better-lvgl-for-dsh
LVGL 8.4 knowledge skill pack for DeepSeek Harness (dsh): registers an offline LVGL 8.4 skill library on ctx.skills so the agent writes correct v8 API code and avoids v9 confusion.
187 results
LVGL 8.4 knowledge skill pack for DeepSeek Harness (dsh): registers an offline LVGL 8.4 skill library on ctx.skills so the agent writes correct v8 API code and avoids v9 confusion.
Conversation-local credential handoff that writes through the DSH credential service without returning the secret to model context.
DeepSeek Harness plugin: track todo_write progress and pop native desktop reminders (bottom-right).
Automatic cross-session GoodMemory recall and writeback for DeepSeek Harness
虾说 — DSH 创作者 AI 工作台插件:首页项目管理 + 课程/公文/小说/论文/自定义多类型 + 可编辑工作流 + 九阶段门禁式流程 + 知识图谱 + 资料库注入 + 本地导入 + AI 润色 + 教案诊断,开箱即用。
DSH bundle: Xiaohongshu (RED) viral-note agent skill — hot-note research, note generation/rewrite, verification, authorized account analysis, QR login and controlled publishing, shipped as a bundled skill provider. Zero-dependency.
Durable layered memory (global / user / project / branch / daily), confirmation-gated writes, todos and skills. Preserves ~/.dsh/memories files in place with in-place adoption, SHA-256 verified backup and rollback.
Task dispatcher for DeepSeek Harness: use TickTick (滴答清单) as the daily task dispatcher — a cordis timer pulls today's due tasks, writes them to the workspace task file, and notifies (WeChat via ClawBot / flomo / macOS) so the agent works through them and writes results back to TickTick
A microphone button for DeepSeek Harness that writes browser speech recognition into the composer draft.
DSH web plugin: a draggable ring-gauge dashboard pinned to the bottom-right that shows live model output speed (tok/s), with an expandable detail panel (per-step exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).
禁止在 edit/write 写入内容中使用匹配正则的字符,extraTools 可额外配置拦截更多工具。可在 cordis 配置文件里配置正则与报错文案。host 单半身。
DSH profile plugin: unconfined (GPU-capable) session sandbox plus per-operation user approval for writes outside the workspace or to protected files.
DSH web plugin: search and read an Outline knowledge base from conversations, with approved, whitelist-guarded document writes.
A dsh policy plugin that gates kubectl writes by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.
DSH Notion skill: read and write Notion workspaces via the official REST API
DSH sandbox extension: protect declared workspace subpaths (e.g. .git) from writes, and optionally grant extra writable roots under workspace-write, enforced for sandboxed CLI commands and the write/edit tools. 为 DSH 沙箱增加工作区子路径只读保护, 并支持在 workspace-write 下声明额外可写根.
Codex-style per-session memory draft for DeepSeek Harness: one session one draft (rollout_summaries), restrained & passive (write only on explicit user request), layered disclosure (summary + registry), idempotent integration watermark. / 一会话一草稿记忆插件。
禁止 write 覆盖已存在的文件:write 只允许创建新文件,目标已存在时在工具执行前直接拒绝并提示改用 edit,全局所有会话生效,防止模型用 write 整体覆写已有内容。纯 host 端 dsh 插件。
DeepSeek Harness tool: read/write the Windows clipboard from WSL.
Manual budget-targeted context compression for DeepSeek Harness: the conversation model picks ranges, a cheap flash-tier route writes the checkpoint summaries.
鐧诲綍鎬佹祻瑙堝櫒浠g悊:browser_* 宸ュ叿鏃忔搷绾典綘宸茬櫥褰曠殑鐪熷疄 Chrome/Edge,170+ 绔欑偣閫傞厤鍣ㄧ粡 site 宸ュ叿鍗冲埢鍙敤,缂洪€傞厤鍣ㄥ彲浼氳瘽鍐呰嚜鍒涗綔;write 鍛戒护甯﹀鎵归棬
DeepSeek Harness plugin: SiYuan (思源笔记) integration — host-side siyuan_* tools for search/read/write plus a dedicated settings page in the Web client.
Noname (无名杀) extension workshop for DeepSeek Harness: AI writes skills/cards with official-reference search, validation-gated writes, task history, and a web workshop panel.
模型可见的远程文件工具 read_remote、write_remote、edit_remote,经 ssh 读写远程主机文件。write_remote 只允许新建,绝无覆写分支;文件后端 RemoteFileSystem 不继承 FileSystem,仅借用 @deepseek-ai/dsh-fs 的类型词表与 FsError。标准可安装的 dsh host 插件。