UNPKG

automagik-genie

Version:

Self-evolving AI agent orchestration framework with Model Context Protocol support

39 lines (30 loc) 1.34 kB
# QA - Create Collective ## Validation Checklists ### Research Outputs - Sources cited with links and dates - Cross-checked key claims (2+ independent sources) - Bias and scope limits noted - Evidence snapshots stored under `validation/` ### Writing Outputs - Audience, purpose, and tone aligned with brief - Clear structure (title, headings, logical flow) - Style guide followed (`@.genie/standards/best-practices.md` or project-specific) - Factual accuracy checks recorded in `validation/` - Readability pass completed (note decisions in `reports/`) ### Editing & Review - Line edits: clarity, grammar, concision - Substantive edits: structure, argument strength - Before/after diffs or notes saved - Final approval noted in `reports/` ## Evidence Paths - Base: `.genie/wishes/<slug>/` - Validation: `validation/` (drafts, comparisons, citations, notes) - Reports: `reports/` (approvals, blockers, done reports) ## Critical Edge Cases - Missing style guide → request or extract inferred guidelines and document - Ambiguous audience/goal → ask targeted questions; record assumptions - Source conflicts → note discrepancies and chosen stance with rationale ## Success Criteria - ✅ Evidence trail demonstrates care and accuracy - ✅ Tone and structure match the brief - ✅ Approvals captured before publishing or handoff