benchmark-623e5a — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited benchmark-623e5a (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Run an MetriLLM benchmark on a locally available model. This skill handles setup verification, model selection, benchmark execution, and result interpretation.
Before running any benchmark, verify the environment:
metrillm list to check the active backend. If needed, use metrillm list --backend <name> for a specific runtime and tell the user to start that runtime first.metrillm works.If $ARGUMENTS is provided, use it as the model name. Otherwise:
list_models tool to list available models.metrillm list (or metrillm list --backend <name>).Help the user pick a model if they're unsure. Smaller models (1-3B) benchmark faster (~30s). Larger models (7B+) take 2-5 minutes.
With MCP (preferred): Use the run_benchmark tool with the model name. Set perfOnly: true for performance-only (faster).
Without MCP:
metrillm bench --model <model-name> --jsonFor performance-only (skip quality tests, much faster):
metrillm bench --model <model-name> --perf-only --jsonThe benchmark produces a JSON result with:
| Metric | What it means |
|---|---|
performance.tokensPerSecond | Generation speed. >30 tok/s = good for interactive use |
performance.ttft | Time to first token in ms. <500ms = responsive |
performance.memoryUsedGB | RAM/VRAM consumed during inference |
fitness.verdict | EXCELLENT / GOOD / MARGINAL / NOT RECOMMENDED |
fitness.globalScore | 0-100 composite score (30% perf + 70% quality) |
fitness.interpretation | Human-readable summary of the verdict |
Present the results in a clear, concise format. Highlight the verdict prominently.
If the user wants to compare models:
get_results tool to retrieve previous results.~/.metrillm/results/.Compare side-by-side on key metrics.
If the user wants to share results to the public leaderboard:
share_result tool with the result file path.metrillm bench --model <model-name> --shareUses official upload defaults by default. For self-hosted/staging deployments, set METRILLM_SUPABASE_URL and METRILLM_SUPABASE_ANON_KEY.
--perf-only / perfOnly: true for quick tests when quality scoring isn't needed~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.