pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces.…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Data & analytics
17,421 results
ray-data
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch,…
sentencepiece
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory),…
tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML…
weights-and-biases
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B -…
topic
Web fiction/novel topic planning, suitable for when users say "I want to write a novel but don't know what to write," "help me think of a novel subject," "find web fiction ideas," "analyze what genres are hot," "novel topic evaluation," "what web fiction genres sell well now," "give me a few novel ideas," "think of a novel cheat," "help me find a popular genre," "what genres are easy to make popular in a novel," "web fiction market trend analysis," "help me do novel topic planning," and other needs, generate multiple sets of topic plans and market…
xlsx-financial-report
Generate a native Excel (.xlsx) file styled as a clean financial / KPI / dashboard report. Use when the user asks for an "Excel report", "financial report",…
data-analysis
Patterns for data loading, exploration, and statistical analysis
lc-site-data
Add a topic to the Study Roadmap (data/roadmap.json) or a question to the Complexity Quiz (data/complexity_quiz.json), satisfying the build-time validators in…
yb-metrics-analysis
Retrieve and analyse YugabyteDB universe metrics to identify and explain operational issues — a quick health-check gate, a guided workload sweep (read/write…
yb-performance-assessment
Start here for a broad, whole-universe YugabyteDB performance assessment — when the request is open-ended ("assess this universe for any performance issues",…
ocr-and-documents
Extract text from PDFs/scans (pymupdf, marker-pdf).
model-code-and-result-generator
Based on model_route.json, the data plan, and the cleaned data, generate a results evidence contract and q1/q2/q3 modeling code scaffolding for the mathematical modeling paper. Invoke when it is necessary to consolidate model outputs, evaluation metrics, structured conclusions, paper tables, and current competition-problem-specific modeling code into paper_output/results/, paper_output/tables/, and…
agent-paste-neon-postgres
Guides and best practices for working with Neon Serverless Postgres. Covers setup, connection methods, branching, autoscaling, scale-to-zero, read replicas,…
mcp-sheet-cache-bridge
Keep Zapier Tables or another MCP-connected record store as the source of truth while Google Sheets-based tools read an event-driven cache tab.
snowflake-development
Comprehensive Snowflake development assistant covering SQL best practices, data pipeline design (Dynamic Tables, Streams, Tasks, Snowpipe), Cortex AI…
backing-up-timestamps
Use when stream timestamping is complete in youtube_*_workspace, when archiving timestamps to timestamp_workspace, or when organizing and moving backed-up…
gm-data-chart
Generate data visualization charts from natural language descriptions. Creates single-file HTML with inline SVG that can be opened in any browser. Use this…
stock-analysis
A comprehensive A-share analysis tool supporting overall market reports and stock group analysis. It integrates the AKShare data source and provides functions such as market snapshots, sentiment analysis, hot sector tracking, technical signal generation, and fundamental scoring. It outputs reports in Markdown and CSV formats.
fund-diagnosis
Single-fund comprehensive diagnostic capability for public mutual funds. It applies when users ask generalized questions such as "How is this fund?", "Is it suitable to continue holding?", or "What are its risk and return characteristics?", and returns a structured Markdown diagnostic report. It analyzes only one fund at a time and does not handle multi-fund comparisons or quantitative modeling. Core trigger conditions: the user's phrasing is a general diagnostic question and does not request specific indicator formula calculations or backtest modeling.
mx-finance-data
Based on the East Money database, it supports natural language queries for financial data, covering various assets such as A-shares, Hong Kong stocks, US stocks, funds, and bonds, including real-time quotes, company information, valuations, financial statements, etc. It can be used for investment research, trade review, market monitoring, industry analysis, credit research, financial statement auditing, asset allocation, and other scenarios, adapting to the diverse needs of institutions and individuals. The returned results include data descriptions and xlsx files. Natural language query for…
mx-macro-data
Based on the East Money database, it supports natural language queries for global macroeconomic data, covering multiple fields such as national economic accounting, price indices, monetary and financial, fiscal revenue and expenditure, foreign trade, employment and livelihood, and industrial operations, adapting to diverse professional scenario needs such as various macroeconomic research, market analysis, and policy interpretation. The returned results include data descriptions and a CSV file. Natural language query for…
mx-stocks-screener
Based on the East Money database, it supports filtering A-shares, Hong Kong stocks, US stocks, funds, bonds, and other assets through natural language input, and supports multi-indicator screening, including technical, news, fundamental, and market sentiment factors. It can be used for global asset quick screening, cross-market monitoring, portfolio construction, strategy backtesting, and other scenarios. The returned results include data descriptions and a CSV file. Natural language screener for investment…
stock-earnings-review
Relying on the East Money database, targeting listed companies/stocks across the five major markets of Shanghai, Shenzhen, Beijing, Hong Kong, and the US, generate earnings review-type output (including financial report analysis and earnings interpretation). When a user explicitly requests an earnings review, financial report analysis, or earnings interpretation, or when expressions such as "earnings review", "financial report review", "earnings analysis", "quarterly report/semi-annual report/annual report review", "financial analysis", "profitability analysis", or "earnings interpretation" appear, this Skill should be triggered.…