Skip to main content

By agent · Claude Code

Claude Code skills: 1068 worth installing

Skills in the open SKILL.md format that Claude Code reads. Each one has a plain-language summary and the command to install it.

Installing a skill in Claude Code

$ npx skills add <author>/<skill>

Replace the placeholder with the author and skill name from the skill's page. Start a new Claude Code session afterwards so the skill is picked up.

Skills for Claude Code

All skills

Terraform Style Guide

HashiCorpOfficial

Generates Terraform HCL that follows HashiCorp's official style conventions.

DevelopmentGitHub stars: 880Installs: 11.7k

Terraform Test

HashiCorpOfficial

Guides writing and running Terraform tests: test files, run blocks, assertions and mocked providers.

DevelopmentGitHub stars: 880Installs: 8.2k

MySQL

PlanetScaleOfficialAudit warning

Plans and reviews MySQL and InnoDB schemas, indexing, query tuning, transactions and operations.

DataGitHub stars: 693Installs: 8.1k

Neki

PlanetScaleOfficial

Explains Neki, PlanetScale's sharded Postgres product, for Postgres scaling and sharding work.

DataGitHub stars: 693Installs: 1.5k

Postgres

PlanetScaleOfficialAudit warning

Covers PostgreSQL best practices: query optimisation, connection troubleshooting and performance.

DataGitHub stars: 693Installs: 7.9k

Vitess

PlanetScaleOfficial

Covers Vitess best practices: query optimisation, sharding, VSchema configuration and keyspace management.

DataGitHub stars: 693Installs: 1.5k

Angular Developer

AngularOfficial

Generates Angular code and gives architectural guidance on components, services, signals, forms and HTTP communication.

DevelopmentGitHub stars: 662Installs: 40.1k

Angular New App

AngularOfficial

Creates a new Angular application with the Angular CLI, following the team's guidelines for a modern setup.

DevelopmentGitHub stars: 662Installs: 16.7k

Firecrawl Agent

FirecrawlOfficial

Navigates websites on its own with Firecrawl and extracts structured data across pages.

DataGitHub stars: 643Installs: 80.4k

Firecrawl Crawl

FirecrawlOfficial

Extracts many pages from one site or section in bulk with Firecrawl.

DataGitHub stars: 643Installs: 80.3k

Firecrawl Download

FirecrawlOfficial

Saves a site or section as local markdown files and screenshots with Firecrawl, for offline reference.

DataGitHub stars: 643Installs: 79.5k

Firecrawl Interact

FirecrawlOfficialAudit warning

Drives a live browser on a scraped page with Firecrawl: click, fill forms, log in and paginate.

AutomationGitHub stars: 643Installs: 64.8k

Firecrawl Map

FirecrawlOfficial

Discovers and lists a site's URLs with Firecrawl, with search filtering.

DataGitHub stars: 643Installs: 79.8k

Firecrawl Monitor

FirecrawlOfficial

Sends a webhook or email alert when watched URLs change or new results appear on the web, using Firecrawl.

AutomationGitHub stars: 643Installs: 32.9k

Firecrawl Parse

FirecrawlOfficial

Converts a local PDF, DOCX, XLSX or HTML file to markdown with Firecrawl, or answers questions about its content.

DocumentsGitHub stars: 643Installs: 50.7k

Firecrawl Scrape

FirecrawlOfficial

Reads a known webpage with Firecrawl and returns its content or structured results.

DataGitHub stars: 643Installs: 82.8k

Firecrawl Search

FirecrawlOfficial

Finds web sources with Firecrawl, returning page excerpts relevant to the query and optionally the full page content.

ResearchGitHub stars: 643Installs: 83.2k

Firecrawl

FirecrawlOfficialAudit warning

Handles any live-web task through the Firecrawl CLI: search, page extraction, site mapping, bulk crawls and change alerts.

ResearchGitHub stars: 643Installs: 102k

DuckDB Attach DB

DuckDBOfficial

Attaches a DuckDB database file, explores its schema and saves the session state for later queries.

DataGitHub stars: 596Installs: 920

DuckDB Convert File

DuckDBOfficial

Converts a data file between formats such as CSV, Parquet, JSON, Excel and GeoJSON with DuckDB.

DataGitHub stars: 596Installs: 677

DuckDB Docs

DuckDBOfficial

Searches the DuckDB and DuckLake documentation and blog posts through a locally cached full-text index.

DataGitHub stars: 596Installs: 1.2k

DuckDB Query

DuckDBOfficial

Runs SQL, or answers natural-language questions, against an attached DuckDB database or directly against files.

DataGitHub stars: 596Installs: 1.3k

DuckDB Read File

DuckDBOfficial

Reads and profiles a data file or remote URL in CSV, JSON, Parquet, Avro, Excel, spatial or SQLite format with DuckDB.

DataGitHub stars: 596Installs: 1.1k

DuckDB S3 Explore

DuckDBOfficial

Explores and queries data on S3, Cloudflare R2, GCS, MinIO and other S3-compatible storage with DuckDB.

DataGitHub stars: 596Installs: 610

Questions

Claude Code and skills.

What is a Claude Code skill?

A folder with a SKILL.md file: instructions, and sometimes scripts and reference files, that Claude Code loads when a task calls for them.

How do I install a skill in Claude Code?

Each skill page has an install command. Run it in a terminal, then start a new Claude Code session so the skill is picked up.

What is the difference between a skill and an instructions file such as AGENTS.md?

An instructions file is loaded in every session and describes the project. A skill is loaded only when a task calls for it, so it can be long and specific without costing context on every turn.

Other agents