Plugins

Context compression skill for DeepSeek Harness -- intelligent conversation summarization

Rename project conversations into clear, content-based Category｜Topic titles.

DeepSeek Harness bundle for Amber Protocol governance tools and skills

Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets

Design I/O for coding agents: controllable UI generation via declarations (spec/domain/craft/design/components/template) and contracts (skill/evaluator). Use for product UI—console, dashboard, agent-ops, CJK-first apps.

Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell, and credential leaks.

Auto-inject user-chosen skills (e.g. caveman, ponytail) into DeepSeek Harness sessions.every prompt or once at session start.

Development kit for DSH plugins: a skill stating the contract lookup order (runtime inspect, then the bundled dsh-doc copy, then a working plugin source) and two check scripts — preflight verifies a plugin project against four install-failure families before packing, recheck re-tests declared host touchpoints after a DSH upgrade.

Tracks the DSH config repo against the copy on this machine (files changed, commits ahead or behind, sessions and skills not captured yet) and generates push, pull and restore scripts that run after the client exits. A blocked pull backs up both sides of every conflicting file so one side can be picked per file; every apply snapshots the profile first, and any snapshot can be restored later. Windows only: the generated sync scripts are PowerShell.

Share selected theme settings, installed plugins and skills by QR code, then review and install them together from an image or screenshot. The QR code carries the install manifest only; larger skill and plugin files are downloaded from the sources it names, so a code from someone else makes your Harness fetch and install from their source.

Syncs DSH skills, profile settings and AGENTS.md with a private git repository: status chip, six-section health check, pull, secret redaction, and a snapshot-then-push flow. Dry-run by default, never rebases or force-pushes.

Skill manager for DSH: drag rows into the order you want, pin any row straight to position 1, and rename a skill inline. Applying rewrites each directory name and the name field in SKILL.md. A skill that appears later is numbered and cleaned up automatically, and a description past 20 Chinese characters gets rewritten. Every change clears the host skill cache and notifies each session, so the slash menu follows at once without restarting DSH. Local-only and offline. Its HTTP routes have no DSH access check, so a page open in your browser could trigger a rename or reorder of your skill folders.

Lazy senior coding ruleset for DeepSeek Harness: injects minimal-code guidance, adds review, audit, debt, gain and help skills, and switches lite/full/ultra per session. Ships a script to sync rules from a pinned upstream commit.

Captures verified project work as masked evidence and reviewable skill proposals; accepted skills become native project skills with version history, diff, rollback, and opt-in global publishing.

Shows and loads Qwen (qianwen*) skills only when the session runs on the Qwen Token Plan CN provider, and hides and blocks them on any other provider.

Registers 36 bundled agent skills (research writing, LaTeX, experiments, design review, office documents, animation, Windows shell and dsh plugin conventions) as one host-only skill provider with no UI, no network calls and no telemetry of its own; skill scripts run with the user's permissions only when invoked, local skills of the same name take priority, and uninstall removes all 36.

Bundles the stack-diagram architecture-diagram skill as a runtime skill, and injects a system-prompt section so the model draws diagrams without being asked. Output is self-contained HTML plus light and dark PNGs from bundled Python scripts; brand logos are fetched at run time.

Registers a skill that turns a Bilibili video link into a structured Obsidian note. It fetches subtitles only with yt-dlp and never downloads the video, merges multi-part anthologies onto one continuous timeline, and writes front matter, timestamped jump-link bullets, a summary and tags into the vault.

Back up and restore a whole DSH environment (installed plugins, DSH and plugin settings, skills, sessions and explicitly registered workspace files) into one private GitHub repository. Multiple machines share a single repo through per-device namespaces that never overwrite each other, and a pull can restore from this device, the latest backup or a chosen device. Push previews a read-only plan before writing, pull backs up local data first, secret-looking settings are redacted and key files are never uploaded. It calls api.github.com with the GitHub token you save in the panel (kept host-side only); its HTTP routes (/one-pack/api/...) require DSH browser auth.

A fastfetch-style system and DSH panel: one slash command (/fastfetch or /ff) and one simple agent tool render OS, kernel, host, CPU, GPU, memory, every disk and local IP address, plus DSH version, model, session mode, plugin and skill counts into a colored terminal card, with a settings page that edits every field.

Every few turns asks the model whether anything is worth keeping, then sorts the answer into memory, skill or hook.

DeepSeek Harness sidebar for LiteLLM models, MCP servers, skills, and spend.

DSH 技能市场与 MCP 连接器市场：浏览实时技能源，一键安装 SKILL.md 技能与 MCP 连接器，装完即刻可用、无需重启。SKILL & MCP marketplace for DeepSeek Harness — browse live sources, install skills and MCP connectors, effective immediately.

A Windows Harness adaptation of [Media Review Skill](https://github.com/Ww-Cooooo/media-review) for AI video feedback: annotate frame regions or time ranges and jump to recognized speech or imported subtitle cues; other Agents with local file and command access can use the original Skill. Windows only and built for DSH 0.2.2-rc.1 (a 0.1.0 release candidate). Waveforms use an existing FFmpeg/ffprobe and transcripts an existing Whisper; without them, manual annotation and subtitle import still work.