ツール

The five-agent PaperOrchestra pipeline (outline, figures, literature review, section writing, polishing) as skills: turns research ideas, experiment logs and a conference template into a LaTeX paper and checks citations via Semantic Scholar. Needs Python; verify the draft yourself.

Economics writing skill built on 50+ guides (Cochrane, McCloskey and others): shapes abstracts, introductions and conclusions by paper type and 13 identification strategies such as DiD, IV and RDD, simulates three referee scores and flags citations to verify.

Helps agents write geospatial SQL for PostGIS, DuckDB, BigQuery and Snowflake: inspect schemas and keep query costs in check, then render results as interactive maps to review and correct. Needs Python and your own database or warehouse; maps use Dekart, which can run locally in Docker.

One server for Google Docs, Sheets, Drive, Gmail and Calendar: draft and format documents, handle comments, organize sheets and charts, triage email and schedule events. Create an OAuth client in Google Cloud and run the auth command once; needs Node.js.

Compares two versions of a LaTeX manuscript and produces a .tex that marks additions and deletions in color and strikethrough; compile it for a tracked-changes PDF to show reviewers, or diff versions from Git history. Ships with TeX Live and MiKTeX; needs Perl.

Official Firecrawl skill: drives the Firecrawl CLI to search, scrape, map site URLs, batch-crawl, interact with pages and monitor changes, returning LLM-ready Markdown. Search and scrape have a rate-limited free tier; crawling and monitoring need an account or self-hosted instance.

Firecrawl's official CLI: scrape, search, map and crawl sites and interact with pages in a browser from the terminal, with Markdown output; can also install companion skills for coding agents. Needs a Firecrawl account or API key, or point it at a self-hosted instance.

Searches about 30 biomedical sources, including PubMed, ClinicalTrials.gov, ClinVar and OncoKB, with one command syntax, covering literature, clinical trials, genetic variants, drugs and pathways. Ships as both a CLI and an MCP server.

Microsoft Azure's official tool for translating Markdown, Jupyter notebooks and image text into 50+ languages; re-translates only changed parts and keeps links and formatting. Needs Python 3.11+ and an Azure OpenAI, OpenAI or Anthropic key; images need Azure AI Vision.

15 marketing and growth skills for founders and small teams: SOPs, go-to-market plans, next growth moves, competitive intel, pricing, cold email outreach, landing page CRO, PRDs, and X and LinkedIn posts. Add a company context file to your project for output that fits your business.

Generates flowcharts, sequence diagrams, class diagrams and other charts from Mermaid syntax with configurable theme and background, exporting SVG or PNG files or a mermaid.ink share link. Validates syntax so the model can fix errors over several turns.

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.

PubMed plugin from Anthropic's life sciences marketplace: connects to the US National Library of Medicine's remote MCP to search biomedical literature and research papers. No account needed.

Anthropic's official life sciences plugin marketplace: install MCP plugins such as PubMed, BioRender, Synapse, ChEMBL and 10x Genomics, plus research skills for single-cell RNA QC, Nextflow pipelines and scvi-tools. Some data sources need an account or subscription.

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.

DAIR.AI Academy lesson-planning plugin: from a topic or source material, builds an interactive mini-course of 6-8 lessons, each with goals, flashcards and a quiz, plus a final review, citing sources when you supply material. Output is local HTML; no server or account needed.

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.

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.

14 social media skills: audience and content pillars, posting calendars, platform-specific posts, threads, carousel scripts and captions, and analytics on what drives follower growth. For LinkedIn, X, Threads, Instagram and more; connect the BlackTwist MCP to schedule posts directly.

Turns a conversation into an album production workflow: concept, research, lyrics and pronunciation checks, Suno-style prompts, mastering, promo videos and social copy. You generate songs in Suno yourself; needs Python 3.11+ and ffmpeg, and the author recommends a Claude Max plan.

Turns Strunk's The Elements of Style (1918) into a writing skill so agents write docs, commit messages and error messages clearly and concisely. The full text (about 12k tokens) loads only when needed. By the author of Superpowers.

Reads an article or document, pulls out the key points and generates an illustration for each, plus an optional cover. Three styles (gradient glass, ticket, vector illustration) and 16:9 or 3:4 ratios for blogs, slides and social posts. Needs a Gemini API key and Python.

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.