Synthesizes validation analysis into a structured 8-section report with clear verdict (GOOD / NEEDS MAJOR WORK / BAD), strengths, critical flaws, blindspots, and actionable path forward. Use after assumption-challenger and antipattern-detector have produced their analyses, or standalone for quick validations. Produces the final deliverable for /validate.
From kw-pluginnpx claudepluginhub kwiggen/claude-code-plugin --plugin kw-pluginThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Transforms raw validation analysis into a structured, actionable 8-section report. The report provides an unambiguous verdict and specific guidance.
Purpose: Unambiguous assessment with confidence level.
Options:
Include: Clear verdict, confidence level (High/Medium/Low), one-sentence rationale.
Purpose: Acknowledge genuine strengths (builds trust for criticism).
Purpose: Expose fatal or near-fatal weaknesses.
For each flaw:
Prioritized list, most critical first. Specific evidence, not vague concerns.
Purpose: Surface blindspots and hidden assumptions.
Types to check:
Purpose: Reframe if solving wrong problem.
Use when:
Format: "You're asking [stated question], but the real question might be [reframed question]."
Skip if problem is correctly framed — state this explicitly.
Purpose: Define measurable success criteria for revision.
For this to be ready:
- [ ] [Criterion 1]
- [ ] [Criterion 2]
- [ ] [Criterion 3]
Purpose: Concrete next steps based on verdict.
Purpose: Information gaps blocking progress.
| Question | Who Can Answer | What It Blocks |
|---|---|---|
| [Question] | [Person/Team] | [Decision] |
| Verdict | Tone |
|---|---|
| GOOD | Affirming with constructive suggestions |
| NEEDS MAJOR WORK | Direct and constructive — "here's what to fix" |
| BAD | Brutally honest but respectful — "here's why to stop" |
Be direct. Be specific. Be constructive. No sugarcoating, no hedging.
Before delivering the report, verify:
WRONG — vague and unmeasurable:
For this to be ready:
- Team should be confident in the solution
- Performance should be acceptable
CORRECT — specific and verifiable:
For this to be ready:
- P95 latency ≤ 200ms under 500 concurrent users (load test documented)
- Zero critical/high findings in security review
- Rollback procedure tested in staging with < 5 min recovery
# Validation Report: [Title]
**Subject**: [What was validated]
**Date**: [Date]
---
## 1. Verdict
### VERDICT: [GOOD / NEEDS MAJOR WORK / BAD]
**Confidence**: [High / Medium / Low]
[One-sentence summary]
---
## 2. What You Got Right
[2-3 specific strengths with why they matter]
---
## 3. Critical Flaws
### Flaw 1: [Title]
**Why It Matters**: [Impact]
**Consequence**: [What happens if not addressed]
---
## 4. What You're Not Considering
[Blindspots, hidden assumptions, ignored scenarios]
---
## 5. The Real Question
[Reframe or "Problem is correctly framed because..."]
---
## 6. What Bulletproof Looks Like
For this to be ready:
- [ ] [Criterion 1]
- [ ] [Criterion 2]
- [ ] [Criterion 3]
---
## 7. Recommended Path Forward
[Specific next steps based on verdict]
---
## 8. Questions to Answer First
| Question | Who Can Answer | What It Blocks |
|----------|---------------|----------------|
| [Question] | [Person/Team] | [Decision] |