Run quality assurance checks on any output before delivery. Validates brand compliance, copy standards, format requirements, and flags issues.
From brand-bond-osnpx claudepluginhub brandbondco/brand-bond-os --plugin brand-bond-osThis 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.
Run automated quality checks on content before it leaves the studio.
Evaluates any output against Brand & Bond quality standards and client-specific rules. Returns a pass/fail verdict with specific issues to fix.
/qa [content or reference to check]
Examples:
/qa (checks the last output in conversation)/qa check the hero copy above/qa review the proposal before sending| Check | Pass Criteria |
|---|---|
| Tone match | Matches client's defined tone (e.g., 3/5 formality) |
| Vocabulary | No prohibited words, uses approved vocabulary |
| Sentence structure | Active voice, appropriate length |
| Personality | Aligns with brand personality traits |
| Check | Pass Criteria |
|---|---|
| Lead with outcome | Benefits before features/technology |
| Specificity | Numbers over adjectives ("3 seconds" not "fast") |
| No empty claims | Every claim is verifiable or specific |
| No hype language | No "revolutionary", "game-changer", etc. |
| No exclamation marks | Unless explicitly approved for brand |
| Check | Pass Criteria |
|---|---|
| Structure | Follows requested format (table, list, prose) |
| Length | Within specified constraints |
| Hierarchy | Clear heading/subheading structure |
| Consistency | Formatting consistent throughout |
| Check | Pass Criteria |
|---|---|
| Data verification | Numbers/stats are sourced or verified |
| Claim accuracy | No overpromising or unverifiable claims |
| Technical correctness | Industry terms used correctly |
| Check | Pass Criteria |
|---|---|
| Client vocabulary | Uses client's approved terms |
| Prohibited terms | Avoids client's blacklisted words |
| Brand guidelines | Follows documented brand rules |
| Legal/compliance | No regulatory red flags |
═══════════════════════════════════════════
QA REPORT
═══════════════════════════════════════════
Content: [what was checked]
Client: [client name if applicable]
Date: [YYYY-MM-DD]
═══════════════════════════════════════════
## Summary
[PASS ✅ | FAIL ❌ | REVIEW ⚠️]
Score: [X/5 gates passed]
---
## Gate Results
### 1. Brand Voice Compliance [✅|❌|⚠️]
- [Specific findings]
### 2. Copy Standards [✅|❌|⚠️]
- [Specific findings]
### 3. Format Standards [✅|❌|⚠️]
- [Specific findings]
### 4. Factual Accuracy [✅|❌|⚠️]
- [Specific findings]
### 5. Client-Specific Rules [✅|❌|⚠️]
- [Specific findings]
---
## Issues to Fix
| # | Issue | Location | Fix |
|---|-------|----------|-----|
| 1 | [problem] | [where] | [how to fix] |
| 2 | [problem] | [where] | [how to fix] |
---
## Verdict
[APPROVED FOR DELIVERY | NEEDS REVISION | BLOCKED]
[If needs revision: specific next action]
═══════════════════════════════════════════
| Verdict | Meaning | Action |
|---|---|---|
| PASS ✅ | All gates passed | Ready for delivery |
| REVIEW ⚠️ | Minor issues, judgment call | Samet decides |
| FAIL ❌ | Critical issues found | Must fix before delivery |
NEO should automatically suggest /qa before:
When content passes QA during a handoff:
HANDOFF
...
## QA Status
✅ Passed /qa on [date]
Gates: 5/5
Ready for next phase
For rapid validation without full report:
/qa quick
Returns only: ✅ PASS or ❌ FAIL: [critical issue]
QA automatically loads client rules when client is specified:
/qa wonn
Loads wonn.md rules and wonn-brand-dna standards for evaluation.