Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A 7-part brand strategy framework for building comprehensive brand foundations. Trigger with phrases like "create brand strategy", "build brand brief", "define brand positioning", "brand messaging", "audience architecture", "brand truth", or "go-to-market brand plan". Use when working with brand strategy.
.claude/skills/jeremylongshore-brand-strategy/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 161% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 15% | 0% |
A systematic 7-part methodology for building brand foundations — the same process top agencies use with Fortune 500 clients.
This skill guides users through a comprehensive brand strategy process, from core identity through measurement. Each phase builds on the previous, creating a cohesive strategic foundation.
Walk the user through each phase sequentially. Ask discovery questions, synthesize their answers, and produce structured outputs for each section before moving to the next.
The foundation. Define who the brand authentically is before anything else.
Discovery Questions:
Output: A Brand Truth statement (2-3 sentences) capturing the brand's reason for being, core belief, and authentic identity.
Define who the brand serves — not demographics, but motivations.
Discovery Questions:
Output: 2-4 audience personas, each with:
Position the brand within the broader landscape.
Discovery Questions:
Output: A positioning statement that captures competitive differentiation and cultural relevance. Include a simple competitive landscape map.
Translate strategy into language.
Discovery Questions:
Output: A messaging framework including:
Define the principles (not the executions) for visual identity.
Discovery Questions:
Output: Visual principles document including:
Define where and how the brand shows up.
Discovery Questions:
Output: Channel matrix with:
Define what success looks like.
Discovery Questions:
Output: Measurement dashboard including:
After completing all 7 phases, compile a Brand Strategy Document containing:
Format as a professional strategy document suitable for stakeholder presentation.
User: "Help me create a brand strategy for my new coffee subscription service" → Begin with Phase 1 (Brand Truth) discovery questions
User: "I need to define our target audience" → Jump to Phase 2 (Audience Architecture) but note that Brand Truth should come first if not already defined
User: "Can you write our brand messaging?" → Jump to Phase 4 (Messaging Framework) but confirm Phases 1-3 are complete or gather that context first
User: "Review my brand strategy" → Evaluate against the 7-part framework, identify gaps, suggest improvements
| Error | Cause | Resolution | |-------|-------|------------| | Authentication failure | Invalid or expired credentials | Refresh tokens or re-authenticate with branding | | Configuration conflict | Incompatible settings detected | Review and resolve conflicting parameters | | Resource not found | Referenced resource missing | Verify resource exists and permissions are correct |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→pass | 5,562 | 6,362 | +14% | 1 | 1 | 0% | 990 | 2,587 | +161% | 0 | 0 | — |
case-06 | fail→pass | 20,136 | 9,982 | -50% | 1 | 1 | 0% | 3,028 | 3,106 | +3% | 0 | 0 | — |
case-01 | fail→fail | 8,977 | 4,441 | -51% | 1 | 1 | 0% | 1,449 | 2,220 | +53% | 0 | 0 | — |
case-02 | fail→fail | 9,794 | 6,080 | -38% | 1 | 1 | 0% | 1,630 | 2,439 | +50% | 0 | 0 | — |
case-03 | fail→pass | 26,188 | 9,237 | -65% | 1 | 1 | 0% | 4,166 | 3,008 | -28% | 0 | 0 | — |
case-04 | pass→pass | 11,515 | 4,027 | -65% | 1 | 1 | 0% | 1,902 | 2,081 | +9% | 0 | 0 | — |
case-07 | pass→pass | 16,812 | 7,749 | -54% | 1 | 1 | 0% | 2,650 | 2,691 | +2% | 0 | 0 | — |
case-08 | pass→pass | 17,718 | 9,727 | -45% | 1 | 1 | 0% | 2,774 | 3,048 | +10% | 0 | 0 | — |
case-09 | fail→pass | 20,192 | 15,349 | -24% | 1 | 1 | 0% | 3,345 | 3,921 | +17% | 0 | 0 | — |
case-10 | pass→pass | 17,370 | 9,636 | -45% | 1 | 1 | 0% | 2,745 | 2,636 | -4% | 0 | 0 | — |
case-11 | fail→pass | 19,153 | 13,420 | -30% | 1 | 1 | 0% | 3,122 | 3,579 | +15% | 0 | 0 | — |
case-12 | fail→pass | 17,533 | 9,036 | -48% | 1 | 1 | 0% | 2,947 | 3,113 | +6% | 0 | 0 | — |
case-13 | fail→pass | 9,398 | 7,305 | -22% | 1 | 1 | 0% | 1,434 | 2,479 | +73% | 0 | 0 | — |
case-14 | fail→pass | 8,442 | 8,624 | +2% | 1 | 1 | 0% | 1,439 | 2,811 | +95% | 0 | 0 | — |
case-15 | pass→pass | 25,422 | 23,391 | -8% | 1 | 1 | 0% | 4,083 | 5,206 | +28% | 0 | 0 | — |
case-16 | fail→pass | 14,811 | 9,957 | -33% | 1 | 1 | 0% | 2,259 | 2,831 | +25% | 0 | 0 | — |
case-17 | pass→pass | 14,617 | 10,556 | -28% | 1 | 1 | 0% | 2,342 | 3,092 | +32% | 0 | 0 | — |
case-18 | pass→pass | 17,642 | 13,884 | -21% | 1 | 1 | 0% | 2,499 | 3,664 | +47% | 0 | 0 | — |
case-19 | pass→pass | 15,492 | 11,931 | -23% | 1 | 1 | 0% | 2,266 | 3,202 | +41% | 0 | 0 | — |
case-20 | pass→pass | 6,235 | 9,107 | +46% | 1 | 1 | 0% | 1,202 | 3,496 | +191% | 0 | 0 | — |
case-21 | pass→pass | 11,500 | 6,675 | -42% | 1 | 1 | 0% | 1,762 | 2,662 | +51% | 0 | 0 | — |
case-22 | pass→pass | 17,273 | 12,959 | -25% | 1 | 1 | 0% | 3,508 | 4,296 | +22% | 0 | 0 | — |
case-23 | pass→pass | 6,713 | 5,760 | -14% | 1 | 1 | 0% | 1,207 | 2,423 | +101% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +39 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.