ツール

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.

Fetches captions and transcripts for YouTube videos and Shorts, with language selection and fallback, optional timestamps and sponsor segments filtered by default. No API key for transcripts; the optional visual analysis tool needs a TwelveLabs API key and a direct video URL.

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.

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.

A macOS say-style text-to-speech CLI that uses ElevenLabs or 60db to speak text aloud or save it as audio (ElevenLabs supports streaming playback), and can list and switch voices. Needs an API key for the chosen service.

Writes human-sounding text for tweets, emails, articles, bios and READMEs: avoids a banned word list, rule-of-three and uniform sentence lengths, limits em dashes and exclamation marks, prefers concrete numbers and real names without inventing data or quotes, and matches the author's voice.

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.

Postiz's official agent CLI: lets AI schedule posts to 28+ platforms such as X, LinkedIn, Instagram, TikTok and YouTube, upload images and video, and check post and account engagement. Ships with skills and a Claude Code plugin. Needs Node.js and a Postiz account (cloud or self-hosted).

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.

Voice skills: TTS with subtitle timing, emotional character voices, translated dubbing, two-host news podcasts, sound effects and songs. Narration and podcasts work with local Kokoro or free voices; emotion, cloning, dubbing, effects and songs need a Noiz API key. Never clone voices to deceive.

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.

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.

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.

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.

Notion's official Claude Code plugin: bundles Notion's hosted MCP with four Cookbook skills (knowledge capture, meeting prep, research write-ups, spec to implementation) and slash commands for searching, creating pages, querying databases and creating tasks. OAuth sign-in.

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.

Write a script, speakers and visuals in MulmoScript (JSON or YAML) and the mulmo command generates narration and images and assembles a video, podcast, slide deck or PDF, for explainer videos. Needs Node.js, FFmpeg and an OpenAI API key; other providers optional.

Astronomer's official data engineering plugin: write Airflow DAGs to best practices, debug pipeline failures, trace data lineage, profile warehouse tables and migrate from Airflow 2 to 3, with a built-in Airflow MCP server and session hooks.

Research guardrails for PhD students: reproduce arXiv papers, debug training anomalies with evidence, compare runs at matched epochs, check paper-code consistency, verify BibTeX, find literature gaps and predict reviewer comments. No MCP or extra dependencies; mostly for ML research.

Typed as /bro, has the agent re-explain its previous reply in plain, casual language without answering anything new or calling tools, keeping paths, commands and numbers verbatim and replying in the original language.

Official FinLab quant skill: lets agents use FinLab data (mainly Taiwan stocks, plus US, Japan, Korea and Hong Kong) to write stock-picking strategies, run backtests and analyze factors. Needs a FinLab account (free tier has a daily data cap), Python 3.10+ and uv. Not investment advice.

Lets agents run local ComfyUI workflows to generate images, audio and video, regenerate from earlier results with new parameters, check the queue and switch models. Install and start ComfyUI, then clone this repo and run the server with Python (port 9000 by default).