think

Think — Mid-Process Brainstorming & Decision Support

The pipeline builds. This skill thinks. Use it whenever you need to pause, explore, or decide.

When to use: Between any two pipeline steps. During /fill when you're unsure about a section. Before /create when choosing a product type. Before /publish when evaluating readiness.

When NOT to use: For mechanical tasks (/validate, /package). Those have deterministic flows — thinking slows them down.

---

Activation Protocol

1. Shared preamble: Load references/quality/activation-preamble.md — context assembly, persona adaptation, deterministic routing rules.
2. Read creator.yaml → adapt to profile.type and technical_level
3. If a product is active (workspace/{slug}/ exists), read .meta.yaml → understand current context
4. Parse $ARGUMENTS or conversation context to identify the thinking need
5. Route to the appropriate thinking mode
6. Load voice identity: Load references/quality/engine-voice-core.md. Every user-facing line in this skill honors the ✦ signature, three tones, and six anti-patterns. 5b. Load UX vocabulary: Load references/ux-vocabulary.md — translate all internal terms before creator-facing output. 5c. Load proactives: Load references/engine-proactive.md — wire #17 (lost creator detection: if the creator has been in /think for 3+ questions without resolution, suggest concrete next step or /scout).

---

Thinking Modes

MODE 1: Brainstorm (divergent)

Trigger: "brainstorm", "ideas for", "what could", "possibilities"

Generate 5-7 distinct approaches to the creator's question. For each:

• Name it in 3 words
• One sentence description
• Strength (why this works)
• Risk (why it might not)

End with: "Which resonates? Or want me to combine elements from multiple?"

MODE 2: Evaluate (convergent)

Trigger: "evaluate", "compare", "which is better", "pros and cons"

Structure the evaluation as a decision matrix:

EVALUATING: {what's being compared}

| Criterion | Option A | Option B | Option C |
|-----------|----------|----------|----------|
| {criterion_1} | {score/assessment} | ... | ... |
| {criterion_2} | ... | ... | ... |

RECOMMENDATION: {option} because {one-sentence reasoning}
RISK: {what could go wrong with the recommendation}