Skills para agentes
Skills para Claude Code, Codex, Cursor y otros agentes del directorio skills.sh: instalaciones, estado de la auditoría de seguridad y el comando para añadir cada skill.
Un skill no está atado a un solo agente: npx skills add lo instala en cualquiera compatible. Sin -a, la CLI detecta los agentes de tu equipo y pregunta dónde añadirlo.
Actualizado · Fuentes: skills.sh
Mostradas: 26 · encontrados: 26 · de 10.000 en el directorio
-
gmgn-market gmgnai/gmgn-skills
Get crypto and meme token price charts (K-line, candlestick, OHLCV), trending meme coin rankings by volume, newly launched tokens on launchpads (pump.fun, fourmeme, letsbonk, Raydium, etc.), the hot-search ranking (most-searched tokens), and search for a specific token or wallet by name, symbol, contract address, wallet address, or ENS via GMGN API on Solana, BSC, Base, or Ethereum. Use when user asks for price chart, trending tokens, what's pumping, hot coins, most searched tokens, new launches, token signals, wants to look up / find / search a specific token or wallet by name or address, or wants to discover early-stage opportunities.
16.205 No superada -
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.
5.360 No superada -
elasticsearch-esql elastic/agent-skills
Execute ES|QL (Elasticsearch Query Language) queries, use when the user wants to query Elasticsearch data, analyze logs, aggregate metrics, explore data, or create charts and dashboards from ES|QL results.
4.407 No superada -
ml-pipeline jeffallan/claude-skills
Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow or Airflow DAGs for training orchestration, builds feature store schemas with Feast, deploys model registries, and automates retraining and validation workflows. Use when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, managing experiment tracking systems, setting up DVC for data versioning, tuning hyperparameters, or configuring MLOps tooling like Kubeflow, Airflow, MLflow, or Prefect.
3.608 No superada -
security-ownership-map openai/skills
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions.
3.583 No superada -
spark-engineer jeffallan/claude-skills
Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operations, configure executor memory, process .parquet files, handle data partitioning, or build structured streaming analytics.
3.574 No superada -
ai-ml-security yaklang/hack-skills
AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.
3.283 No superada -
breadth-chart-analyst tradermonty/claude-trading-skills
This skill should be used when analyzing market breadth charts, specifically the S&P 500 Breadth Index (200-Day MA based) and the US Stock Market Uptrend Stock Ratio charts. Use this skill when the user provides breadth chart images for analysis, requests market breadth assessment, positioning strategy recommendations, or wants to understand medium-term strategic and short-term tactical market outlook based on breadth indicators. Also works WITHOUT chart images by fetching CSV data directly from public sources. All analysis and output are conducted in English.
3.150 No superada -
apify-content-analytics apify/agent-skills
2.544 No superada -
llm-public-opinion-analytics-assistant reason-machines/data-skills
Multi-platform hot search crawler and LLM-powered public opinion analysis system with clustering, sentiment analysis, and multi-channel push notifications
2.380 No superada -
roblox-mm2-analytics-toolkit reason-machines/data-skills
Analytics and inventory management toolkit for Roblox Murder Mystery 2 gameplay optimization
2.376 No superada -
mm2-analytics-roblox-tracker reason-machines/data-skills
Analyze Murder Mystery 2 gameplay data, track inventory, and optimize strategy using this Roblox analytics toolkit
2.355 No superada -
mm2-roblox-analytics-toolkit reason-machines/data-skills
Murder Mystery 2 gameplay analytics, inventory tracking, and strategy optimization toolkit for Roblox
2.354 No superada -
mm2-analytics-dashboard-roblox reason-machines/data-skills
Murder Mystery 2 inventory tracking, analytics dashboard, and gameplay optimization toolkit for Roblox
2.344 No superada -
murder-mystery-2-analytics-toolkit reason-machines/data-skills
Analytics dashboard and inventory management toolkit for Roblox Murder Mystery 2 game data tracking and optimization
2.338 No superada -
mm2-analytics-roblox-toolkit reason-machines/data-skills
Roblox Murder Mystery 2 analytics dashboard and inventory tracking toolkit with data visualization and strategy analysis
2.337 No superada -
mm2-roblox-analytics-tracker reason-machines/data-skills
Analytics and inventory tracking toolkit for Roblox Murder Mystery 2 with strategic gameplay insights
2.320 No superada -
llm-public-opinion-analytics reason-machines/data-skills
Multi-platform public opinion analysis assistant with web scraping, LLM-powered analytics, topic clustering, sentiment analysis, and multi-channel alerts
2.255 No superada -
ml-paper-writing orchestra-research/ai-research-skills
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.
2.186 No superada -
data-engineering-medallion-pipeline reason-machines/data-skills
End-to-end data engineering pipeline using MinIO, Airbyte, PostgreSQL, DBT, and Airflow with medallion architecture (Bronze/Silver/Gold layers)
2.043 No superada -
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 No superada -
retail-etl-pipeline-medallion reason-machines/data-skills
End-to-end retail ETL pipeline using PySpark, SQL Server, and Medallion Architecture (Bronze/Silver/Gold layers) for data warehousing
1.788 No superada -
snowflake-dbt-airbnb-analytics reason-machines/data-skills
Inside Airbnb data warehouse built with Snowflake and dbt, demonstrating modern analytics engineering patterns with staging, intermediate, and mart layers.
1.702 No superada -
qqmusic tencentmusic/qqmusic-skills
QQ Music — search songs, albums, playlists, music videos, artists; daily recommendations; music charts & rankings; AI-powered playlists; personalized listening reports & music insights. QQ音乐助手：搜索、每日推荐、排行榜、AI歌单、听歌报告、AI解读。
1.682 No superada -
okx starchild-ai-agent/official-skills
OKX OnChainOS: on-chain trading, analytics, security, DeFi across 20+ chains. Use when running OKX-routed on-chain ops (e.g. swap on Ethereum, scan token risk, track smart money, check wallet portfolio). Wallet: default to the user's Agent Wallet (via the `wallet` skill). Only use the OnchainOS TEE wallet (`onchainos wallet login <email>`) when the user explicitly asks for it.
1.652 No superada -
lieflat-charts larashero3-dotcom/lieflat-charts
一套模板驱动的数据可视化与报告生成 skill，既能严格从 Lupi、Basics、Glance、Maps 与 Interactive gallery 的真实实现生成 HTML 图表，也能从 12 套中英文整页报告模板生成可发布的 HTML 报告；以 Mono 为保底，能按数据语义自动选择内置彩色预设，也支持用户明确提供的自定义色板。地图仅在用户明确要求时启用，同一交付禁止混用色系。
1.586 No superada
Las descripciones son de sus autores, en inglés. Revisa el código de una skill en su repositorio antes de instalarla.
Una skill es una carpeta con un archivo SKILL.md y, si hace falta, algunos scripts. El agente la carga cuando la tarea que le pides encaja con lo que describe la skill: por ejemplo, cómo trabajar con un framework concreto, cómo redactar documentación o cómo preparar un despliegue. Así amplías lo que sabe hacer tu agente sin tener que explicárselo en cada conversación.
De dónde sale el directorio
Las skills proceden de skills.sh, un directorio para Claude Code, Codex, Cursor y otros agentes. Sincronizamos cada día las 10 000 skills con más instalaciones. Cada ficha muestra el nombre, el autor y el repositorio, el número de instalaciones, el estado de la auditoría de seguridad y el comando para añadir la skill, con el botón «Copiar el comando».
Las descripciones son de sus autores, en inglés, y no las traducimos. El código de cada skill está en GitHub, enlazado desde la ficha.
Cómo buscar
- Más instaladas y «En tendencia»: la segunda pestaña ordena por las instalaciones ganadas en los últimos 7 días.
- Temas: frontend, backend, DevOps, bases de datos, seguridad, documentación y otros.
- Agentes: para ver solo las skills compatibles con el tuyo.
- Buscador por nombre o descripción.
Cada vista muestra como máximo 100 skills; afina con los filtros si buscas algo concreto.
La auditoría de seguridad
Los estados vienen de las auditorías que publica skills.sh: «Superada», «Advertencias», «No superada» y «Sin auditar». Una auditoría superada no es una garantía. Una skill puede incluir scripts que el agente ejecutará en tu equipo, así que lee el código en el repositorio antes de instalarla, sobre todo si pide acceso a la red o a tus archivos. Las instalaciones también las cuenta skills.sh: indican popularidad, no calidad ni seguridad.
Cómo encaja con el resto
Las skills funcionan dentro de un agente, así que primero necesitas uno: los tienes en agentes de programación. El agente, a su vez, rinde según el modelo que usa, y eso lo muestran las clasificaciones de programación y de agentes. Una buena skill no convierte un modelo flojo en uno fuerte, pero ahorra instrucciones repetidas y hace que el agente siga las convenciones de tu proyecto.