Activate when starting work with a new client, conducting a brand audit, benchmarking competitors, or answering 'where do we start' and 'what should we do'. Also activates when a brief feels incomplete or the real problem hasn't been named yet.
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.
Discovery is not a formality. It's the most critical phase — wrong diagnosis means wrong solution.
What the client says ≠ What the client needs ≠ What the market actually requires
Your job in discovery is to close this gap. Don't accept surface-level answers. Dig until you find the real problem.
Before any work begins, evaluate the brief:
| Signal | Problem | Action |
|---|---|---|
| "We need a new logo" | Solution stated, problem unknown | Ask: what's not working now and why? |
| "We need to look more premium" | Symptom stated, cause unknown | Ask: premium compared to whom, for whom? |
| "Our competitors are doing X" | Reactive thinking | Ask: what do YOU stand for, independent of competitors? |
| Vague target audience | No strategic foundation | Stop. Define audience before anything else. |
| No clear success metric | Can't evaluate outcomes | Ask: how will we know this worked? |
If the brief has 2+ of these signals — do not proceed to strategy. Run full discovery first.
Structure every discovery output as:
1. SITUATION — Where the brand actually is (not where they think they are)
2. REAL PROBLEM — The underlying issue (one clear sentence)
3. OPPORTUNITY — What can be built from here
4. UNKNOWNS — What we still need to find out before proceeding
5. NEXT STEP — Specific, not generic
Keep it sharp. A 2-page discovery report beats a 20-page one that no one reads.
Push back hard in these situations:
"We're in a hurry, skip discovery"
Discovery isn't a phase you skip — it's the phase that prevents you from building the wrong thing. A week of discovery saves months of revision.
"We already know our audience"
Tell me specifically who they are, what they believe, and what needs to change. If you can answer that in one sentence, we can move fast. If not, we need to spend time here.
"Just make it look like [competitor]"
Looking like a competitor means you'll always be second. Let's find what only you can own.
Discovery feeds directly into:
bb-brand-strategy — positioning, TOV, USPbb-brand-identity — if visual direction emergesbb-studio-ops — if scope needs to be redefined based on findings