SKILLEMALL.ai
GitHub ↗ RU Sign in

CF llamaguard

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

davila7/claude-code-templates Agent Skills author: davila7 MIT 1 file body ≈ 2 163 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Meta's 7-8B specialized moderation model for LLM input/output filtering.

As a process F 28/100 · No process to follow — References files that are not bundled: references/custom-categories.md, references/benchmarks.md, references/deployment.md

IntegrationAI and agentstype 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
C
88/100
safety, quality, tests
Safety 60%
100
Quality 40%
70
Run on models
none yet
Process rating
F
28/100
No process to follow
References files that are not bundled: references/custom-categories.md, references/benchmarks.md, references/deployment.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

The same skill appears in 2 more places: RA-Skills, AI-Research-SKILLs

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 · 0

✓ No critical or high findings

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/custom-categories.md
  • warning missing-ref reference to a missing file: references/benchmarks.md
  • warning missing-ref reference to a missing file: references/deployment.md
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: references/custom-categories.md, references/benchmarks.md, references/deployment.md
  • 0Tools and files. 3 referenced file(s) missing: references/custom-categories.md, references/benchmarks.md, references/deployment.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 40Consistency. Frontmatter name (llamaguard) differs from the folder (safety-alignment-llamaguard)
  • 100Steps. 35 steps
  • 100Execution cost. Instruction body is 2163 tokens

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
  • -2localhost URLs: will not work for another user
  • +2Single-language instructions
  • +3Description length 268: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 35 items
  • +4Has examples (13 code blocks)
  • +1License stated

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