude modern React patterns, Server Components, and performance optimization |
web-design-guidelines | Guides Claude on UI/UX principles, spacing, typography, and responsive layouts |
pdf / docx / xlsx | Enables Claude to read, create, and manipulate Office documents and PDFs |
supabase-postgres-best-practices | Helps Claude write optimized Postgres queries, RLS policies, and auth flows |
seo-audit | Lets Claude analyze pages for SEO issues and suggest improvements |
browser-use | Allows Claude to control browsers for testing and automation |
The Context7 Skills Registry is a searchable marketplace of skills indexed from GitHub repositories. Each skill is identified by its repository path (e.g., /anthropics/skills) and skill name.
When browsing or searching skills, you'll see:
| Field | Description |
|---|---|
| Name | The skill identifier used for installation |
| Description | What the skill does and when to use it |
| Install Count | Number of times the skill has been installed |
| Trust Score | Quality and safety indicator (0-10) |
You can interact with the registry directly from your terminal using the ctx7 CLI. No configuration needed — most commands work without authentication.
Discover and install skills:
# Search the registry by keyword
ctx7 skills search pdf
ctx7 skills search "react testing"
# Browse all skills in a specific repository
ctx7 skills info /anthropics/skills
# Install a skill interactively (prompts you to pick)
ctx7 skills install /anthropics/skills
# Install a specific skill by name
ctx7 skills install /anthropics/skills pdf
# Get suggestions based on your project's dependencies
ctx7 skills suggest
Manage installed skills:
# List skills installed in the current project
ctx7 skills list
# List skills installed for a specific client
ctx7 skills list --claude
ctx7 skills list --cursor
# Remove a skill
ctx7 skills remove pdf
Generate a custom skill with AI:
# Requires login — opens an interactive generation flow
ctx7 login
ctx7 skills generate
All install commands accept --claude, --cursor, --universal, and --global flags to target a specific client or install location.
See the CLI reference for the full flag reference and examples.
Context7 vets every skill in the registry before it reaches you — both through automated scanning and community-driven quality signals.
Every skill has a trust score from 0 to 10 that reflects the reliability of its source.
| Score | Level | Meaning |
|---|---|---|
| 7.0 - 10.0 | High | Verified or well-established source |
| 3.0 - 6.9 | Medium | Standard community contribution |
| 0.0 - 2.9 | Low | New or unverified — review before using |
Higher scores indicate skills from reputable sources with community validation. Trust scores are visible in search results and install prompts so you can make an informed decision before installing.
Context7 automatically scans skills for potential security issues before they appear in the registry:
Each skill is a directory containing at minimum a SKILL.md file:
my-skill/
├── SKILL.md # Main instructions (required)
├── templates/ # Optional templates
├── examples/ # Optional example outputs
└── scripts/ # Optional executable scripts
Skills use YAML frontmatter followed by markdown instructions:
---
name: my-skill
description: What this skill does and when to use it
---
Instructions for the AI assistant go here.
Use markdown formatting, code examples, and clear steps.
| Field | Required | Description |
|---|---|---|
name | Yes | Identifier for the skill (lowercase, hyphens allowed) |
description | Yes | Explains what the skill does — used for discovery and auto-triggering |
The markdown body contains the actual instructions your AI assistant follows when the skill is invoked.
The CLI automatically detects installed AI coding assistants and offers to install skills for them.
| Client | Project Directory | Global Directory |
|---|---|---|
| Universal (Amp, Codex, Gemini CLI, GitHub Copilot, OpenCode + more) | .agents/skills/ | ~/.agents/skills/ |
| Claude Code | .claude/skills/ | ~/.claude/skills/ |
| Cursor | .cursor/skills/ | ~/.cursor/skills/ |
| Antigravity | .agent/skills/ | ~/.agent/skills/ |
Project vs Global:
--global): Installed in your home directory, available across all projectsUse the ctx7 CLI to install, search, generate, and remove skills. See the CLI reference for all commands.
# Quick start
npx ctx7 skills search pdf
npx ctx7 skills install /anthropics/skills pdf
If you see permission errors when installing or removing skills:
# Fix directory permissions
sudo chown -R $(whoami) ~/.claude/skills
If a skill is blocked, it contains content flagged as potentially malicious. This is a security feature — the skill cannot be installed.
Error: This skill contains potentially malicious content and cannot be installed.
Consider using an alternative skill or contacting the skill author.
If your AI coding assistant isn't detected, ensure its configuration directory exists:
# For Claude Code
mkdir -p .claude
# For Cursor
mkdir -p .cursor
If login fails or tokens expire:
ctx7 logout
ctx7 login