dsh-skill-explorer
zhu1090093659
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.
Installed cleanly when we ran it
sandbaseai/sandbase-skills
Mounts 88 packaged research, social-intelligence, marketing and business Agent Skills into dsh through the filesystem Skill provider.
Install
via GitHub · GitHub source
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.
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 GitHub · GitHub source
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/desktop/pnpm-workspace.yaml.
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 yesterdayon DeepSeek Harness 0.2.2-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 0.2.2-rc.5, yesterday.
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.
shell commands (bash, exec, spawn …)
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 — Sandbase-skills plugin mounts research, social-intelligence, marketing and business Agent Skills into DeepSeek Harness through the filesystem Skill provider.
Who it is for — If you are building research or marketing workflows with DeepSeek Harness and need to supplement those domains with Agent Skills, you can install it. If your workflows already include all required research, social intelligence and business capabilities, you do not need to install it.
Watch out — Installing from GitHub source requires manually allowing the build script. Sandbox test passed: installed in a fresh profile and registered into profile. No obvious issues found.
The verdict — I would install it because it supplies repeatable workflow instructions that integrate directly with DeepSeek Harness.
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.

sandbase-skills is a DeepSeek Harness plugin that mounts a catalogue of packaged research, social-intelligence, marketing and business Agent Skills through the filesystem Skill provider. DeepSeek Harness loads the plugin’s packaged instruction files rather than a separate service: the repository keeps canonical Skills under research/ and marketing/, with DeepSeek Harness packaging and install metadata under dsh/. Each Skill defines a repeatable workflow, evidence rules and an output format.
The Skills can use capabilities already supplied by the host agent. For example, multi-source-search uses existing search and page-reading tools and includes an evidence-ledger example plus an offline validator. Specialised social, market and data workflows may use SandBase providers when SANDBASE_API_KEY is configured. The key must be set in the environment, not in a prompt or committed file.
The terminal-surface risk matters because these instruction files run inside an agent with access to its host-provided tools; review the Skills before granting that access. sandbase-skills is a poor fit when only a small, narrowly defined workflow is needed, when the agent has no suitable search or page-reading tools, or when the required SandBase providers cannot be configured.
DeepSeek Harness loads the packaged Skill instructions through the filesystem Skill provider. The repository’s canonical sources are research/ and marketing/; the DeepSeek Harness packaging and installation metadata are in dsh/. A Skill is an instruction file describing a repeatable workflow, evidence rules and an output format. The README describes a catalogue covering research, social intelligence, marketing, media generation, software engineering, data science and business workflows.
The flagship multi-source-search Skill uses the host agent’s existing search and page-reading tools. It includes a worked evidence-ledger example and an offline validator. The README does not document a separate runtime service for this Skill.
multi-source-search does not require a SandBase account when the host agent already provides search and page-reading tools. Specialised social, market and data-provider Skills can use SandBase providers when this environment variable is configured:
| Variable | Use |
|---|---|
SANDBASE_API_KEY |
Provides access to SandBase capabilities for applicable Skills |
Keep SANDBASE_API_KEY in the environment. The README says not to place it in a prompt or committed file.
Use npx skills use sandbaseai/sandbase-skills@multi-source-search to generate the complete prompt for the named Skill without installing it. GitHub CLI 2.90.0 or later can inspect a Skill with gh skill preview sandbaseai/sandbase-skills research/multi-source-search; replace the final path with another catalogue path.
The host agent must provide the tools required by a selected workflow. SandBase-backed workflows require the relevant provider configuration, including SANDBASE_API_KEY where applicable. The README does not specify a DeepSeek Harness version requirement or additional plugin configuration keys. The terminal-surface risk should be reviewed because the Skills operate within the agent’s available tool access.
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
zhu1090093659
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.
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
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
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