Discover blockchain academic skills, compare source repositories and read the instructions for each workflow.
Perform comprehensive geopolitical research using GDELT data sources and specialized analysis agents. Routes queries to appropriate workflows (conflict analysis, sanctions research, actor mapping, narrative ana...
Multi-source comprehensive research using perplexity-researcher, claude-researcher, and gemini-researcher agents. Three modes - Quick (3 agents), Standard (9 agents), Extensive (24 agents with be-creative skill...
AI-powered research skill with five workflows - chat (single-model conversation), consensus (multi-model synthesis), thinkdeep (systematic investigation), ideate (creative brainstorming), and deep (multi-phase...
ライブラリ内の類似した信号処理手法の技術的・物理的な違いを分析し、比較解説付きのノートブックセクションを作成する
LLM 기반 심층 리서치 스킬. 주제에 대해 자동으로 검색 계획을 수립하고, 웹 스크래핑 후 종합 리포트를 생성. 사용 시점: (1) 특정 주제에 대한 포괄적인 분석이 필요할 때 (2) 다양한 소스에서 정보를 수집하여 종합해야...
DuckDuckGo 기반 빠른 웹 검색 스킬. 특정 사실 확인, 최신 뉴스 조회, 간단한 정보 수집에 사용. 사용 시점: (1) 특정 사실을 빠르게 확인해야 할 때 (2) 최신 뉴스나 이벤트를 조회할 때 (3) 심층 분석 전 초기 정보 수집...
Send Research Swarm documents to Kindle. Use when "send to Kindle", "send research to Kindle", "send someday-maybe to Kindle", "Kindle my research", "with links expanded", "send last week's research", "send Jan...
Search code and documentation using full-text and semantic search. Accepts a query string and returns matching files with relevance scores.
This skill guides the process of creating context-free queries for a web search agent (another Claude instance with web search tools). Use this when you need expert guidance from web research but the search age...
Search press releases using press-ndjson-search and format results for blog post references. Generates press_references.json files that can be displayed with the PressReferences component.
Use the `emv-pers` search script to find press items in `press.normalized.ndjson` and return small, LLM-safe JSON results (date, title, url, verbatim excerpts). Use when the LLM needs sources, dates, and exact...
Transcribe handwritten multi-source research notes from reMarkable PDFs or paper photos. Trigger phrase "process deep dive notes". Handles research compilations with multiple sources per document. Converts hand...
Review and triage PR comments interactively
External (non-workspace) research protocol. Use network search only to locate canonical repos/docs, then verify by reading source (github_repo) or official docs (Context7/DeepWiki). Enforce fact-driven answers...
Revisa la ortografía española en archivos del proyecto (acentos, eñes, signos de interrogación). Usar cuando el usuario diga "revisa ortografía", "busca faltas", "corrige acentos" o invoque /revisar-ortografia.
AI SEO Audit v2.0 for Generative Engine Optimization (GEO). Analyzes websites for AI discoverability in ChatGPT, Claude, Perplexity, and Google AI Overviews. Uses research-backed methodology with 36 checks acro...
Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Doc...
Use this agent when needing to gather comprehensive documentation and best practices for specific frameworks, libraries, or dependencies in a project. Specializes in fetching official documentation, exploring s...
Use when you need programming best practices, patterns, or documentation. Queries the Grimoire knowledge base for curated guidance on Go, Rust, Python, and more. Invoke before implementing features, debugging,...
Use Exa's /search and /contents APIs to perform internet-scale retrieval, filter by domain/date, and fetch cached page text, highlights, or summaries.
Review synthesis prep for the-art readiness. Verify thematic guidance format, not outline format. Gate before DRAFT stage.
Prepare synthesis guidance for the-art. NOT an outline. Provides thematic guidance, narrative intent, and evidence library that enables synthesis instead of expansion.
Fact-check and verify technical accuracy of blog articles. Code examples, links, claims, dates. Use at TECHNICAL stage of blog pipeline.
Create D3 questions focused on written explanations and reflections of static content (text, images, diagrams). For video-based questions, use implement-video-question instead.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.