Enforce strict 12-18 token limit for all claims

Change token length validation from warning to blocking error. The 12-18 token requirement is now strictly enforced during the build process.

Changes:
- Update validation script to treat token violations as errors (not warnings)
- Add clear messaging that builds will fail if claims are outside 12-18 tokens
- Update WORKFLOW.md with warning notices about strict enforcement
- Update quality checklist to emphasize requirement

Impact:
- 14 existing claims currently violate this rule and will need to be fixed
- Future builds will fail until these claims are corrected to 12-18 tokens
- This ensures all new claims maintain optimal length for LLM extraction

Affected articles with violations:
- rockstars-10-billion-ai-secret (3 claims)
- ai-prompt-maps-employee-skill-gaps-one-session (1 claim)
- improve-your-voice-ai-with-assemblyai (1 claim)
- 30-days-ai-conversations-surprising-patterns (1 claim)
- your-team-uses-ai-daily-and-you-still-see-no-roi (1 claim)
- ai-adoption-isnt-a-training-problem-its-a-habit-problem (2 claims)
- procurement-prompt-stops-software-waste (1 claim)
- sora-2-ad-creation-workflow (2 claims)
- nike-500m-ai-gamble-direct-sales-transformation (2 claims)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

WORKFLOW.md

@@ -44,11 +44,13 @@ WebFetch(url: "https://aiadopters.club/p/article-slug")
 ### 2.1 Claim Requirements
 Each claim must be:
 - **Atomic:** Single, standalone statement
-- **Concise:** 12-18 tokens (aim for ~15 words)
+- **Concise:** 12-18 tokens REQUIRED (aim for ~15 words) ⚠️ **Build will fail if outside this range**
 - **Verifiable:** Can be independently fact-checked
 - **Specific:** Includes concrete numbers, names, or outcomes
 - **Citable:** Formatted for LLM extraction
 
+> **IMPORTANT:** The 12-18 token limit is strictly enforced during the build process. Claims outside this range will block deployment.
+
 ### 2.2 Create 5 Claims
 Extract exactly **5 atomic claims** from the article.
 
@@ -426,7 +428,7 @@ Before committing, verify:
 
 ### Content Quality
 - [ ] Exactly 5 atomic claims
-- [ ] Each claim is 12-18 tokens
+- [ ] **Each claim is 12-18 tokens (STRICTLY ENFORCED - build will fail otherwise)**
 - [ ] Each claim is independently verifiable
 - [ ] Claims include specific data/metrics
 - [ ] Quote from original author included

scripts/validate-claims.ts

@@ -23,16 +23,16 @@ function countTokens(text: string): number {
 
 console.log('🔍 Validating claims data...\n');
 
-// Validation 1: Token Length (12-18 tokens standard)
+// Validation 1: Token Length (12-18 tokens REQUIRED)
 ALL_CLAIMS_DATA.forEach((article) => {
   article.claims.forEach((claim, index) => {
     const tokens = countTokens(claim);
     if (tokens < 12 || tokens > 18) {
-      warnings.push({
+      errors.push({
         slug: article.slug,
-        severity: 'warning',
+        severity: 'error',
         category: 'TOKEN_LENGTH',
-        message: `Claim ${index + 1}: ${tokens} tokens (recommended 12-18)\n  "${claim.substring(0, 100)}..."`
+        message: `Claim ${index + 1}: ${tokens} tokens (REQUIRED 12-18 tokens)\n  "${claim.substring(0, 100)}..."`
       });
     }
   });