Herramientas

ByteDance's open-source multimodal agent CLI: operates browsers via vision or the DOM and calls terminal, file and MCP tools to complete tasks, with a Web UI and headless server mode. Needs Node.js 22+ and a model API key.

Browser automation MCP server open-sourced by ByteDance in the UI-TARS-desktop repo: drives pages through Puppeteer accessibility data with an optional vision mode, running locally over stdio or remotely over SSE or Streamable HTTP.

Detects your CPU, memory and GPU and scores open models on whether they run, speed, quality and context, then works with local runtimes like Ollama, llama.cpp and MLX to download and benchmark them. recommend --json gives agent-friendly output.

Package manager for the open Agent Skills ecosystem: one command installs skills from GitHub and other sources into Claude Code, Codex, Cursor and dozens more agents, with search, update and removal. From Vercel Labs.

When a user asks whether a skill exists for some task, searches the skills.sh ecosystem with the skills CLI, then recommends and installs a fit. Maintained by Vercel Labs and shipped in the skills CLI repo.

Define multi-container apps in compose.yaml and bring up services, databases, caches and the rest with one docker compose up, handy for agents setting up local dev and test dependencies. Maintained by Docker; included with Docker Desktop on macOS.

Local model gateway that routes requests from Claude Code, Codex and other coding agents to providers like DeepSeek, Kimi, Gemini and OpenRouter, with failover, rule-based routing and request logs. Bring your own API keys.

Trading research agent from HKU's HKUDS whose MCP server offers 70+ tools for quotes, financials, backtesting and research across A-shares, Hong Kong and US stocks and crypto. Needs local Python; HK, US and crypto research need no API key. For research only; not investment advice.

Official CLI for Tencent's open-source knowledge base platform WeKnora: upload documents, manage knowledge bases, run hybrid search and answer questions from them, or serve as a read-only MCP. Needs your own WeKnora deployment and a source build with Go 1.26+.

Lightweight command-line JSON processor that slices, filters, maps and transforms JSON with concise expressions and no runtime dependencies. A staple for agents parsing API responses and logs.

For preclinical life sciences research: bundles MCP connectors for PubMed, bioRxiv, ChEMBL, Open Targets, ClinicalTrials and more, plus analysis skills for single-cell RNA QC, scvi-tools and nf-core pipelines. Official from Anthropic; some data sources need accounts.

Generates people analytics reports from employee data: headcount snapshots, voluntary and involuntary attrition, diversity metrics, spans of control and flight risk, with findings and recommendations for leadership. Needs an uploaded employee CSV or a connected HRIS. Official from Anthropic.

Anthropic's official data skill that guides agents to write, translate and optimize SQL across Snowflake, BigQuery, Databricks, PostgreSQL and other warehouse dialects, including CTEs, window functions and analytical aggregations.

Data analysis plugin: writes queries in each SQL dialect, explores datasets, runs statistical tests, charts with Python and builds interactive HTML dashboards, then reviews methods and conclusions before sharing. Connects to Snowflake, BigQuery and other warehouses. Official from Anthropic.

Plugin for design teams: design critiques, design system audits, UX copy, accessibility checks, user research synthesis and developer handoff notes. Official from Anthropic; works best with Figma connected.

Turns campaign or channel data into weekly, monthly or quarterly marketing reports: executive summary, key metrics and period-over-period trends, wins and misses, and next-period priorities. Connect analytics tools or just paste tables or key numbers. From Anthropic's knowledge-work-plugins.

Calls Codex from Claude Code for read-only or adversarial code reviews, or delegates tasks to Codex to run in the background. Maintained by OpenAI; needs a ChatGPT account (the free tier works) or an API key.

Vercel's official cost and performance skill: gathers production metrics, usage and project config, investigates only the routes and files the metrics point to, and returns ranked, doc-backed recommendations. Supports Next.js, SvelteKit and Nuxt; needs Vercel CLI v53+ logged in and linked.

Vercel's official deployment skill: checks the git remote, project link and CLI login, then deploys a preview (default) or production via git push or vercel deploy. When login isn't possible in a sandbox, it can create a claimable preview link.

React and Next.js performance rules from Vercel's engineering team: 70 rules ranked by impact covering request waterfalls, bundle size, server performance and re-renders, for writing, reviewing and refactoring. Maintained by Vercel.

Vercel's React Native and Expo best practices ranked by impact, covering list scrolling performance, Reanimated animations, navigation, UI patterns, state management and monorepo setup. Maintained by Vercel.

Vercel's guide to React composition patterns: replaces boolean prop sprawl with compound components, lifted state and clean Context interfaces, including React 19 API changes. Useful for refactoring component libraries and reviewing component architecture.

Reviews UI code against Vercel's Web Interface Guidelines, covering accessibility, focus, forms, animation, typography, dark mode and more, listing issues as file:line. Fetches the latest rules before each review. Maintained by Vercel.

Processes large tool outputs in a sandbox and returns only the results to context; logs session events in SQLite with FTS5 so work continues after context compaction. Supports Claude Code, Codex and a dozen other clients. ELv2 licensed.