SKILLEMALL.ai
GitHub ↗ RU Sign in

CC tao-run-deft-aoi

Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and deployment gating against a customer-defined primary metric and optional constraints. Use only when the request identifies an AOI / automated-optical-inspection, PCB-defect, VisualChangeNet, or ChangeNet workflow. Supports air-gapped/offline runs with pre-staged assets. Never infer AOI from generic iterative-improvement language. Do not use for CLIP / SigLIP image retrieval, attribute-labelled image data, standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.

ClawHub Agent Skills author: NVIDIA 1 file body ≈ 4 711 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP…

As a process C 61/100 · Has gaps — References files that are not bundled: references/air-gap.md, references/network-bootstrap.md, references/visual-changenet.md

ProcedureDockerData and analyticsInfrastructureAI and agentstype 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
C
86/100
safety, quality, tests
Safety 60%
94
Quality 40%
73
Run on models
none yet
Process rating
C
61/100
Has gaps
References files that are not bundled: references/air-gap.md, references/network-bootstrap.md, references/visual-changenet.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
70
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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Task Bash Write
  • low Exfiltration read-dotenv SKILL.md:160
    Reads a .env file (detector / deny-list definition)
    `set -a; source /path/to/.env; set +a`. The run never creates or writes that
    detector

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/air-gap.md
  • warning missing-ref reference to a missing file: references/network-bootstrap.md
  • warning missing-ref reference to a missing file: references/visual-changenet.md
  • warning missing-ref reference to a missing file: references/tao-mine-aoi-images.md
  • warning missing-ref reference to a missing file: references/tao-generate-anomalies.md
  • warning missing-ref reference to a missing file: references/skill_info.yaml
  • warning missing-ref reference to a missing file: references/preflight.md
  • warning missing-ref reference to a missing file: references/pipeline-and-state.md
  • warning missing-ref reference to a missing file: references/metric-contract.md
  • warning missing-ref reference to a missing file: references/tao-analyze-gaps-visual-changenet.md
  • warning missing-ref reference to a missing file: scripts/init_deft_state.py
  • warning missing-ref reference to a missing file: scripts/render_report.py
  • warning missing-ref reference to a missing file: references/*.md
  • warning missing-ref reference to a missing file: references/scripts-and-agents.md
  • warning missing-ref reference to a missing file: references/tao-route-visual-changenet-samples.md
  • warning missing-ref reference to a missing file: references/data-layout.md

Process rating: all ten parameters 61/100

Will not run. References files that are not bundled: references/air-gap.md, references/network-bootstrap.md, references/visual-changenet.md
  • 0Tools and files. 16 referenced file(s) missing: references/air-gap.md, references/network-bootstrap.md, references/visual-changenet.md
  • 0Result and completion. Does not say what the result is
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 4711 tokens
  • 85Steps. 23 steps, 1 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (9 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 703: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 23 items
  • +1License stated

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