Skills til agenter
Skills til Claude Code, Codex, Cursor og andre agenter fra kataloget skills.sh: installationer, status for sikkerhedstjek og kommandoen til at tilføje en skill.
En skill er ikke bundet til én agent: npx skills add installerer den i enhver understøttet agent. Uden -a finder CLI’en agenterne på din computer og spørger, hvor den skal tilføjes.
Opdateret · Kilder: skills.sh
Vist: 26 · fundet: 26 · af 10.000 i kataloget
-
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
apify-content-analytics apify/agent-skills
2.544 Ikke bestået -
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 Ikke bestået -
roblox-mm2-analytics-toolkit reason-machines/data-skills
Analytics and inventory management toolkit for Roblox Murder Mystery 2 gameplay optimization
2.376 Ikke bestået -
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 Ikke bestået -
mm2-roblox-analytics-toolkit reason-machines/data-skills
Murder Mystery 2 gameplay analytics, inventory tracking, and strategy optimization toolkit for Roblox
2.354 Ikke bestået -
mm2-analytics-dashboard-roblox reason-machines/data-skills
Murder Mystery 2 inventory tracking, analytics dashboard, and gameplay optimization toolkit for Roblox
2.344 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
mm2-roblox-analytics-tracker reason-machines/data-skills
Analytics and inventory tracking toolkit for Roblox Murder Mystery 2 with strategic gameplay insights
2.320 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået -
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 Ikke bestået
Beskrivelserne er forfatternes egne, på engelsk. Læs koden til en skill i dens repository, før du installerer den.
Hvad er en skill?
En skill er en mappe med en SKILL.md-fil og eventuelt scripts, som en agent indlæser, når opgaven passer. Den kan lære agenten at arbejde med et bestemt filformat, følge en bestemt arbejdsgang eller bruge et værktøj. Kataloget viser skills fra skills.sh til Claude Code, Codex, Cursor og andre agenter med navn, forfatter og repository, antal installationer, status for sikkerhedstjek og kommandoen til at tilføje skillen.
Sådan er kataloget bygget
- De 10 000 mest installerede skills, synkroniseret dagligt fra skills.sh.
- »Populære nu« er installationer i de seneste 7 dage.
- Filtre efter emne og agent samt søgning; højst 100 skills pr. visning.
- Knappen »Kopiér kommandoen« kopierer installationskommandoen.
Beskrivelserne er forfatternes egne, på engelsk, og bliver ikke oversat. Installationer tælles af skills.sh.
Status for sikkerhedstjek
Hver skill har en af fire statusser fra de tjek, skills.sh offentliggør: »Bestået«, »Advarsler«, »Ikke bestået« eller »Ikke tjekket«. Et bestået tjek er ikke en garanti. En skill kan køre scripts på din maskine med agentens rettigheder, så læs koden i repositoryet, før du installerer den.
Sådan finder du en god skill
- Filtrér efter din agent og det emne, du arbejder med.
- Se på installationer og »Populære nu« som et første fingerpeg, ikke som et kvalitetsstempel.
- Åbn repositoryet på GitHub, og læs SKILL.md og eventuelle scripts.
- Installer, prøv på et testprojekt, og fjern skills, du ikke bruger.
Eksempler på skills
Der findes skills til at skrive tests, gennemgå pull requests, arbejde med regneark og PDF-filer, bygge brugerflader efter et designsystem eller følge en virksomheds kodestil. Nogle er små og indeholder kun instruktioner, andre har scripts, der kører kommandoer. Jo mere en skill gør, jo vigtigere er det at læse koden først.
Hvor passer skills ind?
Skills gør en agent bedre til bestemte opgaver, men erstatter ikke en god model. Vælg først agent på siden om kodeagenter, og byg derefter videre med skills.