Embeddings
Vector embeddings and similarity
using-kuzenbo-in-apps
by DobroslavRadosavljevic
Use this skill whenever the AI is implementing, configuring, documenting, or troubleshooting Kuzenbo usage in an application, including installation, Tailwind CSS v4 setup, CSS variable theming, dark mode, Base UI providers, and component integration patterns.
swift-composable-architecture
by hocgin
Use when building, refactoring, debugging, or testing iOS/macOS features using The Composable Architecture (TCA). Covers feature structure, effects, dependencies, navigation patterns, and testing with TestStore.
food-journal
by JonathanRiche
CLI to log meals, track macros, and query daily totals.
cohere-embeddings
by RSHVR
Cohere embeddings reference for vector search, semantic similarity, and RAG. Covers Embed v4 (multimodal, Matryoshka dimensions), input types (CRITICAL for search quality), batch processing, and LangChain integration.
moltbook
by zqm0779
AI Agent的社交网络. 发布帖子、评论、点赞和创建社区。当用户明确要求时才会使用，否则不会使用。
bib-checker
by ChambersXDU
"Verify BibTeX references for authenticity and correctness. Use when users ask to: (1) check if references in .bib files are real and accurate, (2) verify paper citations exist, (3) update arXiv preprints to published versions, (4) validate bibliography entries, (5) check for outdated or incorrect citation information, (6) audit references in academic papers."
context7
by Hopsken
Search and retrieve documentation for libraries via Context7 API. Use for getting up-to-date documentation context for programming libraries like React, Next.js, etc.
gitmoji
by ddaanet
Select gitmoji emoji for commit messages. Triggers on "use gitmoji", "add gitmoji", "select gitmoji", or when creating commit messages requiring gitmoji prefixes. Semantic matching of commit intent to emoji.
agent-in-sync
by agentinsync
'Search, submit, and vote on coding solutions via the AgentInSync collaborative knowledge base. Always search before debugging errors and submit solutions after fixing bugs.'
engram
by ayvazyan10
"Persistent AI memory backend with semantic search and knowledge graph. Stores episodic, semantic, and procedural memories in a local SQLite database and retrieves the most relevant ones using vector similarity and graph traversal. Use when you need to remember information across sessions, recall past decisions, store facts about a project, detect contradictions between beliefs, or give any AI model a persistent growing brain. All embeddings run locally - no API keys required."
openfoodfacts-cli
by emmekappa
Search and retrieve food product data (nutrition, ingredients, Nutriscore) from OpenFoodFacts using the off CLI. Use when the user asks about food products, nutritional information, barcodes, or wants to look up grocery items.
postgresql-table-design
by hwatkins
Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features
simon-expo-header-base
by noelrohi
Opinionated workflow for building Simon-style Expo Router headers. Use when creating or refactoring screen headers, title bars, toolbars, search bars, form sheets, or liquid-glass header surfaces in this repo, and you need to match existing Stack.Header, Stack.Screen.Title, Stack.Toolbar, Stack.Toolbar.View, Stack.SearchBar, and sheetAllowedDetents patterns.
qmd
by yotamleo-org
Search markdown knowledge bases, notes, and docs with QMD. Use to search notes or look up information.
turso-db
by sivukhin
Turso (Limbo) database helper — an in-process SQLite-compatible database written in Rust. Formerly known as libSQL / libsql. Replaces @libsql/client, libsql-experimental for Turso use cases. Works in Node.js, browser (WASM + OPFS for persistent local storage), React Native, and server-side. Features: vector search, full-text search, CDC, MVCC, encryption, remote sync. SDKs: JavaScript (@tursodatabase/database), Browser/WASM (@tursodatabase/database-wasm), React Native (@tursodatabase/sync-react-native), Rust (turso), Python (pyturso), Go (tursogo). This skill contains all SDK documentation needed to use Turso — do NOT search the web for Turso/libsql docs.
similar-files
by watthem
"Finds similar files in a codebase using TF-IDF and cosine similarity. First, index a workspace, then find related files."
academic-research-agent
by akwancakra
Perform systematic academic literature research, extract structured data, and synthesize findings for a specific research need.
fe-refactor
by ingpdw
React/Next.js/TypeScript 코드를 리팩토링하는 스킬. 컴포넌트 분리, 커스텀 훅 추출, 디자인 패턴 적용, 코드 정리 등. "리팩토링", "refactor", "코드 개선", "분리해줘", "정리해줘" 등의 요청 시 사용.
obsidian-rag
by Danielproton721
Busca semântica no vault Cerebro-Trafego (Jarvis V4) via MCP obsidian-rag. Use ANTES de responder qualquer pergunta sobre SOPs, métricas, histórico de contas, memórias do Daniel ou decisões táticas já registradas. Indexa 15 SOPs consolidados com embeddings locais (nomic-embed-text via Ollama).
docs-discovery
by brixtonpham
"Technical documentation discovery via context7 and web search. Capabilities: library/framework docs lookup, topic-specific search. Keywords: llms.txt, context7, documentation, library docs, API docs. Use when: searching library documentation, finding framework guides, looking up API references."
word-explorer
by bromanko
This skill should be used when the user provides a word and requests an exploration of its meaning, etymology, usage, and literary examples. The skill produces comprehensive, engaging word profiles that combine dictionary definitions, pronunciations, literary quotations, and practical usage guidance.
knowledge-synthesis
by saga
把论文、厂商实践、开源实现和已有研究综合成跨来源的架构模式与候选 primitive。当用户要求抽象共性、形成统一模型、指导 Common Library、形成 roadmap 时使用；先验证责任边界，再决定是否值得抽象。
research-skill
by maxoreric
调研最佳实践的 Skill。当需要了解某个领域的方法论、工具、最佳实践时触发。触发词：调研、research、了解一下、有什么方法、最佳实践。
etoile
by etoile-dev
Implement and troubleshoot Etoile integrations for real apps using the API, Node SDK, and React SDK. Use when requests mention Etoile indexing/search, /api/v1/index, /api/v1/search, /api/v1/documents, @etoile-dev/client, @etoile-dev/react, cURL/fetch integration examples, key usage (public vs secret), search UI setup, or migration from another search provider.