도구

Unbabel's machine-translation quality metric: comet-score rates translations per sentence and overall, XCOMET marks error spans and severity, and CometKiwi works without a reference. Good for spot-checking MT. Needs Python 3.8+; models download from Hugging Face, some need a license; GPU helps.

A research plugin for Claude Code: commands like /omp:survey, /omp:experiment and /omp:write chain literature review, topic selection, experiments, writing and self-review, with 5 specialized agents and 34 research skills that remember project progress across sessions. Experiments lean toward ML.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Google Maps for agents: place search and details, forward and reverse geocoding, routes, distance matrices, multi-stop optimization, weather and static maps, plus trip planning and local SEO ranking skills. Needs Node.js and a billing-enabled Google Maps Platform API key; calls may cost money.

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.

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.

Anthropic's official skill that reads outpatient notes like a medical coder, decides which diagnoses to report and assigns billable ICD-10-CM codes as specific as the record allows, verified via the ICD-10 connector in the healthcare plugin. US outpatient; certified coder review required.

Anthropic's official skill for US prior auth review: checks records, provider credentials and codes, weighs medical necessity against Medicare policy, recommends approve, deny or pend and drafts the letter. Needs the healthcare plugin's CMS, NPI and ICD-10 connectors; clinicians confirm.

Anthropic's official healthcare plugin for the US system: extract data from clinical notes, assign ICD-10 and CPT/HCPCS codes, review prior auths, screen for fraud and draft trial protocols, with hosted CMS, NPI and PubMed connectors. FHIR access needs API rights; clinicians must review.

Install the QGIS MCP plugin from the QGIS plugin repository and agents get 125 tools to manage layers, edit features, run processing algorithms, style maps, build layouts and atlases, and run SQL across layers; supports QGIS 3.28 to 4.x. Needs QGIS and uv; no repo download required.

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).

Official Databricks skills guiding agents to build Lakeflow pipelines and jobs, Apps, Lakebase, Vector Search, Model Serving and AI/BI dashboards on the lakehouse. Needs the Databricks CLI.

Official Databricks plugin with skills for the CLI and auth, Genie data queries, Apps, Lakebase, Lakeflow jobs and pipelines, Model Serving and DABs deployment, plus hooks for prompt routing, session context and auth failure hints. Needs a Databricks account.

59 clinical research skills from a radiologist at Korea's Asan Medical Center: study design and sample size, de-identification, statistical figures, 49 reporting guidelines, risk-of-bias checks, citation verification and reviewer replies. Literature APIs need no key. Medical review required.