DSH专用，这个工具不同于传统的AI理解视频流程（定时切帧-切出的帧猜测上下文），而是以5-15FPS一帧来尽可能获取视频的内容，再以网格的形式存入每一帧；网格使用预训练模型进行分组（相同的场景/内容会尽可能在一个网格大组中），这样你的AI在使用了这个插件/工具后能够更好的形容看到的视频，并且不会花什么token；我接下来会在缩短完成这个流程所需要的时长上做努力（目前中端手机在OCR与ASR全开启的情况下让AI完成一个这样的工作流时长需要原视频的1.5倍～3倍左右），解决这个工具最大的痛点。
Install verification: No L4/L5 install test yet
Data as of (UTC)
What it does
DSH专用，这个工具不同于传统的AI理解视频流程（定时切帧-切出的帧猜测上下文），而是以5-15FPS一帧来尽可能获取视频的内容，再以网格的形式存入每一帧；网格使用预训练模型进行分组（相同的场景/内容会尽可能在一个网格大组中），这样你的AI在使用了这个插件/工具后能够更好的形容看到的视频，并且不会花什么token；我接下来会在缩短完成这个流程所需要的时长上做努力（目前中端手机在OCR与ASR全开启的情况下让AI完成一个这样的工作流时长需要原视频的1.5倍～3倍左右），解决这个工具最大的痛点。
Installation
dsh plugin --profile web add github:yangjili6/video-understanding-kitInstall method: GitHub · no verification record (L1-L5)
Verification & Compatibility
No verification record yet for this plugin.
- • Node.js: not stated
- • DSH: not stated
- • External credentials: none detected
Author badges
Embed the dsh.so badges in your README to show this plugin's automated security-scan and install-test status:
`[](https://www.dsh.so/artifact/video-understanding-kit/?ref=badge)`dsh.so is an independent community project, not affiliated with or endorsed by DeepSeek AI. Badges are maintained by dsh.so; embed links carry a ?ref= attribution parameter.
Security Report
Two automated layers, neither a manual review: a static scan (per-plugin rule checks) and a model-driven dynamic security audit that covers only the subset static-flagged at warn or above and never executes plugin code.
Static n/a; dynamic no conclusion (static stands) → overall low.
——v0.1.9The scan result is valid for the scanned commit. New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.
not in the dynamic queue (the queue only covers plugins whose static tier is medium or above — medium/high/critical; since 2026-10-24 entries rated low are not audited even when dsh-only rules logged warnings) — this does not mean the dynamic audit found it safe.
Rule (2026-10-28): when a dynamic conclusion exists it is authoritative (it may raise or lower the level); the static scan tier (vet primary, dsh backstop) applies only when there is none (not queued / audit failed / withdrawn). The audit never writes the exemption list (exemptions are manual only); a wrong conclusion is withdrawn by human review and the tier falls back to the static scan tier.
Disclaimer: the static scan and the dynamic security audit are both automated analysis, not a security guarantee. Always review what you install.
Activity
Last commit 2026-11-01 · activity: Active
• Repo created: 2026-10-19
• Stars: ★ 1 · Forks: 0
• Health: Active — committed within last 30 days
Source
Author README
View on GitHub ↗The author's original README from the repository — fetched live, unedited (the English page loads the default README).
Frequently asked questions
What is @yangjili6/video-understanding-kit?
@yangjili6/video-understanding-kit is a DeepSeek Harness (dsh) plugin listed on dsh.so — an independent community registry that indexes public source repositories and publishes automated security-scan and install-verification results for each entry.
Is dsh.so or this plugin page official?
dsh.so is an independent community registry and is not affiliated with, endorsed by, or sponsored by DeepSeek AI.
How do I install @yangjili6/video-understanding-kit?
Run dsh plugin --profile web add github:yangjili6/video-understanding-kit in a DeepSeek Harness (dsh) environment. The command is parsed from the plugin manifest, but its install spec is not verified yet (L3); sandbox install and runtime testing have not passed.
How does the security scan relate to a manual audit?
Both layers are automated, not a manual audit. The static scan is heuristic analysis of the repository source, so it can produce false positives and miss context. The model-driven dynamic security audit only covers plugins static-flagged at warn or above, never executes plugin code, and its conclusion is authoritative when there is one (it may raise or lower the static tier); exemptions stay manual. Neither layer is an endorsement: review the repository and the permissions it asks for before installing, together with the verification level and health signals.
How fresh is the data on this page?
The data on this page is as of 2026-11-01 (UTC) — the most recent valid timestamp among the registry refresh, install verification, security scan and dynamic audit. Build time is never used as a data date.