detection-training SKILL.md skillA
detection-training from nebius/nebius-physical-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nebius/nebius-physical-ai/detection-training@git:20260906.2c32550Pins git:20260906.2c32550 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nebius/nebius-physical-ai
- Path
skills/tools/detection-training/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260906.2c32550, committed Sep 6, 2026
- First version recorded
- Aug 17, 2026
- Size
- 9,052 bytes
- Repository stars
- 106
- License
- Apache-2.0
Use to train and evaluate Faster R-CNN detectors from LanceDB materialized views (BDD100K failure-mode slices) — direct versus deployed-service execution, the mandatory label map for string categories, and checkpoint discovery at eval time.
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
# Detection training (LanceDB view → Faster R-CNN) This tool trains an object detector on a **slice** of a dataset rather than the whole thing. The input is a LanceDB materialized view, which is what makes the failure-mode workflow possible: curate a view of nighttime frames, or distant objects, or riders, then train and evaluate only on that slice. Upstream is `skills/tools/lancedb/SKILL.md` — create the view with `npa workbench lancedb create-mv` / `refresh-mv` before anything here. The end-to-end pipeline is `workflows/testing/bdd100k-pipeline.yaml`, with a walkthrough in `docs/workbench/cookbooks/bdd100k-pipeline.md`. ## Two execution modes Direct (the default) runs the work from your CLI invocation. Service mode calls a deployed Kubernetes endpoint: ```bash npa workbench detection-training train --view <mv-name> --output-uri s3://<bucket>/runs/<id>/ npa workbench detection-training train --view <mv-name> --service --endpoint <url> ``` Deploy the service only when you want a persistent endpoint several runs share: ```bash npa workbench detection-training deploy \ --project <alias> --cluster-name <name> \ --input-path s3://<bucket>/lancedb/<db>/ \ …
Read the whole file at its exact version.
How to install
mdr add nebius/nebius-physical-ai/detection-training@sha256:8051a8b3ac33a964The line at the top of this page pins the label git:20260906.2c32550, 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_5jn3nggsefojxmc7)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 17, 2026 and Sep 6, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260906.2c32550 latest | 2026-09-06 | 2c32550 | 9,052 B | A | view · diff |
| git:20260906.525ee24 | 2026-09-06 | 525ee24 | 5,713 B | A | view · diff |
| git:20260823.224d9da | 2026-08-23 | 224d9da | 5,733 B | A | view · diff |
| git:20260817.be3cf06 | 2026-08-17 | be3cf06 | 5,598 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 (9052 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
nebius/nebius-physical-ai · 106 stars · license Apache-2.0 · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5jn3nggsefojxmc7 GET https://markdownregistry.com/api/v1/resolve?ref=nebius/nebius-physical-ai/detection-training GET https://markdownregistry.com/api/v1/blob/8051a8b3ac33a9640807f433f49dc45a76cda8c61a908b48d2bf365ca9e6aa81
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: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.