SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
17,421 results
MiniQMT / XtQuant Python quantitative development assistance skill. Use when the user asks about MiniQMT, QMT, XtQuant, xtdata, xttrader, market data interfaces, trading interfaces, account/order/position queries, margin trading, or the local MiniQMT official documentation.
MATLAB R2026a data analysis workflow for tables, timetables, statistics, fitting, optimization-assisted analysis, visualization, report artifacts, and…
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating…
Use when extracting a page needs scripted interaction first — click, type, press a key, scroll, wait, screenshot, or run JS before capturing the DOM. Covers…
Use crawlberg cli reference documentation.
Use crawlberg mcp reference documentation.
Use when the user wants a single page rendered as clean Markdown plus structured metadata. Covers `crawlberg scrape URL`, JSON vs Markdown output, what…
Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command,…
Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers,…
Use when generating embeddings, calling the 12 web-search providers, or running OCR over documents with the 4 OCR providers through liter-llm. Covers embed,…
Use when extracting metadata from HTML — title, description, language, Open Graph, JSON-LD / Microdata / RDFa, headers, links, and images. Covers the --json…
Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown /…
Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and…
Use when choosing an output format for extracted documents — text, markdown, djot, html, or JSON. Maps consumer (LLM, parser, archive) to the right `--format`…
Turn a short-video comment section into an interactive knowledge graph and publish it in a form that both humans and agents can read. Use when the user says "analyze my comment section," "comment section graph," "what are people concerned about," "what is everyone talking about in the comments," "comment atlas," "turn the comments into a graph," or "publish the graph," or when they have a batch of comment data and want to see its structure. Produces a zero-dependency single file…
Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon…
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function…
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media…
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types…
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms.…
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream…
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices,…
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers…
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics),…