Tools

Open-source personal AI assistant that runs on your own machine and talks to you over 20+ chat channels such as Telegram, Slack and iMessage. The openclaw CLI manages the gateway, channel pairing and plugins; switch models between Claude, Codex and local ones.

Command-line audio and video downloader supporting thousands of sites: pick formats and quality, grab subtitles and metadata, and merge or transcode with FFmpeg. The actively maintained fork of youtube-dl.

From Microsoft: converts PDF, Word, Excel, PowerPoint, HTML and other files or URLs to Markdown so agents can read and search them. A single convert_to_markdown tool over STDIO or local HTTP.

Converts PDF, Word, Excel, PowerPoint, HTML, images, audio and more into Markdown that keeps headings, lists and tables, ready for LLMs to read and analyze. Maintained by Microsoft; requires Python 3.10+.

Anthropic's document skills, the implementation behind Claude's file features: create, edit and analyze Word, Excel, PowerPoint and PDF files, including tracked changes, comments, formulas and form filling. Source-available, not under an open-source license.

Extracts text and tables from PDFs; merges, splits and rotates pages, adds watermarks, fills forms and OCRs scanned documents. The official Anthropic skill behind Claude's document features; source-available, not open source.

Lets agents model, lay out scenes, tweak materials and run Python in Blender, and import Poly Haven, Sketchfab and AI-generated 3D assets. Requires uv and the companion Blender add-on.

OCRs photos of visa documents such as bank, employment or income certificates, translates them into English and builds a side-by-side bilingual PDF. Needs Python (pillow, reportlab) and an OCR engine. Not an official certified translation: verify names, amounts and dates.

Makes GIFs that follow Slack's recommended size, frame rate, color and length for emoji (128x128) and message GIFs (480x480), with animation tips and tools to assemble and validate them. Built on Python and Pillow. Official Anthropic skill.

Creates generative art such as flow fields and particle systems with p5.js and seeded randomness: first writes an algorithmic design philosophy, then outputs an interactive HTML viewer with tunable parameters. Official Anthropic skill.

Creates, reads and edits Word documents: tables of contents, page numbers and letterheads, tracked changes, comments and find-and-replace, while preserving existing formatting. The official Anthropic skill behind Claude's document features; source-available, not open source.

Writes internal communications in familiar company formats: 3P updates, leadership reports, project status updates, company newsletters, FAQs and incident reports. Official Anthropic skill.

Ten built-in color and font themes to apply to slides, documents, reports and HTML landing pages, or generate a new theme on demand. Official Anthropic skill.

When answering questions about using Claude and its products, attaches a matching course, tutorial or case study from the Claude Academy catalog. Recommends only strong matches and never invents courses. Official Anthropic skill.

Creates, reads and edits PowerPoint decks: applies templates and layouts, handles speaker notes and comments, and merges or splits slides. The official Anthropic skill behind Claude's document features; source-available, not open source.

Creates, edits and analyzes Excel spreadsheets: formulas, formatting, charts and data cleaning, plus conversion between CSV, TSV and other tabular formats. The official Anthropic skill behind Claude's document features; source-available, not open source.

Official MoneyPrinterTurbo skill: give it a topic or script and the agent installs, configures and produces a short video with voiceover, stock footage, subtitles and music; defaults to Chinese vertical MP4. Needs an LLM API key and a free Pexels key; macOS and Windows.

Generates or edits images: photos, illustrations, textures, game sprites, product mockups and transparent assets. A built-in Codex system skill using the image_gen tool, no install needed; with approval it can use a bundled CLI script that needs OPENAI_API_KEY. By OpenAI.

OpenAI's open-source general-purpose speech recognition model. The whisper command transcribes many languages, translates foreign speech into English and writes subtitle files. Needs FFmpeg; faster with a GPU.

Official MCP reference server for reading, writing, editing, moving and searching local files within an allowlist of directories, adjustable at runtime through Roots. Handy for organizing documents from a desktop client.

Gives agents the current time and IANA time zone conversion, detecting the system time zone automatically. No API key needed. Official MCP reference server, written in Python.

Baidu PaddlePaddle's official OCR and document parsing tool: the paddleocr command reads text from images and parses PDFs and scans into Markdown or JSON, supporting 100+ languages with models that run locally.

Official PaddleOCR MCP: text recognition and layout parsing for images and PDFs (PP-OCR, PP-StructureV3, PaddleOCR-VL), returning text or Markdown. Runs inference locally, or calls the official API or a self-hosted service.

Document parser from OpenDataLab that turns PDFs, images and Office files into Markdown or JSON, handling tables, formulas and complex layouts well, with page-by-page reading and citation anchors for agents. Parses locally by default; needs Python 3.10+.