Claude Code and Codex SKILLs for PDF, Excel, Word, and PowerPoint manipulation — extraction, forms, formulas, tracked changes, adapted from Anthropic skills.
$ git clone https://github.com/appautomaton/document-SKILLs.git▲ +141 ★ this week
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
▲ +86 ★ this week
The keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your other agents. Free, open source, Mac. 口喷鸡：Agent 时代的输入法。
Vision & image analysis skill for Claude Code & Codex. 帮不能看图的模型看懂图片和视频。
AI-Native document parser: PDF, Office & images → clean Markdown with LaTeX, tables & OCR. Zero-dependency CLI & skill for Claude Code, Cursor & AI agents.
Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, and AI-enriched metadata from research papers and books. Generate PRDs, workflows, topic clusters, and Claude Code skills from PDFs. No OCR required.
▲ +26 ★ this week
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Data from GitHub · snapshot Nov 13, 2026