tao-generate-image-grounding SKILL.md skillA
tao-generate-image-grounding from nvidia-tao/tao-skill-bank is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nvidia-tao/tao-skill-bank/tao-generate-image-grounding@v0.1.0Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nvidia-tao/tao-skill-bank
- Path
skills/data/tao-generate-image-grounding/SKILL.md- Versions recorded
- 6
- Latest version
- v0.1.0, committed Oct 15, 2026
- First version recorded
- Jun 3, 2026
- Size
- 8,053 bytes
- Repository stars
- 95
- License
- Apache-2.0
"Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them.
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
# Image Grounding Pipeline > **Standalone install?** If this session was not initialized by the TAO skill bank plugin, run the `tao-setup` skill first (host preflight, credentials, cross-skill discovery). Turn `(image, caption)` pairs into per-image grounded annotations: cleaned captions, referring expressions with character spans, and pixel-space bounding boxes for each expression. A single VLM (Gemini or any OpenAI-compatible endpoint) handles both steps. ## Purpose Generate phrase-grounded training data for referring-expression and grounding models. The VLM acts as a "teacher" annotator: Step 0 extracts referring expressions from the caption while looking at the image; Step 1 returns one bbox set per expression for each image. ## Pipeline Architecture ``` Step 0: Expression extraction → VLM cleans caption, extracts referring expressions + char spans Step 1: Phrase grounding → VLM returns pixel bboxes + scores per expression ``` …
Read the whole file at its exact version.
How to install
mdr add nvidia-tao/tao-skill-bank/tao-generate-image-grounding@sha256:9ddbd9f12aa7d6e2The line at the top of this page pins the label v0.1.0, 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_gxa3lhdwlslrlfdu)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jun 3, 2026 and Oct 15, 2026, about one every 27 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.0 latest | 2026-10-15 | f1e6f8d | 8,053 B | A | view · diff |
| v0.1.0 | 2026-08-28 | ae022a9 | 8,072 B | A | view · diff |
| v0.1.0 | 2026-08-03 | 03f2daa | 8,053 B | A | view · diff |
| v0.1.0 | 2026-06-08 | b31d2b9 | 7,829 B | A | view · diff |
| v0.1 | 2026-06-03 | 94ef697 | 7,827 B | A | view · diff |
| v0.1 | 2026-06-03 | 2fd0a48 | 7,813 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 (8053 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-tao/tao-skill-bank · 95 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gxa3lhdwlslrlfdu GET https://markdownregistry.com/api/v1/resolve?ref=nvidia-tao/tao-skill-bank/tao-generate-image-grounding GET https://markdownregistry.com/api/v1/blob/9ddbd9f12aa7d6e2ecee873636cd1e805b5c28826e515ff1156e814bb3e9cc96
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.