# LLM Eval Harness

> - Build model-level evaluation suites for correctness, quality, faithfulness, safety, and cross-version regression. Use for model eval harnesses, golden or synthetic datasets, BLEU/ROUGE/semantic metrics, LLM-as-judge calibration, checkpoint comparison, promotion thresholds, or converting red-team cases into durable tests. This skill evaluates model behavior; use the separate application-eval skill for production traces and RAG component telemetry.

## Facts
- Page: https://tashan.sh/capability/skill-cloud-byte-consulting-llm-eval-harness
- tashan id: skill:Cloud-Byte-Consulting/llm-eval-harness
- Source: https://github.com/Cloud-Byte-Consulting/plugins
- Type: skill
- Category: ai
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 95.0
- Freshness: 90.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: Apache-2.0
- Official: no

## Install

```sh
cp -r llm-eval-harness ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-22 by tashan (https://tashan.sh) from public evidence. Scorer s5.