Loading...
Loading...
Found 1,849 Skills
Run the Upstash CLI (`upstash`) against the Upstash Developer API for Redis, Vector, Search, QStash, and teams. Use when listing or managing databases, backups, vector/search indexes, QStash instances, team members, stats, or any non-interactive Upstash automation with JSON output and terminal commands.
Persistent memory layer for AI agents using Postgres/pgvector with MCP server support
Professional workflow for creating bespoke vector and complex raster icons. Supports Design (visual), Path (vector-driven), Desire (conceptual), and 3D/complex chroma-key modes. Features AI prompt engineering, automated binarization, improved alpha cleanup, and SVG optimization.
Professional workflow for creating bespoke vector and complex raster icons. Professional icon design workflow including Design (visual), Path (vector), Desire (conceptual), and 3D chroma-key modes. Features AI prompt engineering, automated binarization, alpha cleanup, and SVG optimization.
Bind the current directory to a MOM project so captured memories are scoped to it. Use when the user wants to set up project scoping, bind a repo, declare a project id, rebind a directory, or asks about .mom-project.yaml.
Semantic skill discovery and routing using GraphRAG, vector embeddings, and multi-tool search. Automatically matches user intent to the most relevant skills from 144+ available options using ck semantic search, LEANN RAG, and knowledge graph relationships. Triggers on /meta queries, complex multi-domain tasks, explicit skill requests, or when task complexity exceeds threshold (files>20, domains>2, complexity>=0.7).
Use OpenSearch vector search edition via the Python SDK (ha3engine) to push documents and run HA/SQL searches. Ideal for RAG and vector retrieval pipelines in Claude Code/Codex.
Generate text embeddings and rerank documents via Together AI. Embedding models include BGE, GTE, E5, UAE families. Reranking via MixedBread reranker. Use when users need text embeddings, vector search, semantic similarity, document reranking, RAG pipeline components, or retrieval-augmented generation.
Guide for using the `paper` CLI tool — a local academic paper management system with AI-powered vector search. Use this skill whenever the user wants to manage academic papers, create knowledge bases, add PDFs to a knowledge base, search papers semantically, configure embedding models, or manage literature metadata and notes. Also trigger when the user mentions "paper" CLI, knowledge bases for research, literature management, or wants to query their paper collection. Even if the user just says something like "add this PDF" or "search my papers" in a project that uses paper-manager, this skill should activate.
Scrapling CLI wrapper for web scraping with browser impersonation, stealth headers, CSS selectors, Cloudflare bypass, and JS rendering. Three fetcher tiers: HTTP (fast), Dynamic (Playwright), Stealthy (Camoufox). Output as HTML, Markdown, or text. Use when: scraping web pages, extracting content with CSS selectors, bypassing anti-bot protection, fetching JS-rendered pages. Triggers: scrape, scrapling, web scraping, extract page, fetch page content, bypass cloudflare.
Adds a data source or connector to a Power Apps code app. Asks what the user wants to accomplish and routes to the appropriate specialized skill.
Guides creation and modification of domain feature systems organized under a systems/ directory. Covers directory layout, API service layer patterns, TanStack Query hooks (queries, mutations, optimistic updates), React context and XState store conventions, hook organization, and public API barrel exports. Use when adding a new domain system, extending an existing one, or fixing bugs in a system-layer codebase. Don't use for generic React component work, backend API implementation, or codebases not organized around a systems/ domain pattern.