6 results
低成本视频理解工具：B站链接/BV/本地视频 → 信息层（ASR+场景+对象轨迹+YOLO）→ 摘要+问答。问题驱动动态路由分层（L0/L1/L2）、语义层复用、预算上限。采用 Python 引擎：核心层需 faster-whisper / opencv / yt-dlp（约 200-300MB），可选语义层另需约 2GB 的 torch / transformers / ultralytics，内置 doctor --fix 一键建 venv 并装齐两者。
生物信息学「许愿式分析」插件：Python 执行器（bio_python：Biopython 全功能 + 出版级绘图）+ 48 个高频语义化工具（差异表达/GSEA、代谢建模/FBA、合成生物学设计、CRISPR、ML、文献检索等）+ 47 个 skill（1 主 skill + 17 领域配方 + 17 协议 + 4 研究方法 + 8 agent 指南）+ 零依赖自举 Python 环境（uv+venv 自动下载到插件私有目录）。用户下载安装即可许愿式分析。
DSH package manager plugin: install dsh-bundle plugins as profile dependencies and hot mount/unmount their bundle patch rows through the official watchUserPatches cordis.patch.yml reload path — no restart, no workspace/.venv second pipeline.
DSH-native uv environment manager with pip fallback and conda visibility
Shadow-replaces the built-in glob tool: auto-excludes bottomless directories (node_modules, dist, build, .venv, ...) and requires an explicit include whitelist to search inside them.
Per-project runtime environments for DeepSeek Harness: auto-adopt or create a project-local Python venv (.venv_local/python) and wire in the toolchains/env vars for the runtimes each project uses.