AGENTS.md@.github/skill-evalA
AGENTS.md@.github/skill-eval from nvidia-ai-blueprints/video-search-and-summarization is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add nvidia-ai-blueprints/video-search-and-summarization/.github/skill-eval/AGENTS.md@git:20261023.6d3e7c3Pins git:20261023.6d3e7c3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- nvidia-ai-blueprints/video-search-and-summarization
- Path
.github/skill-eval/AGENTS.md- Versions recorded
- 10
- Latest version
- git:20261023.6d3e7c3, committed Oct 23, 2026
- First version recorded
- Aug 17, 2026
- Size
- 55,529 bytes
- Repository stars
- 1,968
- License
- Apache-2.0
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Skills Eval Agent — System Prompt You are the VSS skills-eval agent, invoked by `.github/workflows/skills-eval.yml` on a `vss-skill-eval-runner` self-hosted box. Two modes: - **Single-spec** (push to a `pull-request/<N>` mirror): the workflow's `plan` job has already diffed the PR and resolved it into one matrix leg per `(spec, platform)`. Your leg is handed exactly one `(skill, spec, platform)` via `EVAL_*` env — you evaluate that one `(spec, platform)` and post its one comment. See § "Single-spec mode" for the step overrides. - **Manual full-sweep** (`workflow_dispatch`): no diff; enumerate every spec on the picked skill(s). See § "Manual full-sweep mode". Your workspace is already checked out at the mirror head. You have `Bash`, `Read`, `Edit`, `Write`, `Glob`, `Grep`; no human is in the loop. Background/task tools are disabled — you drive harbor synchronously (§ "No polling"). The steps below describe the **full** flow (diff → … → comment). In single-spec mode step 1 is the plan job's job, not yours — you start at step 3 with the spec you were given. ## Per-leg scratch isolation (read before any path below) …
Read the whole file at its exact version.
How to install
mdr add nvidia-ai-blueprints/video-search-and-summarization/.github/skill-eval/AGENTS.md@sha256:46ab6c24188e71c4The line at the top of this page pins the label git:20261023.6d3e7c3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_mny7cifvqzhfk3md)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Aug 17, 2026 and Oct 23, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261023.6d3e7c3 latest | 2026-10-23 | 6d3e7c3 | 55,529 B | A | view · diff |
| git:20261015.0626912 | 2026-10-15 | 0626912 | 54,465 B | A | view · diff |
| git:20261014.4ebe00a | 2026-10-14 | 4ebe00a | 54,187 B | A | view · diff |
| git:20261008.d09f772 | 2026-10-08 | d09f772 | 53,663 B | A | view · diff |
| git:20260921.5dae882 | 2026-09-21 | 5dae882 | 52,649 B | A | view · diff |
| git:20260914.4ac059f | 2026-09-14 | 4ac059f | 52,438 B | A | view · diff |
| git:20260910.0fa6fe0 | 2026-09-10 | 0fa6fe0 | 52,151 B | A | view · diff |
| git:20260821.153066f | 2026-08-21 | 153066f | 51,676 B | A | view · diff |
| git:20260817.4173191 | 2026-08-17 | 4173191 | 54,652 B | A | view · diff |
| git:20260817.7829ab1 | 2026-08-17 | 7829ab1 | 54,596 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (55529 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 · 1,968 stars · license Apache-2.0 · pushed 2026-11-07 · branch develop
API
GET https://markdownregistry.com/api/v1/artifacts/art_mny7cifvqzhfk3md GET https://markdownregistry.com/api/v1/resolve?ref=nvidia-ai-blueprints/video-search-and-summarization/.github/skill-eval/AGENTS.md GET https://markdownregistry.com/api/v1/blob/46ab6c24188e71c4d73553aeae14a12fd854a7e6f5f54ba9f70f0ae712d30dc4
Your AI assistant 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.
Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.
More from nvidia-ai-blueprints/video-search-and-summarization
Every file in nvidia-ai-blueprints/video-search-and-summarization