Representacions vectorials
Representacions vectorials i similitud
gifgrep
malue-ai
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.
adl
Tyler-R-Kendrick
Use when defining AI agents declaratively with Agent Definition Language (ADL). Covers agent identity, LLM configuration, tools, permissions, RAG inputs, and governance metadata. USE FOR: declarative agent blueprints, agent identity and permissions, LLM configuration, governance metadata DO NOT USE FOR: agent runtime orchestration (use cagent), tool integration (use mcp), agent communication (use a2a)
quarterly-connect
toddward
Assist users in creating quarterly connects that act as a strategic partner to guide employees through comprehensive quarterly reflections, helping craft insightful narratives for Quarterly Connection reviews that align with company values and career development goals.
consult_mvx_docs
multiversx
Access the global MultiversX documentation library to answer technical questions or verify implementation details.
UI/UX Pro Max - Design Intelligence
joneqian
Claude Skill 合集
nfl-super-bowl-scores
Ontos-AI
Finds Super Bowl score records on the NFL website for a given year.
google-image-crawler
xdrshjr
基于 Playwright 的 Google 图片爬虫 Skill，支持自动化搜索、提取高清原图 URL 和批量下载。 核心能力： - 使用 Playwright 自动化 Google 图片搜索，无需手动操作浏览器 - 智能提取原始高清图片 URL（通过解析 imgurl 参数） - 支持自动滚动加载更多图片，突破单次搜索结果限制 - URL 去重和过滤（自动排除缩略图和无效链接） - 支持图片尺寸过滤（最小宽度/高度） - 提供异步和同步两种 API 接口 - 批量下载支持并发和进度显示 适用场景： - 需要批量获取图片素材（设计、训练数据集等） - 需要从 Google 图片搜索抓取高清原图 - 需要自动化图片采集工作流 注意事项： - 请遵守 Google 服务条款和网站的 robots.txt - 控制请求频率，避免对服务器造成压力 - 商业使用请确认图片版权合规 - 建议使用代理避免 IP 限制
ast-grep
tizee
Structural code pattern search and refactoring using ast-grep (sg). Use for finding functions, classes, methods, imports, or any code structure patterns. Supports syntax-aware analysis across multiple languages including JavaScript, TypeScript, Python, Ruby, Go, Rust, and more. Use when searching for code patterns based on structure rather than plain text.
algolia-search
ncdevshiv
"Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning Use when: adding search to, algolia, instantsearch, search api, search functionality."
searching-academic-outputs-with-dimensions
kjgarza
Search for academic literature, empirical evidence, and scholarly research using the Dimensions database. Use when seeking research papers to support product decisions, find empirical studies, conduct literature reviews, explore funding patterns, validate hypotheses with academic sources, or discover research trends. Supports publications, grants, patents, clinical trials, and researcher profiles. Triggers on requests for "academic evidence", "empirical research", "find studies", "literature search", or "research to support decisions".
librarian
Lynricsy
Web research agent for documentation, web search, and code search. Use when: querying docs, searching latest tech info, code search via grep.app. 网络研究专家，专注于外部信息检索。
vault-similar
uhop
Find records semantically similar to a given vault note via embedding nearest-neighbours. Backed by GET /sections/{record_id}/similar. Use when the user says /vault-similar, asks "what other notes are like this one", or wants to discover related concepts beyond what's explicitly wikilinked. Returns ranked records by cosine similarity. Requires vault-storage (:8123) — Obsidian's REST API doesn't expose embeddings.
cortex
digin1
Cortex — self-evolving memory and agent fleet — store, search, and manage memories with semantic search across all projects
grey-haven-seo-geo-optimization
greyhaven-ai
"Use when optimizing web content for search engine visibility, improving AI search engine citations (GEO), auditing website SEO, implementing structured data markup, or researching keyword strategy. Triggers: 'SEO', 'GEO', 'search optimization', 'schema markup', 'meta tags', 'AI search', 'Perplexity', 'search rankings', 'structured data', 'generative engine optimization', 'rich results', 'robots.txt', 'sitemap'."
codebase-navigator
leegonzales
Semantic code search using osgrep for understanding codebases, finding implementations, and navigating large projects. Use when asked "where is", "how does", "find the code that", or any question about code location or implementation.
teach
adamos486
Transforms technical documents into rigorous learning journeys with collegiate-level mastery requirements. Uses Bloom's taxonomy progression, 80%+ mastery thresholds, and multi-level verification before advancing. Treats learning as a high school to college graduation progression. Use when user wants deep understanding, not surface familiarity.
setup-semantic-release
AntJanus
Use when setting up automated versioning, when asked to "set up semantic release", "add conventional commits", "configure automated versioning", "set up commitlint", "add husky hooks", "set up changelog generation", or when initializing a new project that needs a commit and release workflow.
plan-minecraft-mod
jujumelona
Convert a user brief and reference images into a version-pinned game design and an honest buildable Fabric slice.
research-minecraft-evidence
jujumelona
Collect exact-version Minecraft, loader, mapping, library and license evidence before code generation without
route-generic-game-research
jujumelona
Decompose any small or game-scale Minecraft mod request into request-derived research domains, then route each
research
johnlindquist
Comprehensive research combining web search and AI synthesis. Use for deep research on topics, comparing technologies, investigating libraries, and finding GitHub issues related to problems.
cass
johnlindquist
Always search before starting any work across all coding agent session histories (Claude Code, Codex, Cursor, Gemini CLI, Aider, ChatGPT) to find whatever we've discussed before.
ground-production-with-live-evidence
jujumelona
Ground Minecraft production and repair decisions in fresh project, exact-version API, ecosystem, repository,
manage-rag-default
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.