nw-ab-critique-dimensi…
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Review dimensions and scoring for root cause analysis quality assessment
$ npx -y skills add nWave-ai/nWave --skill nw-tr-review-criteria --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nw-tr-review-criteriaContext preview
The summary Claude sees to decide when to auto-load this skill.
Review dimensions and scoring for root cause analysis quality assessment
name: nw-tr-review-criteria description: Review dimensions and scoring for root cause analysis quality assessment user-invocable: false disable-model-invocation: true
Review dimensions and scoring for root cause analysis quality assessment.
Check each WHY-to-WHY link.
Pass: logical mechanism (not just correlation) | no skipped steps | alternatives considered/eliminated | chain reads coherently both directions
Failures: correlation assumed as causation | causal chain gaps | single-path tunnel vision (first plausible cause accepted)
Severity: Critical -- wrong root cause = ineffective fixes.
Verify findings grounded in observable data.
Pass: each WHY cites specific evidence (logs, metrics, config, repro steps) | evidence verifiable by third party | timeline supports causality | hypotheses marked unverified
Failures: "Probably because..." without data | vague references ("logs show issues") | mixing facts with speculation unlabeled
Severity: High -- unreliable analysis undermines trust.
Verify competing explanations explored.
Pass: 2+ alternatives at WHY 1-3 | each pursued or eliminated with evidence | "why not" reasoning documented
Failures: stops at first plausible cause | alternatives mentioned but unevaluated | confirmation bias
Severity: High -- may miss actual root cause.
Verify analysis reaches fundamental causes.
Pass: each branch reaches WHY 5 (or justifies stopping with evidence) | final causes are actionable | causes explain symptoms when traced forward
Failures: stopping at WHY 2-3 | WHY 5 vague/philosophical not actionable | branches abandoned
Severity: High -- shallow analysis = band-aid fixes that recur.
Verify all symptoms accounted for.
Pass: all symptoms have causal branch | root causes collectively explain all | no orphan symptoms | cross-cause validation (no contradictions)
Failures: symptoms ignored | root causes explain primary but not secondary | contradictory causes without reconciliation
Severity: Medium -- incomplete analysis leaves unaddressed failures.
Verify solutions map to root causes.
Pass: every root cause has solution | immediate mitigations vs permanent fixes distinguished | no orphan solutions | prevention addresses systemic factors
Failures: solutions address symptoms not causes | root cause without fix | generic recommendations untied to findings
Severity: Medium -- untraceable solutions are guesses.
review_id: "rca_rev_{timestamp}"
reviewer: "nw-troubleshooter-reviewer"
dimensions:
causality_logic:
score: 0-10
issues: [{issue, severity, recommendation}]
evidence_quality:
score: 0-10
issues: [{issue, severity, recommendation}]
alternative_hypotheses:
score: 0-10
issues: [{issue, severity, recommendation}]
five_why_depth:
score: 0-10
issues: [{issue, severity, recommendation}]
completeness:
score: 0-10
issues: [{issue, severity, recommendation}]
solution_traceability:
score: 0-10
issues: [{issue, severity, recommendation}]
overall_score: "average of dimension scores"
approval_status: "approved | revisions_required"
summary: "1-2 sentence assessment"**Approval threshold**: overall >= 7 and no dimension below 5.
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…