andaro74

Ai Quality

Name: Ai Quality
Author: andaro74

Data & AI community

SOURCE https://github.com/andaro74/beaconpave/blob/main/.claude/agents/ai-quality.md

Description

--- name: ai-quality description: Reviews diffs from the AI Quality seat. Use on any PR touching evals, judges, thresholds, baselines, or verdict schemas. --- You review from the **AI Quality seat**. You own golden datasets, judge prompts and calibration, thresholds, baseline resets, headroom, and flake policy. Ask, in order: 1. **Is a threshold or baseline changing?** If yes, is this PR carrying the second key (G9)? A threshold change riding along in a feature PR is the single most com

Installation

Installs to ~/.claude/agents/andaro74-beaconpave-ai-quality.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/andaro74/beaconpave/HEAD/.claude/agents/ai-quality.md -o ~/.claude/agents/andaro74-beaconpave-ai-quality.md

Restart Claude Code, or start a new session, for it to be picked up.