Skills voor agents
Skills voor Claude Code, Codex, Cursor en andere agents uit de skills.sh-directory: installaties, status van de beveiligingscontrole en het commando om een skill toe te voegen.
Een skill zit niet vast aan één agent: npx skills add installeert hem in elke ondersteunde agent. Zonder -a zoekt de CLI de agents op je computer en vraagt waar hij moet komen.
Bijgewerkt · Bronnen: skills.sh
Getoond: 26 · gevonden: 26 · van 10.000 in de directory
-
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.
16.126 Mislukt -
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.
5.343 Mislukt -
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.
4.379 Mislukt -
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.
3.596 Mislukt -
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.
3.566 Mislukt -
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.
3.560 Mislukt -
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.
3.268 Mislukt -
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.
3.135 Mislukt -
apify-content-analytics apify/agent-skills
2.544 Mislukt -
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 Mislukt -
roblox-mm2-analytics-toolkit reason-machines/data-skills
Analytics and inventory management toolkit for Roblox Murder Mystery 2 gameplay optimization
2.376 Mislukt -
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 Mislukt -
mm2-roblox-analytics-toolkit reason-machines/data-skills
Murder Mystery 2 gameplay analytics, inventory tracking, and strategy optimization toolkit for Roblox
2.354 Mislukt -
mm2-analytics-dashboard-roblox reason-machines/data-skills
Murder Mystery 2 inventory tracking, analytics dashboard, and gameplay optimization toolkit for Roblox
2.344 Mislukt -
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 Mislukt -
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 Mislukt -
mm2-roblox-analytics-tracker reason-machines/data-skills
Analytics and inventory tracking toolkit for Roblox Murder Mystery 2 with strategic gameplay insights
2.320 Mislukt -
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 Mislukt -
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.
2.181 Mislukt -
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 Mislukt -
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 Mislukt -
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 Mislukt -
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 Mislukt -
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。
1.679 Mislukt -
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 Mislukt -
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。
1.576 Mislukt
De beschrijvingen zijn van de auteurs zelf, in het Engels. Lees de code van een skill in zijn repository voordat je hem installeert.
Wat is een skill?
Een skill is een map met een bestand SKILL.md en eventueel scripts. Het bestand beschrijft een taak of werkwijze, bijvoorbeeld hoe je een changelog schrijft, een database migreert of een bepaald framework gebruikt. Een agent laadt de skill pas als de taak erbij past, zodat hij gericht meer kennis en gereedschap krijgt zonder dat alles standaard in zijn context zit. Skills werken met Claude Code, Codex, Cursor en andere agents.
Wat laat de directory zien?
Deze pagina toont skills uit de directory van skills.sh: de top 10.000 op aantal installaties, dagelijks gesynchroniseerd. Per skill zie je:
- de naam, de auteur en de repository;
- het aantal installaties;
- de status van de “Beveiligingscontrole”;
- het commando om de skill toe te voegen, met een knop “Commando kopiëren”.
“Trending” sorteert skills op het aantal installaties dat er de afgelopen 7 dagen bij kwam. Je filtert op onderwerp en op agent, of je zoekt op naam; per weergave zie je maximaal 100 skills. De beschrijvingen zijn van de auteurs zelf, in het Engels, en worden niet vertaald.
Hoe lees je de beveiligingscontrole?
skills.sh publiceert controles van skills, en wij tonen de uitkomst: “Geslaagd”, “Waarschuwingen”, “Mislukt” of “Niet gecontroleerd”. Een geslaagde controle is geen garantie. Een skill kan scripts bevatten die je agent uitvoert op je eigen machine, met toegang tot je bestanden. Lees daarom de code in de repository voordat je een skill installeert, zeker bij “Waarschuwingen” of “Niet gecontroleerd”. Ook het aantal installaties zegt iets, maar niet alles: die telt skills.sh, en populair is niet hetzelfde als veilig.
Waar begin je?
Kies eerst je agent in het filter, zodat je alleen skills ziet die erbij passen. Zoek dan op het onderwerp waar je agent nu tekortschiet, lees de SKILL.md in de repository en kopieer pas daarna het commando. Welke agents er zijn, lees je bij codeeragents.