16 skills found
ningzimu / codex-gpt-imageOpenClaw/Claude Code SKILL.md for gpt-image-2 via Codex OAuth, no OPENAI_API_KEY required
SylphxAI / pdf-reader-mcpGive your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.
Nlkomaru / codingoklch-based color palette and semantic token generator for design systems.
wuyoscar / GPT-Image2-SkillGPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
kitlau86 / agent-vision-mcpAn MCP server that gives non-vision LLMs the ability to "see" images. Plug in any OpenAI-compatible vision API (Gemini, Qwen-VL, OpenAI, or self-hosted) and your text-only model — like DeepSeek in Claude Code — can analyze screenshots, OCR text, read charts, and more.
ThisIsLittleSky / WaterPaper水论文skill一句话出论文：多角度选题、真实文献采集、大纲写作、降低AIGC率、降低重复率、绘制图表、DOCX交付
yintzuyuan / glyphs-info-mcpUnified MCP server for Glyphs handbook and API queries
Shaohan-He / deepseek-eyes给 DeepSeek 装上眼睛 — MCP Server + 通义千问VL, 剪贴板图片→视觉模型→文字描述 / Give DeepSeek the ability to see images via clipboard + Qwen-VL
KimYx0207 / AI-Coding-Guide-ZhClaude Code + OpenClaw + Codex 中文教程 | 39篇完整教程 + 1张速查卡 | 80万+内容量 | 1500+实操示例 | AI Coding / Agent 三线学习路径
pdfinn / oedmcpMCP server for Oxford English Dictionary 2nd Edition access
OranAi-Ltd / orangeo-ai-visibility-skillOpen-source GEO / AEO skill for AI visibility readiness: check robots.txt, llms.txt, schema, citation signals, competitor gaps, and buyer prompts
tody-agent / cm-exampleA template demonstrating the universal format compatible with Antigravity, Claude, Cursor, and OpenClaw.
ifmelate / document-reader-mcpUniversal MCP server for extracting text from various document formats and converts to .md file
stefans71 / documentOpen PI Harness Advanced V2 — modular extensions for local LLM coding workflows
oranguthang / documentAlien Soldier (J) source code (assemble with AS)
SemineChen / yueban-image-to-code像素级 750px 图片转代码与切图工作流。当 Codex 需要把当前选中的 UI 图片、截图、App/Web 设计稿、Figma 图片导出稿或设计长图转换为代码，并输出独立透明 PNG 切图资源时使用。适用于严格 1:1 等比例还原、画板宽度精确 750px、禁止自动排版优化、文本可编辑、简单图形原生矢量/代码化、图标和位图独立透明 PNG 提取，以及按矢量层、文本层、位图/图标切图三类模块独立验收的任务。
