doc-adr-fixer

Automates the full ADR lifecycle from source documents (BRD, PRD, EARS, BDD) or free-text prompts through generation, validation, and iterative refinement. Detects whether an ADR exists, routes to generation or review-and-fix accordingly, and maintains the ADR index with passing scores. Supports single or batch processing with configurable quality thresholds and fix iteration limits.

Quality-advisor gives live feedback while you create or review SDD documents, catching completion gaps, documentation anti-patterns, tag compliance, and naming issues before submission. It scores sections, detects common problems like missing traceability or broken links, validates cumulative tagging across layers, and returns actionable recommendations to fix issues.

gate-check automates the verification step in the change governance process by selecting the correct approval gate based on affected layers, running its entry criteria and error checks, and populating the approval form for human sign-off. It verifies but never approves—all signature and decision fields remain blank for the designated approvers.

doc-adr captures a single architectural decision using the Context-Decision-Consequences pattern, positioned as Layer 5 in the specification-driven development flow. It records the rationale, chosen approach, evaluated alternatives, and accepted trade-offs for decisions that bridge container and component design.

doc-validator enforces consistency rules across your entire SDD documentation corpus—catching broken links, orphaned artifacts, cumulative-tag gaps, duplicate IDs, and traceability gaps across all 8 layers. It runs declarative checks against your corpus structure and can optionally repair safely-fixable issues like missing reciprocal links or stale metadata. Use it before releases or after batch generation to ensure your documentation chain stays machine-verifiable and traceable.

adr-critique systematically reviews existing or inherited ADRs to identify violations of shared rules, gaps in business-to-architecture reasoning, and conflicts with neighboring decisions or LikeC4 models. Each issue surfaces as a single flag requiring architect sign-off before moving to the next, ensuring quality without bulk rewrites.