Skills para agentes
Skills para Claude Code, Codex, Cursor e outros agentes do diretório skills.sh: instalações, status da auditoria de segurança e o comando para adicionar cada skill.
Uma skill não fica presa a um agente: npx skills add a instala em qualquer agente compatível. Sem -a, a CLI encontra os agentes do seu computador e pergunta onde adicioná-la.
Atualizado · Fontes: skills.sh
Exibidas: 15 · encontradas: 15 · de 10.000 no diretório
-
uv-package-manager wshobson/agents
Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.
16.092 Reprovada -
Creates and edits parametric CAD parts and assemblies as Python build123d models that cadgen's engine builds and the CAD Viewer shows live; exports STEP, STL, 3MF, GLB and xbf files on request; resolves prompt references, measures geometry, and articulates or animates assemblies. Use for 3D CAD modeling, editing a model script (any change to a part's or assembly's `.py`), organizing a CAD project, exporting or converting CAD files, Quick Edit prompts, mechanisms, and explode or showcase animations. Opens and reviews existing XBF, STEP/STP, STL, 3MF and GLB files in the CAD Viewer.
15.744 Reprovada -
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.
14.318 Reprovada -
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.
11.556 Reprovada -
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.
10.262 Reprovada -
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.
9.356 Reprovada -
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.
6.625 Reprovada -
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.
6.320 Reprovada -
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.
5.992 Reprovada -
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.
5.956 Reprovada -
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.
4.645 Reprovada -
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.
2.757 Reprovada -
modal k-dense-ai/scientific-agent-skills
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.
2.161 Reprovada -
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.
2.134 Reprovada -
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 Reprovada
As descrições são dos próprios autores, em inglês. Leia o código de uma skill no repositório dela antes de instalá-la.
O que é uma skill
Uma skill é uma pasta com um arquivo SKILL.md e, opcionalmente, scripts, que um agente de IA carrega quando a tarefa combina com ela. Funciona como um manual especializado: em vez de explicar tudo de novo a cada conversa, o agente lê as instruções da skill na hora certa. Este diretório reúne skills do skills.sh para Claude Code, Codex, Cursor e outros agentes.
O que a página mostra
- nome, autor e repositório de cada skill;
- número de instalações e status da auditoria de segurança;
- o comando para adicionar a skill, com o botão “Copiar o comando”.
O diretório traz as 10 000 skills mais instaladas, sincronizadas diariamente. A aba “Em alta” ordena pelas instalações ganhas nos últimos 7 dias. Há filtros por tema e por agente, além da busca; cada visualização mostra no máximo 100 skills.
Como ler a auditoria
Os status vêm das auditorias publicadas pelo skills.sh: “Aprovada”, “Alertas”, “Reprovada” e “Não auditada”. Uma auditoria aprovada não é garantia. Skills podem incluir scripts que rodam na sua máquina, então leia o código no repositório antes de instalar, principalmente se ela pede acesso a arquivos, rede ou credenciais.
Passo a passo para instalar com cuidado
- Filtre pelo agente que você usa e pelo tema da tarefa.
- Abra o repositório e leia o SKILL.md e os scripts.
- Prefira skills com status “Aprovada” e autor identificável.
- Copie o comando e instale num projeto de teste antes de usar no trabalho.
Observações
As descrições são dos próprios autores, em inglês, e não são traduzidas. As instalações são contadas pelo skills.sh. Para escolher o agente que vai usar as skills, veja os agentes de programação.