guobinmengxiang-rgb/dsh-xhs-note
guobinmengxiang-rgb★ 0JavaScript最后同步: 2026-08-16
DSH plugin: format Xiaohongshu notes. Don't pip the wrong dsh.
README 摘要
dsh-xhs-note Format a Xiaohongshu note (title max 20 Unicode code points) as a DeepSeek Harness tool. Do not pip the wrong dsh. GitHub topic: dsh-plugin. Chinese: README.zh.md Try without dsh node demo.mjs Prints the sample title and the course URL. Install into a profile This package is plain JavaScript. There is no prepare or build step, so a git install does not need allowBuilds. dsh plugin --profile web add github:guobinmengxiang-rgb/dsh-xhs-note Check the composed layer without booting: dsh --profile web --dump-config You should see a dsh-xhs-note layer. Then start the profile as usual. Official CLI is @deepseek-ai/dsh (today 0.1.0-rc.6). The PyPI package deepseek-harness-cli is a different tool (dsh doctor / dsh chat). Honest limits - npx may not load local overlays. The course overlay in dsh-getting-started still needs an absolute path to a TypeScript file. - This bundle cordis.patch.yml uses the package name dsh-xhs-note, not a filesystem path. - DeepSeek Harness is a developer preview: THERE WILL BE COMPATIBILITY-BREAKING CHANGES. - The plugin runs on your machine. Tool - Plugin export name: format-xhs-note - Tool name: format xhs note - Inject: tools - Title rule: Unicode…
在 GitHub 查看完整 README →分类
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
★ 2,208
Anionex/agent-vision-toolkit为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
★ 933
Anionex/dsh-vision-toolkit让纯文本模型更好地做视觉任务的DeepSeek Harness插件:带意图的图片问答、长截图 OCR、UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
★ 488