dsh-web is a plugin ecosystem that adds a web interface and optional tools to DeepSeek Harness, an AI development environment. It is used to provide features such as task boards, mobile remote control, SSH operations, image understanding, file and code panels, Git views, agent presets, and interchangeable skins through independently loaded plugins. The catalogue skills are plugins and related workflows for extending and operating the DSH Web environment.
Borrowing it
Nothing to install: this file belongs to zhu1090093659/dsh-web. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zhu1090093659/dsh-web/dev/.agents/skills/dsh-web-web-qa/SKILL.mdgit clone --depth 1 https://github.com/zhu1090093659/dsh-webWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zhu1090093659/dsh-web/dsh-web-web-qa)<a href="https://agentmods.dev/skills/zhu1090093659/dsh-web/dsh-web-web-qa"><img src="https://agentmods.dev/badge/skills/zhu1090093659/dsh-web/dsh-web-web-qa/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zhu1090093659/dsh-web/dsh-web-web-qa"><img src="https://agentmods.dev/badge/skills/zhu1090093659/dsh-web/dsh-web-web-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00428 |
| Opus 5 | $0.00020 | $0.00214 |
| Sonnet 5 | $0.00008 | $0.00086 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
dsh-web-web-qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Validating dsh-web in the Web GUI
Use the real DSH Web GUI and the profile that loads the affected bundle. This skill covers client-facing verification; it does not replace unit tests, host tests, or repository gates.
Prepare the actual runtime
- Build the affected plugin or skin through its documented package command. Run the focused unit tests and
pnpm runtime-deps:checkwhen client runtime imports changed. - Do not start a replacement standalone Vite application. The DSH Web shell requires its host boot data and must be verified through the existing DSH GUI.
- Confirm whether the documented HMR path applies. Otherwise refresh the real GUI after rebuilding and verify the loaded bundle is the changed one.
Exercise the user-visible behavior
- Use the application route and workflow a user actually reaches, not only an isolated component mount.
- Check the changed feature plus its expected empty, loading, error, disabled, and persisted states where they exist.
- Inspect at a desktop and a narrow mobile viewport when the surface is responsive. Verify text fits, controls remain reachable, and layout does not overlap or leave a blank panel.
- Check browser console errors and failed asset loads. For stateful or security-sensitive UI, exercise the relevant confirmation, failure, and cleanup paths.
- Capture a screenshot or other concise evidence when the change is user-visible. Close temporary browser task spaces after the verification unless the user needs the page left open.
Report evidence honestly
State the exact GUI URL or profile used, the build and reload path, the interactions exercised, and the observed result. If the environment cannot run the live GUI, report that limitation and the strongest non-visual evidence obtained.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 29 lines · 41 tokens per session scan A 15bd3269d7e8
dsh-web-web-qa is a skill published in the GitHub repository zhu1090093659/dsh-web (7,321 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 428 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
browser-qa
Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.
dsh-webapp-testing
Verify a local web application's rendered browser behavior with console, network, server, and focused regression-test evidence.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
daytona-windows-cert
Run the verified Windows repro for iPolloWork enterprise TLS behavior: install a fake corporate CA into the Windows machine store, serve healthy and broken HTTPS control planes, install a Windows build, and prove the desktop app and spawned runtimes use the operating system trust path.