SKILLEMALL.ai
GitHub ↗ RU Sign in

BF deepstream-import-vision-model

Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.

ClawHub Agent Skills author: NVIDIA 1 file body ≈ 3 414 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end…

As a process F 51/100 · Will not run — References files that are not bundled: references/model-acquire.md, references/engine-build.md, references/pipeline-run.md

AnalyzerPDFDockerPlaywrightInfrastructureSoftware developmentData and analyticstype 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
86/100
safety, quality, tests
Safety 60%
95
Quality 40%
73
Run on models
none yet
Process rating
F
51/100
Will not run
References files that are not bundled: references/model-acquire.md, references/engine-build.md, references/pipeline-run.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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.

Dangerous commands 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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 Dangerous commands cmd-install-from-url SKILL.md:259
    Installs a package from an untrusted URL / archive (documentation table row)
    | `No module named 'pyservicemaker'` | Install into venv: `pip install /opt/nvidia/deepstream/.../pyservicemaker*.whl` |
    table

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/model-acquire.md
  • warning missing-ref reference to a missing file: references/engine-build.md
  • warning missing-ref reference to a missing file: references/pipeline-run.md
  • warning missing-ref reference to a missing file: references/report-generation.md
  • warning missing-ref reference to a missing file: references/windows.md
  • note edit-residue the text marks something as outdated (lines 63, 147): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 51/100

Will not run. References files that are not bundled: references/model-acquire.md, references/engine-build.md, references/pipeline-run.md
  • 0Tools and files. 5 referenced file(s) missing: references/model-acquire.md, references/engine-build.md, references/pipeline-run.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 50When it triggers. No condition that starts the skill
  • 100Steps. 16 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3414 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 top-level sections: this looks like several domains in one skill

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 310: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 16 items
  • +4Has examples (9 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.