Tools

Lets agents write and run Playwright scripts on the fly for browser testing and automation, auto-detecting local dev servers, with screenshots, responsive checks, login flows and link checking. After installing, run npm run setup in the skill directory.

Recognizes images or whole PDFs (including scans) with math formulas and tables into Markdown and LaTeX, strong on English and Chinese and supporting 80+ languages, handy for digitizing exams, lecture notes and study notes. An open-source Mathpix alternative that runs locally with Python.

Search and download arXiv papers and read the authors' LaTeX source section by section, export BibTeX and follow topic updates, with papers cached locally. No API key needed.

Turns a topic or article into a narrated explainer video in English or Chinese: research, script, voiceover, storyboard and per-shot animation, with subtitles and chapter cards. Needs Node.js, ffmpeg and Python; takes about 1-3 hours depending on length. Free for non-commercial use only.

Pluggable natural-language linter that checks Markdown and plain text for wording, punctuation and terminology consistency like code, with auto-fix, and can also run as an MCP server. Rules are installed separately, mostly for Japanese and English; requires Node.js 20+.

MCP server built into the textlint proofreader: agents check Markdown, plain text and other documents against your rules for wording, punctuation and formatting issues and get auto-fixed text. Needs Node.js plus a .textlintrc and rule packages in your project; textlint has no default rules.

Microsoft's official skill collection: 170+ skills focused on Azure SDKs (Python, .NET, TypeScript, Java, Rust) and Microsoft Foundry development, plus plugins, custom agents and MCP configs. Microsoft recommends picking skills per project rather than installing them all.

Standards-based command-line calendar that syncs iCloud and other CalDAV calendars via vdirsyncer, so agents can query your schedule and quickly add events; also has an interactive UI. Setting up vdirsyncer takes some technical effort; no Windows support.

Measurement-first audits and optimization of web quality using Lighthouse, Chrome DevTools performance traces and CrUX data, covering Core Web Vitals, WCAG 2.2 accessibility, SEO and best practices, for any frontend framework. By Addy Osmani (not an official Google project).

Unified search across 20+ academic sources including arXiv, PubMed, bioRxiv, Semantic Scholar and OpenAlex, returning deduplicated, normalized results and downloading full text via open-access channels first. Most sources need no API key.

Open-source local video editor with a multi-track timeline. Claude Code or Codex can rough-cut by chat, cut flubs and pauses from the transcript, and add subtitles, transitions and music as drafts you approve. Needs the desktop app with a project open; AI features need your own API keys.

Replaces arXiv preprint entries in your .bib file with the official published versions from DBLP and ACL Anthology, keeping citation keys, to tidy references before camera-ready. Overwrites the file by default, so preview with --dry-run. Mainly covers CS venues; needs Python 3.10+.

Postgres rules ranked by impact: query optimization, indexing, connection pooling, RLS security, schema design and lock troubleshooting, with wrong-vs-right SQL examples, applicable to any Postgres. Maintained by Supabase.

Supabase's official general skill covering the database, Auth, Edge Functions, Realtime, Storage, vectors and queues, plus supabase-js/SSR integration, the CLI and MCP, migrations and RLS security checks, and it checks the latest docs and changelog before acting.

Connects to your Supabase projects: manage schemas and migrations, run SQL, deploy Edge Functions, create development branches and generate TypeScript types. A remote server hosted by Supabase with OAuth sign-in.

Converts PDF, Word, Excel, PowerPoint, images, audio, web pages and YouTube transcripts into Markdown that agents can read and cite. Built on Microsoft MarkItDown; the Docker image lacks audio transcription and image recognition, so build locally for full features.

Open-source, agent-friendly BI: define metrics and dashboards in YAML and SQL, and rill init generates project instructions and MCP config for Claude Code so agents can build business dashboards and answer questions in natural language. Local use is free; publishing to Rill Cloud needs an account.

Open-source meeting bot and real-time transcription platform: sends a bot into Google Meet, Teams or Zoom and transcribes live by speaker, with MCP so agents can dispatch bots and read transcripts. Use the hosted service (API key) or self-host.

WhatsApp CLI: pair as a linked device, sync messages to local SQLite, search offline, send text and files, and manage groups, with --json output for agents. Built on the unofficial WhatsApp Web protocol.

Supermemory's official Claude Code plugin: hooks save memories automatically when a session ends and recall them on demand, giving persistent memory across sessions and projects, with shared project memory for teams. Needs a Supermemory API key and Node.js 18+.

Google's official terminal coding agent and successor to Gemini CLI: understands your codebase and, with your approval, edits files and runs commands. Shares its engine and settings with the Antigravity 2.0 desktop app. Closed source; sign in with a Google account; free tier included.

From a single topic, the agent writes a storyboard, generates paper-cutout collage visuals, motion, narration, music and subtitles, and assembles a Vox-style explainer or ad with ffmpeg, checking with you on storyboard and style. Needs a prepaid Atlas Cloud API key, ffmpeg and Python.

Plugin marketplace for multi-agent dev workflows: omo multi-agent orchestration, BMAD agile role flows, requirements-driven development, SPARV and common dev commands, delegating coding tasks to Codex, Claude, Gemini and other backends (their CLIs installed separately). AGPL licensed.

Bright Data's official MCP: web search (Google, Bing, Yandex), any page to Markdown, structured data extraction from e-commerce, social and other platforms, and remote browser control. Needs an API token; includes 5,000 free requests a month.