Research skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

tutor-research

학습 질문을 받으면 공식 문서(context7)와 웹검색을 동시에 병렬로 조사해, 출처가 검증된 최신 학습 근거를 종합해 드립니다. 개인 튜터가 자료를 미리 조사해 오는 역할입니다. 다음과 같은 요청 시 사용하세요: - "claude cowork의 Skills와 Sub-agents 차이를 최신 정보로 조사해줘" - "이 개념 정확한 최신 내용으로 알려줘" - "여러 자료 병렬로 조사해서 가르쳐줘" - "context7로 공식 문서랑 웹 최신 내용 같이 찾아줘" - "React 19 use훅 공식 문서 기준으로 설명 준비해줘" - "튜터처럼 이 주제 깊이 조사해줘" 질문을 리서치 축으로 분해해 context7(라이브러리·SDK·CLI 공식 문서)과 WebSearch(최신 트렌드·튜토리얼·비교)를 병렬 실행하고, 출처를 교차검증한 뒤 learning-material로 넘길 종합본을 만듭니다. [책임 경계] vs moai-education:research-assistant: 이 스킬=개인 학습용 최신 정보 빠른 조사, 저 스킬=학술 논문용 문헌 검토와 인용 관리.

254 repo starsObserved in 1 repos
Research
GitHub

felo-search

Felo AI real-time web search for questions requiring current/live information. Triggers on current events, news, trends, real-time data, information queries, location queries, how-to guides, shopping, or when Claude's knowledge may be outdated.

252 repo starsObserved in 2 repos
Research
GitHub

felo-web-fetch

Extract webpage content with Felo Web Extract API. Use for turning URLs into html/markdown/text, selecting specific page areas with CSS selectors, and controlling extraction options like crawl mode, cookies, user-agent, and timeout.

252 repo starsObserved in 2 repos
Research
GitHub

gemini-deep-researcher

Use this skill when a user wants a comprehensive research report on any topic with cited sources. Prefer this skill for requests like "research this topic", "give me a deep analysis of", "幫我研究", "深度分析", or when the user needs a well-sourced report for decision-making, presentations, or learning. This skill uses Gemini's Deep Research agent and takes several minutes to complete.

252 repo starsObserved in 1 repos
Research
GitHub

openprd-benchmark-router

为 OpenPrd 产品、CLI、Agent harness、AI code review / PR review harness、上下文工程、提示词优化和图标资源选择对标来源与调研路径。

252 repo starsObserved in 1 repos
Research
GitHub

searcharvester-deep-research

Deep-research methodology with a ROLE-BASED team of parallel sub-agents. One `delegate_task` batch dispatches 2–3 researchers (each on a distinct sub-question), 1 critic (adversarial counter-search), and 1 fact-checker (numeric/date verification). The lead synthesises their findings into a cited report at ./report.md. Use for "research", "deep research", "report with sources", comparisons with citations, anything needing grounded multi-source evidence.

252 repo starsObserved in 1 repos
Research
GitHub

searcharvester-extract

Fetch a web page and extract its main content as clean markdown via trafilatura. Strips navigation, ads, and footers automatically. Supports size presets (short/medium/long) and full mode with pagination for very long documents. Use after `searcharvester-search` to actually read the pages behind your URLs.

252 repo starsObserved in 1 repos
Research
GitHub

searcharvester-search

Search the web via SearXNG (100+ engines: Google, DuckDuckGo, Brave, Bing, Yandex, Mojeek, ...) through a Tavily-compatible API. Use when the user needs to find information, recent news, compare sources, gather facts, or locate specific URLs. Returns title + URL + short snippet for each result. For full page content, follow up with the `searcharvester-extract` skill.

252 repo starsObserved in 1 repos
Research
GitHub

demographics-analysis

Demographics and market site analysis — population, income, age, housing market, and employment data from an address.

251 repo starsObserved in 2 repos
Research
GitHub

nyc-dob-permits

Look up DOB permit and job filing history for any NYC building — new-building, alteration, and demolition filings with status and dates. Use when the user asks what work was filed or permitted at an address, or to gauge renovation history during due diligence. NYC only; for open violations use /nyc-dob-violations.

251 repo starsObserved in 1 repos
Research
GitHub