AI prompts, agents, and anti-patterns for QA — from specification audits to API test generation
21 files for Claude Code, Codex, GitHub Copilot and OpenCode: api-tests, auditor, doc-lint, init-agent and 17 more — 2,657 tokens loaded in every session.
.github/copilot-instructions.md A 718 tok AGENTS.md A 503 tok CLAUDE.md C 1,436 tok .claude/settings.json B — .claude/settings.json A — .agents/skills/api-tests/SKILL.md A 21 tok .agents/skills/auditor/SKILL.md A 20 tok .agents/skills/doc-lint/SKILL.md A 18 tok .agents/skills/init-agent/SKILL.md A 21 tok .agents/skills/init-project/SKILL.md A 20 tok .agents/skills/init-skill/SKILL.md A 16 tok .agents/skills/output-review/SKILL.md A 13 tok .agents/skills/repo-scout/SKILL.md A 19 tok .agents/skills/screenshot-analyze/SKILL.md A 23 tok .agents/skills/sdet/SKILL.md A 16 tok .agents/skills/skill-audit/SKILL.md A 18 tok .agents/skills/spec-audit/SKILL.md A 20 tok .agents/skills/test-cases/SKILL.md A 16 tok .agents/skills/update-ai-setup/SKILL.md A 23 tok These files are vlad-ryzhkov/AI-QA-workshop-feb19's own configuration — they tell Claude Code, Codex, GitHub Copilot and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.