zhu1090093659/dsh-web#packages/dsh-skill-explorer
Skill center for the dsh web GUI: browse all loaded skills grouped by source, enable or disable model invocation, create new skills, and delete into a recoverable trash.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via npm
Resolves a published tarball rather than cloning the repository.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 6d agoon DeepSeek Harness 0.2.1-rc.5.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.1-rc.5, 6d ago.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
Neither shell commands nor credentials.
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — Groups loaded skills by source in the DSH Web GUI, with toggles for model invocation, creation, and deletes that land in recoverable trash.
Who it is for — You work in the DSH Web GUI with agents, skills already loaded, and you need the UI to decide whether the model may invoke them. If your workflow never leaves the terminal, skip it; you will not hit this surface.
Watch out — Install on a fresh profile succeeded, and the harness registered it into the profile. No obvious pitfalls found.
The verdict — I would spend the plugin slot only while the skill list still changes in the GUI; a freeze-it-and-forget-it setup does not earn the slot.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
dsh-skill-explorer is a DeepSeek Harness plugin that provides a skill centre for the DeepSeek Harness web GUI. It shows all currently loaded skills, groups them by source, and exposes controls for whether each skill may be invoked by the model. The web interface also supports creating new skills and moving deleted skills into recoverable trash rather than removing them without a recovery path.
DeepSeek Harness presents dsh-skill-explorer as a management surface for the skills already available to an agent. This is intended for developers who need to inspect the loaded skill set, adjust model-invocation availability, add skills, or remove skills while retaining the option to recover them. The supplied documentation does not describe a separate command-line interface, configuration file, API, storage path, or implementation hook for these operations; the documented interaction is through the web GUI.
dsh-skill-explorer is not the right choice for an installation that does not use the DeepSeek Harness web GUI, or for users who only need to run existing skills and do not need skill administration. It should also not be treated as a general-purpose skill runtime: the documented scope is browsing and managing loaded skills, not defining how individual skills execute.
DeepSeek Harness exposes dsh-skill-explorer through the web GUI. The supplied documentation does not specify configuration keys, defaults, environment variables, file paths, or a separate API for the plugin. No additional configuration is described beyond the skill-management controls in the interface.
DeepSeek Harness displays all loaded skills in groups arranged by source. From this skill centre, dsh-skill-explorer documents four management operations:
The model-invocation control concerns whether the model can call the selected skill. The documented deletion behaviour places the skill in recoverable trash, rather than describing an irreversible deletion. The README does not define the recovery workflow, trash retention period, or the fields required when creating a skill.
DeepSeek Harness loads this plugin as part of the web GUI plugin setup. The repository supplies the package installation command separately, but this reference does not repeat it. The README does not state a minimum DeepSeek Harness version, supported operating systems, browser requirements, or compatibility details specific to dsh-skill-explorer.
The documented scope is skill discovery and lifecycle management in the web GUI. The README does not document command names, command arguments, configuration files, programmatic interfaces, or the underlying hook used to read and write skill data. It also does not describe how skills are stored, how sources are determined, or how recoverable trash is restored. These details should not be inferred from the plugin's visible controls.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
iflytek
Browse and search a SkillHub registry and manage local skill installation, updates, and removal inside DeepSeek Harness. Targets DSH 0.2.0-rc.2 and 0.2.1-rc.2; not yet compatible with 0.2.1-rc.3.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
chuspeeism
现代化可灵活嵌入的任务面板，支持 Codex、DeepSeek Harness
Installed cleanly when we ran it
QingYunA
Answers a question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled `am` CLI builds the page, with flow, sequence, tree, timeline and ER diagrams, tables and callouts.
Installed cleanly when we ran it
Alisa0808
Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
Installed cleanly when we ran it
zhuyansen
Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
Installed cleanly when we ran it
hyhmrright
Provides six code quality skills for code review, architecture audits, technical debt, test quality, health dashboards, and remediation.
Installed cleanly when we ran it
