识别图片内容。当用户发送图片、截图、报错图,或要求分析某张本地图片时使用。先定位图片文件路径,再运行 vision.py 脚本获取文字描述。
DDDFXYqiming/Agent_Resources
SkillsMP 已收集 DDDFXYqiming/Agent_Resources 中的 6 个 Skill。打开任一 Skill 可查看来源和详情。
- 最近记录的来源活动
- SkillsMP 收录数据更新
- 已收集 skills
- 6
- GitHub 星标
- 2
- GitHub Forks
- 0
已展示 6 / 6 个已收集 Skill。
AI-driven multi-format SVG content generation system. Converts source documents (PDF/DOCX/URL/Markdown) into high-quality SVG pages and exports to PPTX through multi-role collaboration. Use when user asks to "create PPT", "make presentation", "生成PPT", "做PPT",…
原文语言:多语言混合
Apply ericwarn丁宁's 市赚率(PR) investment methodology: PE/PB/ROE valuation, PR three formulas, dividend-payout correction, 0.4/0.5/0.6PR buy zones, A/H tax differences, red-dividend ETF rotation, and Buffett case studies. Use when the user asks about…
原文语言:多语言混合
Use when applying or explaining the investment methodology from the 40-video Bilibili corpus: technical chart analysis, ETF timing, support/resistance, EMA tunnel, KDJ/MACD/Bollinger/Fibonacci rules, volume-amount validation, and risk vetoes. Produces…
原文语言:多语言混合
Use when controlling Windows native desktop apps or real-browser sessions with GenericAgent-style code_run: dynamic Python execution, Win32/UIA/OCR/screenshots/CDP, and observe-act-verify loops.
原文语言:多语言混合
Use when user wants to summarize, analyze, or generate notes from a video URL. Converts video content into structured Markdown notes with timestamps, extracted visual frames, native multimodal image observations, and AI summaries. Supports Bilibili, YouTube,…
原文语言:多语言混合