Agent skills
Skills for Claude Code, Codex, Cursor and other agents from the skills.sh directory: installs, security audit status and the command to add a skill.
A skill is not tied to one agent: npx skills add installs it into any supported one. Without -a the CLI finds the agents on your computer and asks where to add it.
Updated · Sources: skills.sh
Shown: 14 · found: 14 · of 10,000 in the directory
-
marimo-pair marimo-team/marimo-pair
Drive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes. Use when the user wants to start a marimo notebook or pair on an active marimo session.
11,435 Failed -
temporal-python-testing wshobson/agents
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
10,420 Failed -
django-tdd affaan-m/ecc
Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs. Use when writing Django or DRF tests with pytest-django, or driving a Django feature test-first.
10,200 Failed -
notebooklm teng-lin/notebooklm-py
Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API. Do not use for the generic Gemini API or unrelated content creation.
9,499 Failed -
python-pro jeffallan/claude-skills
Use when building Python 3.11+ applications requiring type safety, async programming, or robust error handling. Generates type-annotated Python code, configures mypy in strict mode, writes pytest test suites with fixtures and mocking, and validates code with black and ruff. Invoke for type hints, async/await patterns, dataclasses, dependency injection, logging configuration, and structured error handling.
7,770 Failed -
fastapi-expert jeffallan/claude-skills
Use when building high-performance async Python APIs with FastAPI and Pydantic V2. Invoke to create REST endpoints, define Pydantic models, implement authentication flows, set up async SQLAlchemy database operations, add JWT authentication, build WebSocket endpoints, or generate OpenAPI documentation. Trigger terms: FastAPI, Pydantic, async Python, Python API, REST API Python, SQLAlchemy async, JWT authentication, OpenAPI, Swagger Python.
5,715 Failed -
django-expert vintasoftware/django-ai-plugins
Expert Django backend development guidance. Use when creating Django models, views, serializers, or APIs; debugging ORM queries or migrations; optimizing database performance; implementing authentication; writing tests; or working with Django REST Framework. Follows Django best practices and modern patterns.
5,534 Failed -
pandas-pro jeffallan/claude-skills
Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation tasks such as joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, or performance optimization of large datasets.
5,323 Failed -
devcontainer-setup trailofbits/skills
Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a project, setting up isolated development environments, or configuring sandboxed Claude Code workspaces.
4,807 Failed -
django-expert jeffallan/claude-skills
Use when building Django web applications or REST APIs with Django REST Framework. Invoke when working with settings.py, models.py, manage.py, or any Django project file. Creates Django models with proper indexes, optimizes ORM queries using select_related/prefetch_related, builds DRF serializers and viewsets, and configures JWT authentication. Trigger terms: Django, DRF, Django REST Framework, Django ORM, Django model, serializer, viewset, Python web.
3,915 Failed -
cuopt-developer nvidia/skills
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
2,621 Failed -
harvard-artifacts-etl-analytics reason-machines/data-skills
Build ETL pipelines and analytics dashboards for Harvard Art Museums API data with Python, SQL, and Streamlit
2,015 Failed -
setup marketcalls/vectorbt-backtesting-skills
Set up the Python backtesting environment. Detects OS, creates virtual environment, installs dependencies (openalgo, ta-lib, vectorbt, plotly), and creates the backtesting folder structure.
1,926 Failed -
e2e-testing hieutrtr/ai1-skills
End-to-end testing patterns with Playwright for full-stack Python/React applications. Use when writing E2E tests for complete user workflows (login, CRUD, navigation), critical path regression tests, or cross-browser validation. Covers test structure, page object model, selector strategy (data-testid > role > label), wait strategies, auth state reuse, test data management, and CI integration. Does NOT cover unit tests or component tests (use pytest-patterns or react-testing-patterns).
1,644 Failed
Descriptions are the authors' own, in English. Read a skill's code in its repository before you install it.
What agent skills are
A skill is a folder with a SKILL.md file — instructions written for an AI agent — and sometimes scripts or templates. When a task matches the skill's description, an agent such as Claude Code, Codex or Cursor loads it and follows it: how to fill in a form, how to review code in a particular style, how to work with a certain file format. This page is a directory of such skills, based on skills.sh.
What the directory shows
- the top 10,000 skills by number of installs, synced daily;
- for each skill: name, author and repository, installs, the status of its security audit and the command that adds it, with a copy button;
- "Trending": the skills that gained the most installs over the last 7 days;
- filters by topic and by agent, and a search; each view shows up to 100 skills.
Reading the audit status
skills.sh publishes security audits of skills. We show the result as Passed, Warnings, Failed or Not audited. A passed audit lowers the risk but is not a guarantee: a skill can contain scripts that your agent will run on your machine. Read the code in the repository before you install a skill, especially one with few installs or no audit.
Installing a skill
- Find a skill through the topics, the agent filter or the search.
- Open its repository and look at SKILL.md and any scripts.
- Copy the command from the row and run it in your project.
- Ask your agent to perform a task that matches the skill.
About the descriptions
The short descriptions are the authors' own, in English, as written in each SKILL.md. We do not translate or rewrite them, and install counts are those reported by skills.sh.