도구

Anthropic's official research skill built on Fischbach and Walsh's problem-selection framework (Cell): a conversational guide to refining project ideas, assessing risk and success criteria, unblocking stalled research and choosing directions. No setup or account needed.

Official BioRender plugin in Anthropic's life sciences marketplace: connects Claude Code to BioRender's scientific icons, templates and figures to find assets and make paper figures, lecture slides and talk graphics. Needs a free BioRender account; authorize it in /plugin after installing.

Plugin from Wiley in Anthropic's life sciences marketplace: connects the Scholar Gateway remote MCP for semantic search across Wiley's peer-reviewed journals, with answers carrying checkable citations and DOI links. Good for literature reviews. Needs a free Scholar Gateway account.

Redis's official MCP server: read and write strings, hashes, lists, streams, JSON and other data structures in natural language, with vector indexing and search and pub/sub. Bring your own Redis instance; runs via uvx.

Lets agents read dbt project models, lineage and Semantic Layer metrics, run build, run and test commands, and call the dbt platform Discovery and Admin APIs. Maintained by dbt Labs; Semantic Layer and platform tools need a dbt platform account.

DAIR.AI learning plugin that turns YouTube lectures and talks into local study material: extracts slide frames, builds timestamped transcripts, and lets you take notes and review in a bundled web viewer. Needs Python, yt-dlp and ffmpeg.

Official DuckDB skills: query local or S3 CSV, Parquet, Excel and JSON files with SQL or plain language, attach databases, convert formats, analyze spatial data and look up documentation. Needs the DuckDB CLI; tested only on macOS and Linux.

Elastic's official skills teaching agents to use Elasticsearch and Kibana correctly: index design, ES|QL queries, search relevance tuning, dashboards, observability troubleshooting and security alert triage. Currently a technical preview.

Chroma's official MCP: lets agents create and manage collections, add documents, and retrieve them with vector search, full-text search and metadata filters. Connects to in-memory or local persistent stores, self-hosted instances or Chroma Cloud.

33 cognitive-science-based tutoring skills for K-12 math and science, exam prep, university subjects, academic writing and job interviews, using Socratic questions and spaced review rather than giving answers. In Chinese and English; copy the skills folder into your agent manually.

Research workbench that turns paper PDFs into a searchable library so Claude Code or Codex can find and close-read papers, draft reviews and manuscripts, answer reviewer comments and check citations. Imports from Zotero and EndNote. Needs Python 3.10+; an LLM API key is optional.

Converts between Markdown, Word, HTML, LaTeX, EPUB and more with Pandoc, exports PDF and PPTX, and can apply a Word template for consistent styling, handy for formatting manuscripts and handouts. Needs Pandoc and uv; PDF export also needs TeX Live.

Give it a YouTube video, web article or PDF link and it extracts the transcript or text, then builds a five-round Ship-Learn-Next action plan saved as Markdown, for self-study. Needs CLI tools such as yt-dlp and pdftotext; videos default to English subtitles.

Official ClickHouse skills: best practices for schema design, primary keys, JOINs and inserts ranked by impact, advice on real-time architecture decisions, in-process SQL and pandas-compatible analysis with chDB, and local and cloud deployment workflows.

Paper review skills by economist Claes Bäckman: eight subagents simulate journal referees for a pre-submission report, plus quick checks, paper-code consistency checks, reviews of pre-analysis plans and grant proposals, and rewriting papers as policy briefs. Mainly for LaTeX manuscripts.

Official ElevenLabs skills: text to speech, speech to text, sound effects and music generation, voice changing, vocal isolation, multilingual dubbing and building voice agents. Needs an ElevenLabs API key.

Uses yt-dlp to pull YouTube subtitles into the agent, so asking it to summarize a video gets you the key points; handy for teachers prepping lessons, researchers and creators. No API key, but needs yt-dlp (Homebrew or WinGet) and Node.js.

MCP server for the Lean 4 theorem prover: lets agents read proof goals, diagnostics and definitions and search theorems via LeanSearch and Loogle, helping mathematicians and students with formal proofs. Needs uv and the Lean toolchain; run it from the Lean project root.

Post-draft polishing skills for English LaTeX papers, Chinese theses (GB/T 7714) and Typst manuscripts: compile diagnostics, format and grammar checks, reference verification, reviewer-style assessment, cover letters and defense slides. Needs Python, uv and TeX Live; academic use only.

68 trading and quant skills focused on crypto and DeFi: market and on-chain data, technical indicators, backtesting, position sizing and risk, prediction markets, and tax tools for cost basis and wash sales. Most need Python and data API keys (often free tiers); get expert review.

Connects Stata to VS Code or Cursor and exposes a local MCP endpoint so Claude Code or Codex can write and run do-files and read regression output, with graphs shown in the editor; for empirical research. Needs a licensed Stata 17+, the extension installed and the editor open.

Appium's official MCP server: lets agents start sessions on Android and iOS emulators and real devices, locate elements, tap, type and take screenshots, and generate Java/TestNG test code. Needs the Android SDK or Xcode.

AI agents collaborate via the ADDIE instructional design model: enter a course name to get a syllabus, LaTeX slides, lecture scripts and assessments, convertible to editable PPTX. Open-source code for an EACL 2026 paper; needs an OpenAI API key, LaTeX for PDFs and Node.js for PPTX.

Official Tavily skills: let agents search the web, extract page content, discover site URLs, crawl in bulk and run cited deep research through the Tavily CLI (tvly). Install the CLI first; search and extract have a limited no-login tier, other features need sign-in or an API key.