# Agentic Eval

> | Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - The user makes an ad-hoc, in-session request to double-check, critique, or review your own output before finishing — e.g. "double check this," "critique your own answer before finishing," "review this before you're done" — even with no mention of building a pipeline or eval system - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

## Facts
- Page: https://tashan.sh/capability/skill-dotknewt-agentic-eval
- tashan id: skill:dotknewt/agentic-eval
- Source: https://github.com/dotknewt/awesome-agency
- Type: skill
- Category: other
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 96.0
- Freshness: 92.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r agentic-eval ~/.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 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.