SKILLEMALL.ai
GitHub ↗ RU Sign in

BF nemotron-policy-generator

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.

ClawHub Agent Skills author: NVIDIA 1 file body ≈ 4 532 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal…

As a process F 43/100 · Will not run — References files that are not bundled: references/target_models.md, references/content_safety_taxonomy.md, assets/policy_md_template.md

GeneratorWordInfrastructureAI and agentsSoftware 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
88/100
safety, quality, tests
Safety 60%
99
Quality 40%
72
Run on models
none yet
Process rating
F
43/100
Will not run
References files that are not bundled: references/target_models.md, references/content_safety_taxonomy.md, assets/policy_md_template.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

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
  • low Secrets in code secret-high-entropy-token SKILL.md:5
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    description: "Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemo…-4B (text) and multimodal Nemo…ty. Produces a Mark
    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/target_models.md
  • warning missing-ref reference to a missing file: references/content_safety_taxonomy.md
  • warning missing-ref reference to a missing file: assets/policy_md_template.md
  • warning missing-ref reference to a missing file: assets/policy_json_schema.json
  • warning missing-ref reference to a missing file: assets/nemotron_system_prompt_template.txt
  • warning missing-ref reference to a missing file: assets/nemotron_policy_generator.html
  • warning missing-ref reference to a missing file: references/policy_patterns.md
  • note frontmatter-key unknown frontmatter key "title"

Process rating: all ten parameters 43/100

Will not run. References files that are not bundled: references/target_models.md, references/content_safety_taxonomy.md, assets/policy_md_template.md
  • 0Tools and files. 7 referenced file(s) missing: references/target_models.md, references/content_safety_taxonomy.md, assets/policy_md_template.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 60Steps. 65 steps, 4 vague phrases
  • 70When it triggers. States when to use, but not when not to
  • 70Failures and branches. 10 branches
  • 70Execution cost. Instruction body is 4532 tokens
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress

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 352: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 65 items
  • +4Has examples (0 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.