DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Skill Studio — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins

dsh-skill-studio

Skill Studio

Skill studio for DeepSeek Harness: visualize all agent skills, view/edit their SKILL.md bodies, toggle model/user invocation, and mine session logs to extract reusable personal skills (auto-loadable by the agent) — from the web settings panel (Skill 工作台) and via skillmgr_* / skillmgr_extract_* tools

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add dsh-skill-studio@0.2.1
READMECompatibilityVersions

Compatibility and provenance

Skill Studio is published as dsh-skill-studio and currently resolves to version 0.2.1. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
9/11/2026

Versions

0.2.1stable
9/11/2026
0.2.0stable
8/29/2026
0.1.2stable
8/23/2026

Related plugins

Loading related plugins…

Latest
0.2.1
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
106.5 kB
Files
10
Surface
web
License
MIT
Source
npm
GitHub
★ 3
Weekly downloads
0
Last push
9/11/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in agents-orchestration.

Headless@deepseek-ai/dsh-headlessThe dsh one-shot bundle: a direct core Agent/Session runner over dsh-base with no Host, HTTP, or browser layerExperimental Agent Team Web Profile@deepseek-ai/dsh-experimental-agent-team-web-profileExperimental Web profile layer for Agent Teams Remote and UI pluginsSubagent Codex@deepseek-ai/dsh-subagent-codexOne-shot Codex subagent provider over the official app-server protocolSubagent Claude Code@deepseek-ai/dsh-subagent-claude-codeOne-shot Claude Code subagent provider over the official Agent SDK

README

dsh-skill-studio

English | 中文

Visualize, edit and manage DeepSeek Harness skills right from the web settings panel — list every skill DSH discovered, view its full SKILL.md, edit the body, and enable/disable model & user invocation with a switch.

Features

  • Skill 管理器 settings panel — 设置 → Skill 管理器: list every skill (name, description, source root, nested flag, model/user invocation state), open any skill to see its full body, edit the SKILL.md file in place, and toggle enable / model-invocable / user-invocable.
  • skillmgr_list — list all skills with source, nested flag and invocation state.
  • skillmgr_get — view one skill's full detail (body + path + policy).
  • skillmgr_save — save a full-body edit (frontmatter + markdown) back to the file.
  • skillmgr_policy — enable/disable a skill (enabled master switch, or per-interface modelInvocable / userInvocable).
  • Two merged catalogs: ① direct filesystem scan of the standard roots (project .dsh/skills / .agents/skills, user ~/.dsh/skills / ~/.agents/skills), expanding one level of nested bundles (e.g. ~/.agents/skills/superpowers/<name> — flagged 嵌套/nested), plus ② the official registry (ctx.skills) for runtime / bundled skills. The panel therefore shows every skill on disk even when the host-plane filesystem provider is disabled (the web architecture deliberately moves local discovery to per-agent presets).
  • Enable/disable is implemented with line-level frontmatter surgery on disable-model-invocation / user-invocable; all other frontmatter lines are preserved verbatim. Saves are picked up by DSH on rediscovery.
  • Read-only safety: only skills with a real file path (filesystem sources) are editable; runtime / bundled skills are shown as read-only. Routes are loopback-only.

Install

# local development
dsh plugin --profile web add link:/path/to/dsh-skill-studio

# after publishing to GitHub (repo tagged with the `dsh-plugin` topic)
dsh plugin --profile web add github:zhengjy01/dsh-skill-studio

Restart dsh web to activate. No build step — lib/ is plain ESM.

Usage

In the web settings page (设置 → Skill 管理器) you can:

  • browse the full skill catalog with source badges and invocation state;
  • click a skill to read its body and edit it (textarea) → 保存 writes the file back;
  • flip 启用 / 模型可调用 / 用户可调用 switches.

You can also just tell your agent:

列出所有 skill,并告诉我哪些被禁用了
帮我禁用 session-knowledge 技能

The agent will use the skillmgr_* tools.

Notes

  • The frontmatter name key must match the skill name (kebab-case); breaking the frontmatter format may cause DSH to skip the skill on rediscovery.
  • Editing is scoped to files the skill registry reports; the plugin never accepts arbitrary paths.
  • Zero runtime dependencies beyond the DSH peer packages.

License

MIT