Automated quality assurance framework for Claude Skills — tests trigger accuracy, output quality, false positives, and consistency
npx skills add Kentobayashi/claude-skills-QA-frameworkAutomated quality assurance framework for Claude Skills — tests trigger accuracy, output quality, false positives, and consistency
Source: https://github.com/Kentobayashi/claude-skills-QA-framework
Discovered by the Awesome Skills daily skill hunter.
One file. 9 questions. Stops AI agents from doing the obviously-wrong thing. MIT. Works with Claude Code, Codex, Cursor, OpenClaw.
Agent skill repository for PJ-SBN-593844/skill-zoom-out.
Public Codex/Claude skills for safe SEO operations, team routing, and approval-gated execution batches
Codex skill for safe Claude peer reviews of code, architecture, schemas, and production readiness
Use DeepSeek API (deepseek-v4) as the backend for Claude Code CLI. One-command setup, health check, auto-repair.
Evaluate LLMs the right way — confidence intervals, unbiased pass@k, significance testing, bias-controlled LLM-as-judge, contamination checks. A drop-in agent skill with a numpy stats core validated against ground truth.