SKILLEMALL.ai
GitHub ↗ RU Sign in

BF tao-port-huggingface-model

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to "integrate a HuggingFace model into TAO", "add an HF model to TAO Toolkit", "wire a HuggingFace ViT/DETR/ SegFormer into tao-pytorch", "build a TAO trainer + deploy pipeline for an HF CV model", or pastes a HuggingFace model URL/ID and wants it turned into a TAO model. Covers the full 7-phase loop: prerequisites check, HuggingFace inspection and validation, codebase exploration, tao-core configuration and native trainer implementation, ONNX export plus TensorRT deploy integration, packaging and L0 testing, container-based end-to-end validation, and (conditional) accuracy/latency tuning. Supports classification, object detection, semantic / instance / panoptic segmentation, zero-shot detection, and depth estimation.

ClawHub Agent Skills author: NVIDIA 1 file body ≈ 4 077 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).

As a process F 40/100 · Will not run — References files that are not bundled: references/phase-0-prereqs.md, references/phase-1-inspection.md, references/hf-inspection.md

IntegrationDockerInfrastructureSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
95
Quality 40%
68
Run on models
none yet
Process rating
F
40/100
Will not run
References files that are not bundled: references/phase-0-prereqs.md, references/phase-1-inspection.md, references/hf-inspection.md
Tools and files w 18
0
Steps w 15
0
Result and completion w 14
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Bash Write Edit Grep Glob

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/phase-0-prereqs.md
  • warning missing-ref reference to a missing file: references/phase-1-inspection.md
  • warning missing-ref reference to a missing file: references/hf-inspection.md
  • warning missing-ref reference to a missing file: references/phase-2-codebase.md
  • warning missing-ref reference to a missing file: references/task-type-guide.md
  • warning missing-ref reference to a missing file: references/phase-3-implementation.md
  • warning missing-ref reference to a missing file: references/tao-patterns.md
  • warning missing-ref reference to a missing file: references/repo-structure.md
  • warning missing-ref reference to a missing file: references/phase-4-deploy.md
  • warning missing-ref reference to a missing file: references/phase-5-packaging.md
  • warning missing-ref reference to a missing file: references/phase-6-container-tests.md
  • warning missing-ref reference to a missing file: references/docker-patterns.md
  • warning missing-ref reference to a missing file: references/phase-7-optimization.md
  • warning missing-ref reference to a missing file: references/workflow-consistency.md
  • warning missing-ref reference to a missing file: references/cross-cutting.md
  • warning missing-ref reference to a missing file: references/phase-N-*.md
  • warning missing-ref reference to a missing file: scripts/__init__.py

Process rating: all ten parameters 40/100

Will not run. References files that are not bundled: references/phase-0-prereqs.md, references/phase-1-inspection.md, references/hf-inspection.md
  • 0Tools and files. 17 referenced file(s) missing: references/phase-0-prereqs.md, references/phase-1-inspection.md, references/hf-inspection.md
  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 31 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 4077 tokens
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • low 17 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (7 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 904: 120–800 characters recommended
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +2Single-language instructions
  • +5Description quotes 4 example trigger phrases
  • +4Structure: 18 headings
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.