SKILLEMALL.ai
GitHub ↗ RU Sign in

BC 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.

NVIDIA-NeMo/Nemotron Agent Skills author: NVIDIA-NeMo 12 files body ≈ 4 532 tokens Open the sourcegithub.com↗ analyzed 5 d ago

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

As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions

GeneratorWordInfrastructureAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
B
90/100
safety, quality, tests
Safety 60%
92
Quality 40%
88
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Steps w 15
60
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: nemotron-policy-generator (NVIDIA/skills)

How to improve

    For the model run — optional
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 8

    ✓ No critical or high findings

    Medium and low: 8
    • low Secrets in code secret-high-entropy-token assets/nemotron_system_prompt_template.txt:32
      High-entropy token-like string (may be an id, hash or a credential)
      ### SECTION 1 — Nemo…-4B
    • low Secrets in code secret-high-entropy-token assets/nemotron_system_prompt_template.txt:160
      High-entropy token-like string (may be an id, hash or a credential)
      Nemo…-4B or Nemo…ety), not by the
    • low Secrets in code secret-high-entropy-token assets/nemotron_system_prompt_template.txt:189
      High-entropy token-like string (may be an id, hash or a credential)
      from transformers import Gemm…ion, AutoProcessor
    • low Risky intent intent-offensive-security references/content_safety_taxonomy.md:121
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - **Definition:** Source code, scripts, or actionable instructions for creating, distributing, or modifying malicious software (viruses, ransomware, keyloggers, spyware, exploits).
      detector
    • low Risky intent intent-offensive-security references/content_safety_taxonomy.md:123
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - **Synonyms:** "malware", "virus", "ransomware", "exploit", "keylogger", "spyware", "trojan", "vulnerability weaponization"
      detector
    • low Secrets in code secret-high-entropy-token skill-card.md:2
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemo…-4B (text) and multimodal Nemo…ety — producing a Markdown policy,
      detector
    • low Secrets in code secret-high-entropy-token skill-card.md:12
      High-entropy token-like string (may be an id, hash or a credential)
      Developers and safety engineers creating custom content-safety policies for NVIDIA Nemotron guardrail models, mapping rough requirements into structured policy artifacts compatible with Nemotron-Conte
    • 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: 10. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "title"

    Process rating: all ten parameters 61/100

    • 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
    • 100Tools and files. No external tools needed
    • 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)
    • +4Reference files are cited in the instructions (3 of 3)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.