vss-search-archive skillA
vss-search-archive is agent-read markdown (skill) from nvidia-ai-blueprints/video-search-and-summarization: Use this skill when a user wants to search archived VSS video or ingest or delete a source for search. Do not use it for visual Q&A, live captioning, or video summarization..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
## Purpose Operate archive search from the caller's host. Compose and Kubernetes use the same `vss configure` and `vss search run` commands; only the deployment origin differs. Source ingestion and deletion are Agent-backed **when the deployment has an agent `/api` route**; on a build without one, they belong to `vss-manage-video-io-storage` `references/provision-vios-source.md`. ## Hard boundaries - Run the project-local CLI on the host. Never use `docker exec`, `kubectl exec`, a pod shell, or a globally installed `vss` as a substitute. - Never improvise a mutation against Elasticsearch, RTVI-CV, RTVI-Embed, storage-ms, or VST. Two paths are sanctioned, and the deployment picks which: the Agent upload/delete lifecycle where an agent `/api` route answers, and `vss-manage-video-io-storage` `references/provision-vios-source.md` where none does. That recipe owns VIOS registration and the hand-driven RT-VLM legs; nothing sanctions a direct call to RTVI-CV or RTVI-Embed, which receive every source from VIOS. - Never remove, broaden, or silently substitute a requested source constraint. - Similarity is retrieval evidence, not proof of visual presence. …
Read the whole file at its exact version.
How to install
mdr add nvidia-ai-blueprints/video-search-and-summarization/vss-search-archive@v3.3.0mdr add nvidia-ai-blueprints/video-search-and-summarization/vss-search-archive@sha256:63338cd37aab59d2Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_p3y5z5jsd4e7cmjx)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v3.3.0 latest | 2026-09-23 | 9a91f6b | 13,568 B | A | view · diff |
| v3.3.0 | 2026-09-23 | 302e11a | 13,237 B | A | view · diff |
| v3.3.0 | 2026-09-18 | 72972f5 | 13,512 B | A | view · diff |
| v3.3.0 | 2026-09-16 | 1ea1d64 | 13,407 B | A | view · diff |
| v3.3.0 | 2026-09-14 | 4ac059f | 13,084 B | A | view · diff |
| v3.3.0 | 2026-09-14 | 256ae38 | 13,064 B | A | view · diff |
| v3.3.0 | 2026-09-07 | 3e4ccbc | 13,123 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13568 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
nvidia-ai-blueprints/video-search-and-summarization · 1,876 stars · license NOASSERTION · pushed 2026-09-24 · branch develop
API
GET https://markdownregistry.com/api/v1/artifacts/art_p3y5z5jsd4e7cmjx GET https://markdownregistry.com/api/v1/resolve?ref=nvidia-ai-blueprints/video-search-and-summarization/vss-search-archive GET https://markdownregistry.com/api/v1/blob/63338cd37aab59d2d131ed625fca3abde20c84b44467e7eab9c6f7ee886002b2
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from nvidia-ai-blueprints/video-search-and-summarization
Every file in nvidia-ai-blueprints/video-search-and-summarization