daiuuuuuuuuuuuuu/visual-proxy
Claude Code skill — 给无视觉能力的 LLM（DeepSeek/o1/o3）外挂看图能力。Vision proxy for text-only LLMs, supports OpenAI/Anthropic/DashScope/Qwen3-VL.
Claude Code skill — 给无视觉能力的 LLM（DeepSeek/o1/o3）外挂看图能力。Vision proxy for text-only LLMs, supports OpenAI/Anthropic/DashScope/Qwen3-VL.
npx add-skill daiuuuuuuuuuuuuu/visual-proxyClaude Code skill — 给无视觉能力的 LLM（DeepSeek/o1/o3）外挂看图能力。Vision proxy for text-only LLMs, supports OpenAI/Anthropic/DashScope/Qwen3-VL.
Automate penetration testing tasks with an LLM-driven multi-agent framework designed for security assessment.
Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
skills i built using claude
Marketplace-managed Claude Code skills for research, writing, slides, and Typst authoring.
🚀 Build and explore multi-agent AI workflows with ready-to-use projects for document serving, Q/A bots, and orchestration.
Claude Code skill for generating technical design docs with ASCII diagrams, API references, and runnable code examples. Bilingual support (Chinese/English).