AI Agent Skills

daily notes

Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414

为短剧人物、造型、地点、道具和状态编写或修改可直接复制的图片提示词 Markdown。用户提到角色设定图、三视图、参考图、场景板、道具图、风格帧、Look Development、状态变体或局部编辑提示词时使用；不生成图片，也不调用供应商。

Secure AI conversations with documents, video, audio, and more. Personal workspaces for focused context, group spaces for shared insight. Classify docs, reuse prompts, a…

ComPDF SDK for Android — a full-featured PDF library offering comprehensive code samples and integration guides. Build robust PDF viewers and editors on Android with sup…

PDF generation with JSX. Page breaks that actually work.

Mmark: a powerful markdown processor in Go geared towards the IETF

一句话需求也能做成像样 PPT：先问清受众、场景和风格，再整理本地资料，生成可编辑 PPTX/Web Deck，并用 GPT 生图、渲染审阅和审计留痕守住真实办公成稿。

Generates VSS video summary reports with LVS HITL and optional Enterprise RAG document grounding. Trigger when the user asks for a frag/RAG-assisted video report, knowle…

Papermerge DMS core backend, REST API server, and frontend UI

Enhanced PDF view for Flutter.

Ask questions and get answers from earnings calls, SEC filings and news

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "explorator…

Create Python API documentation in Markdown format.

Copy AI conversations as clean Markdown Context Bundles — one click from ChatGPT, Claude, Gemini, DeepSeek, Grok & GitHub. Copy from sidebar without opening. Zero upload…

Archive session learnings, debugging solutions, and deployment logs to .archive/yyyy-mm-dd/ as indexed markdown with searchable tags. Use when completing a significant t…