스킬 · DeepSeek Harness 플러그인 — 28 페이지

Adobe Lightroom Classic for DeepSeek Harness (dsh) — mounts the lightroom-py MCP server as native dsh tools. Pure-config bundle inside the lightroom-py repo; the Python package comes from PyPI (pip install lightroom-py).

Academic literature search, citation and BibTeX tools for DeepSeek Harness and any agent (Crossref + OpenAlex + Semantic Scholar).

Loom (织机) — second-validator plugin for DeepSeek Harness: a silent external coach that weaves your agent's tools, skills, config and even its model from usage history, with deterministic verification and cold-apply.

Media the agent can actually work with: media_probe (ffprobe's reading of any image, video or audio file, translated into a report and a browser-playability verdict with the exact ffmpeg command that would fix it), media_run (a real ffmpeg or ffprobe command as an ARGV array - no shell, a deadline, an output cap, and no overwrite unless asked), and media_frames (frames out of a video at named timestamps, sampled evenly, or tiled into one contact sheet). Ships the pin for a static ffmpeg/ffprobe copy per platform (SHA-256 verified, installed into $DSH_HOME/dsh-media/bin on first need, used only when the machine has none of its own), two bundled skills (ffmpeg-cli, ffprobe-cli), and the host routes dsh-video's tab reads: a Range-capable file stream, the same probe summary as JSON, and a background remux/transcode that turns a container a browser cannot open into a cached MP4.

Move your whole Claude Code setup into DeepSeek Harness (DSH) with one command - skills, MCP servers, hooks, instructions. 从 Claude Code 拎包入住 DSH。

DSH 插件：零侵入运行事实遥测——纯观察者（零工具注册/零 LLM 调用），session 结束时自动把任务/模型/工具/失败/状态/时长按一行一会话写入观测卡，附自动统计汇总区与 raw sidecar。Zero-intrusion run-fact telemetry for DeepSeek Harness: one row per session in the observation card + auto stats + raw sidecar.

配置打包器（Agent config packer for DeepSeek Harness）：把本地 Agent 资产（Skills/会话/Profile/设置/记忆）按模块打包成 zip——迁移、分享、恢复、差异对比、隐私安全扫描，全部可选。v0.2.5：记忆模块语义澄清（包内只有 Markdown 镜像，运行时 SQLite 真库不在包内；中英 README 增「记忆怎么迁移」）+ 客户端 bundle 迁入 lib/；全链路异步 IO（fs/promises + execFile，不再阻塞事件循环，对外 API 一律返回 Promise）+ /packer/api/* 防护（鉴权默认 fail-closed：只用官方 connection.requestRejection，拿不到就 403；请求体上限 8MB 与速率限制 60 次/分钟在完整缓冲请求体之前判定；错误文案脱敏）、测试补齐；v0.2.3：恢复安全加固（目标路径 containment / 缺指纹 fail-closed / 备份+原子替换+失败回滚 / tar 成员白名单 / SQLite 库默认排除）+ 隐私扫描补齐（Unix 与 UNC 路径、无引号密钥与密钥形状、全量计数、无扩展名文本）+ peerDependenciesMeta 标记宿主内建 peer 为 optional；v0.2.2：管理面板按打包工作流设计语言（阶段流程条/器材面板/diff 色带/橙琥珀青品牌色）+ 深色适配（DSH 主题跟随）

PaddleOCR text-recognition and document-parsing skills with native DeepSeek Harness tools and GUI configuration.

Community DeepSeek Harness plugin that bundles the AntV chart visualization skill and a native chart-generation tool.

DSH 插件商店 + 安装排障技能一体包：Web GUI「插件商店」页签浏览插件目录（名称/介绍/原链接），一键触发安装；内置 dsh-plugin-installer 技能作为安装后端引擎。

Find DeepSeek Harness plugins from the dsh.so registry — like find-skill, but for dsh plugins.

Use raincode's model layer (cheap model pool, prompt caching, retry) and skill library inside DeepSeek Harness (dsh)

DeepSeek Harness plugin: complete Polymarket API coverage — market data tools, authenticated trading tools, WebSocket stream service, and an embedded Polymarket knowhow skill

DeepSeek Harness 0.2.1 系列兼容的提示词与宿主补丁插件：管理注入、规则集与 Skill，支持补丁应用/还原、密封 asar 自愈、会话回退和网络范围白名单。基于 YuJunZhiXue/dsh-purge 上游维护。

Record & Replay for the dsh web GUI: (1) replay every automatically recorded session as a readable timeline, export/import shareable replay packs, re-run a recorded conversation; (2) Codex-style screen recording -> skill generation - record a computer-use session in the browser (getDisplayMedia -> webm + sampled frames), replay it, and have an agent analyze the frames and install a generated SKILL.md into ~/.dsh/skills. Hot-pluggable - mounted via the profile patch layer, no dsh source changes.

Native s1 tools for the DeepSeek Harness (DSH), registered as first-class tools (s1_search, ...).

Context admission and disclosure layer for DeepSeek Harness: tool output admission, history forgetting, skill catalog disclosure

DSH Web panel for dsh-sieve: context reduction, judge status and ledger records

Microsoft SkillOpt-Sleep integration for DeepSeek Harness: give your dsh agent a nightly sleep cycle that harvests past sessions, replays recurring tasks, and consolidates validated skills behind a held-out gate.

The SKILLS BROWSER: one button immediately left of the page-zoom control in the conversation header opens a centered modal listing every skill the harness actually loads for this conversation - name, description, where it came from (project / user / custom / bundled / runtime), the provider that owns it, whether the model and the user may invoke it, and the absolute file behind it - and shows that skill's markdown as a RENDERED document on the pack's white Markdown page (the same MarkdownText primitive and the same data-document-markdown container the right bar's rendered Markdown view uses, so it reads as a document in either app appearance), with the source - frontmatter included - appearing only once Edit swaps the page for the textarea and a Save that goes back through this plugin's own authenticated route. The catalog is the HOST's: ctx.skills.snapshot() is the same registry the system prompt and the / menu read, so the modal cannot disagree with what the model was given. A file-backed skill is editable here (the client never names a path: it names a skill, and the host writes the file the registry itself resolved, atomically, with an mtime/size guard so a save cannot clobber a concurrent edit); a skill registered at runtime without a file is shown from its loaded content and is honestly read-only. No core patches, no fork, no npm dependencies.

DeepSeek Harness 原生 AI Agent 技能集市与多技能中文意图批量调度插件

DSH 仓库技能市场管理器:按 仓库地址+分支+稀疏路径 拉取插件/技能,安装进 ~/.dsh/skills,在设置页以插件维度管理

Questionnaire-style survey plugin for DeepSeek Harness: the do_a_survey tool asks 1-10+ questions at once (single/multi/yes-no/compare/open types) in four presentation modes (compact/inline/overlay/grid), with per-question skip, full Markdown & color rendering, and a two-column recap after submit. Bundle form resident in the Web profile; companion skill ships a dynamic-plugin fallback recipe.

题庄中小学 K12 真题检索、免费抽题、练习测验与智能组卷 DeepSeek Harness 插件。