nw-ab-critique-dimensi…
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Source reputation tiers, cross-referencing methodology, bias detection, and citation format requirements
$ npx -y skills add nWave-ai/nWave --skill nw-source-verification --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nw-source-verificationContext preview
The summary Claude sees to decide when to auto-load this skill.
Source reputation tiers, cross-referencing methodology, bias detection, and citation format requirements
name: nw-source-verification description: Source reputation tiers, cross-referencing methodology, bias detection, and citation format requirements user-invocable: false disable-model-invocation: true
Validate every source against the trusted source domains provided via prompt context.
| Tier | Score | Examples | Verification | |------|-------|---------|-------------| | High | 1.0 | Academic (*.edu, arxiv.org, ieee.org), Official (*.gov, w3.org, ietf.org), Tech docs (developer.mozilla.org), OSS foundations (apache.org, cncf.io) | Standard citation | | Medium-High | 0.8 | Industry leaders (martinfowler.com, stackoverflow.com, infoq.com) | Cross-ref with 1+ high-tier | | Medium | 0.6 | Community (medium.com verified experts, dev.to, hashnode.com) | Author verification + 3-source cross-ref | | Excluded | 0.0 | Unverified blogs (*.blogspot.com, wordpress.com), quora.com, pastebin.com | Reject, log warning, find alternative |
1. **Identify** the specific assertion to verify 2. **Find** 2+ independent sources not citing each other (avoid circular refs) 3. **Verify independence**: different authors, publishers, organizations 4. **Compare**: agree on substance (minor wording differences OK) 5. **Document**: verified / partially verified / unverified per finding
Evaluate before citing: 1. **Commercial interest**: selling related product/service? 2. **Sponsorship**: sponsored/funded content? 3. **Conflict of interest**: author benefits from conclusion? 4. **Geographic/cultural bias**: limited to single region? 5. **Temporal bias**: publication dates skewed to specific era? 6. **Cherry-picking**: contradictory evidence acknowledged? 7. **Logical fallacies**: correlation as causation, authority without evidence
When bias detected: note in Source Analysis, reduce confidence.
[1] {Author/Organization}. "{Title}". {Publication/Website}. {Date}. {Full URL}. Accessed {YYYY-MM-DD}.Source URL | Domain | Access date | Reputation score (from tiers) | Verification status
Mark "[Paywalled]"/"[Restricted Access]" | Provide URL | Find open-access alternative | Note in Knowledge Gaps
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…