Skill-uri pentru agenți
Skill-uri pentru Claude Code, Codex, Cursor și alți agenți din directorul skills.sh: instalări, starea auditului de securitate și comanda de adăugare a unui skill.
Un skill nu este legat de un singur agent: npx skills add îl instalează în orice agent compatibil. Fără -a, CLI-ul găsește agenții de pe computer și întreabă unde să-l adauge.
Actualizat · Surse: skills.sh
Afișate: 26 · găsite: 26 · din 10.000 în director
-
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 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat -
apify-content-analytics apify/agent-skills
2.544 Picat -
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 Picat -
roblox-mm2-analytics-toolkit reason-machines/data-skills
Analytics and inventory management toolkit for Roblox Murder Mystery 2 gameplay optimization
2.376 Picat -
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 Picat -
mm2-roblox-analytics-toolkit reason-machines/data-skills
Murder Mystery 2 gameplay analytics, inventory tracking, and strategy optimization toolkit for Roblox
2.354 Picat -
mm2-analytics-dashboard-roblox reason-machines/data-skills
Murder Mystery 2 inventory tracking, analytics dashboard, and gameplay optimization toolkit for Roblox
2.344 Picat -
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 Picat -
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 Picat -
mm2-roblox-analytics-tracker reason-machines/data-skills
Analytics and inventory tracking toolkit for Roblox Murder Mystery 2 with strategic gameplay insights
2.320 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat -
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 Picat
Descrierile sunt ale autorilor, în engleză. Citiți codul unui skill în repository-ul său înainte de a-l instala.
Ce este un skill
Un skill este un dosar cu un fișier SKILL.md și, opțional, scripturi, pe care un agent îl încarcă atunci când sarcina se potrivește. În SKILL.md autorul descrie ce face skill-ul și cum trebuie folosit; agentul citește descrierea și aplică instrucțiunile doar când are nevoie de ele. Directorul de pe această pagină vine de la skills.sh și conține skill-uri pentru Claude Code, Codex, Cursor și alți agenți.
Ce vedeți în tabel
- numele skill-ului, autorul și repository-ul;
- „Instalări”, numărate de skills.sh;
- starea auditului de securitate: „Trecut”, „Avertismente”, „Picat” sau „Neauditat”, din auditurile publicate de skills.sh;
- comanda de adăugare a skill-ului, cu butonul „Copiați comanda”.
Directorul conține primele 10.000 de skill-uri după numărul de instalări, sincronizate zilnic. Secțiunea „În tendințe” ordonează skill-urile după instalările noi din ultimele 7 zile.
Cum căutați
- Folosiți filtrul „Subiecte” pentru domenii precum „Frontend și UI”, „DevOps” sau „Testare”.
- Alegeți agentul pe care îl folosiți, ca să vedeți doar skill-urile compatibile.
- Căutați după nume sau cuvânt cheie; pe o pagină apar cel mult 100 de skill-uri.
Descrierile sunt ale autorilor, în engleză, și nu sunt traduse.
Pentru ce sunt utile skill-urile
Skill-urile îi dau agentului cunoștințe pe care modelul nu le are din start: regulile unei echipe, pașii pentru un anumit framework, un format de documentație sau un proces de publicare. În loc să repetați aceleași instrucțiuni în fiecare conversație, le instalați o dată, iar agentul le folosește doar atunci când sarcina o cere.
Înainte de instalare
Un audit trecut nu este o garanție. Un skill poate conține scripturi pe care agentul le rulează pe calculatorul dumneavoastră, așa că citiți codul din repository înainte de a-l instala. Preferați skill-urile cu autor cunoscut și cod clar, instalați doar ce folosiți și verificați ce modifică agentul după ce încarcă un skill nou. Agenții care pot folosi skill-uri sunt pe pagina Agenți de programare.