- Home
- /
- Categories
- /
- Embeddings
Embeddings
Vector embeddings and similarity
manage-rag-default
by DocAILab
Analyze a RAG task and produce guidance for choosing exactly one available Agentic RAG Skill using evidence dependencies, retrieval routes, corpus characteristics, and execution budget. Use as the first and only Skill loaded during the Manage selection stage.
react-tailwind
by babandeepsingh
Opinionated assistant for installing and configuring Tailwind CSS in React projects, then revamping components using Tailwind utility classes and semantic design tokens. Use when working on React (CRA, Vite, Next.js, Remix, plain SPA) and you need guidance on Tailwind setup, dependency selection and installation order, configuration, semantic theme design, and common UI recipes (forms, data tables, navigation, modals, layout).
amazon
by CodeDraig
Enables Claude to browse Amazon products, manage wishlists, and track orders (no purchases)
OSS Promoter Skill
by ourines
Set enabled: false for weeklies that are language/topic specific and don't match the project
xcli
by vforsh
Use the xcli CLI to list likes, list bookmarks, search posts, and check usage on X.
document-qa
by IchenDEV
文档问答流程,基于知识库文档回答问题,提供引用和置信度
mrs-server-dev
by mpesce
Work on the Mixed Reality Service server codebase. Use for FastAPI endpoint changes, server-side validation/auth updates, search/register/release contract changes, database-layer behavior, and server test/release hardening.
memories
by proompteng
Save and retrieve memories or embeddings via the repo helpers or API. Use when working with embedding config or memory storage.
uniapp-ui
by zwmmm
"UniApp + UnoCSS + WotUI page generator from designs. Converts screenshots or HTML/CSS to UniApp pages. Features: intelligent component mapping with priority (custom components, then WotUI, then built-in), 6 page templates (form, list, detail, tab, search, grid), auto-analyze custom components, cross-platform compatibility checks. Use for: creating UniApp pages, converting designs to code, mobile app/mini-program/H5 development. Actions: generate, create, build, convert, analyze, design. Tech: Vue3, UnoCSS, Wot Design Uni, UniApp."
client-meeting-prep-agent
by neurongraph
An agent that helps relationship managers prepare for upcoming client meetings by synthesizing a tailored Point of View and detailed Speaker Notes from multiple information sources.
butler-db-schema
by Tzeusy
Guide for designing and managing a butler's PostgreSQL database schema. Use when creating tables, writing migrations, adding indexes, or evolving a butler's data model.
explain
by TakaGoto
"Get a deep-dive explanation of any RAG concept"
spelunk — AI Agent Skill Reference
by usercise
automatically skipped during indexing and will not appear in results.
install-skill
by paulo20223
Search and install skills from skills.sh and GitHub repos. Use when users ask to find skills, install skills, download skills, add skills from GitHub, search for skills, browse skills, get a skill, or want new capabilities. Trigger phrases include "install skill", "find skill", "search skills", "add skill", "download skill", "get skill from github", "skills.sh", "browse skills", "what skills are available", "I need a skill for".
salam
by SalamLang
Use when writing, reading, debugging or reviewing Salam source (.salam files) - the Salam programming language with English/Persian/Arabic keywords. Covers its enforced declaration ordering, the until = while rule, stdlib lookup, and the toolchain traps that silently produce wrong behaviour. Triggers on .salam files, "Salam", "salamlang", or any request to compile, check or run Salam code.
firecrawl
by fvanevski
"Acquire, retain, retrieve, and audit web research with Firecrawl. Use when Codex needs to search or scrape the web, query or inspect the authoritative PostgreSQL research corpus, run hybrid lexical/vector retrieval, fetch bounded citation passages, diagnose ingestion or indexing, or manage research provenance and recovery."
faiss
by majiayu000
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
minimax-coding-plan
by mengbo
MiniMax Coding Plan MCP - Web search and image understanding tools for developers
verified-search
by ljchg12-hue
Expert verified search with source validation, credibility scoring, and fact-checking
Knowledge Base Search
by srsubramanian
Search and retrieve information from the vector knowledge base (RAG)
actions-optimiser
by kaihendry
This skill should be used when the user asks to "optimise GitHub Actions", "improve my workflow", "make actions better", "review workflow usage", "how are others using this action", "find best practices for GitHub Actions", or wants to gather real-world context on how GitHub Actions are used to improve their workflows.
semantic-explore
by adilasif
This skill should be used when the user asks to understand code behavior, explore how something works, find where functionality is implemented, or asks questions like "how does X work", "where is Y handled", "what does Z do", "show me the code that", "find the implementation of", or "trace the flow of". Also use for exploring unfamiliar codebases or when grep/glob returns too many irrelevant results. Use BEFORE or ALONGSIDE keyword search.
vibe_learn
by knvpk
Personal knowledge tutor and wiki maintainer. Invoke for ANY of these: "next topic", "teach me", "explain X", "what is X", "bring me next topic", "continue learning", "let's learn", "start topic", "I want to learn", "what's next", "how am I doing", "progress report", "stats", "show my progress", any question about a concept in the curriculum, any URL or article to ingest, or "lint" / "health check" the wiki.
Hyperparameter Search
by sovr610
This skill should be used when the user asks to "tune hyperparameters", "find optimal learning rate", "run grid search", "run random search", "Bayesian optimization", "learning rate finder", "hyperparameter sweep", "tune model", "search space", "parameter optimization", "Optuna", "Ray Tune", "hyperband", "population based training", or needs guidance on hyperparameter search strategies, search space definition, trial management, or automated tuning for the brain_ai system.