nw-ab-critique-dimensi…
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Roadmap-specific validation checks for architecture reviews. Load when reviewing roadmaps for implementation readiness.
$ npx -y skills add nWave-ai/nWave --skill nw-roadmap-review-checks --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nw-roadmap-review-checksContext preview
The summary Claude sees to decide when to auto-load this skill.
Roadmap-specific validation checks for architecture reviews. Load when reviewing roadmaps for implementation readiness.
name: nw-roadmap-review-checks description: Roadmap-specific validation checks for architecture reviews. Load when reviewing roadmaps for implementation readiness. user-invocable: false disable-model-invocation: true
Six mandatory checks for every roadmap review. Each produces a finding block.
Verify completing all steps produces an INVOCABLE feature, not just existing code.
Criteria: at least one step targets entry point integration | acceptance tests invoke through driving ports | clear user invocation path after completion
Severity: BLOCKER if no integration step or invocation path. HIGH if tests at wrong boundary.
EXTERNAL VALIDITY CHECK: PASSED|FAILED
Issue: {missing wiring}
Consequence: {what happens without fix}
Required Action: {integration step to add}Scan AC for implementation details locking crafter into predetermined structure.
Detection: underscore-prefixed identifiers | method signatures with params | internal class references | specific return types
Severity: HIGH. Flag each coupled AC with rewrite.
Rationale: AC = WHAT (observable behavior), never HOW (internal structure). Crafter decides during GREEN + REFACTOR.
Calculation: implementation steps / unique production files in `files_to_modify`
Thresholds: acceptable <= 2.0 | warning 2.0-2.5 | reject > 2.5
Identical pattern check: 3+ steps with identical AC differing by substitution -> require batching.
Verify no implementation code. BLOCKER.
Detection: code snippets/algorithms in descriptions | method implementations in AC | pseudocode/logic | variable names, loops, conditionals
Architect defines WHAT; crafter decides HOW. Roadmap code prevents better solutions via TDD.
Quantitative thresholds: total words 500 (1-3 steps) / 1500 (4-8) / 3000 (9-15) | step description max 50 words | AC max 5 per step, 30 words each | notes max 100 words
Verbosity detection: multi-sentence blocks -> bullets | qualifiers (comprehensive, robust) -> delete | motivational language -> delete | redundancy -> state once | tutorials -> delete, assume expertise
Precision: every AC single interpretation | testable outcome | business over technical jargon
Severity: BLOCKER if word count exceeds threshold.
Verify unit tests respect hexagonal boundaries.
Rules: invoke through driving ports only | no domain entity unit tests | behavior focus | never import internal/private modules
Severity: HIGH.
AI agents that guide you from idea to working code, with human judgment at every gate. nWave runs inside Claude Code. It breaks feature delivery into seven waves (discover, diverge, discuss, design, devops, distill, deliver).
Repo: nWave-ai/nWave
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton…
Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement
5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance
Architectural style selection decision matrices, trade-off analysis, structural enforcement rules, and combination patterns. Load when choosing or evaluating…