/explore

Divergent thinking — target three distinct feasible implementation options, then converge on a recommendation. Produces options, not plans.

Structured execution spec: protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the @STAMP date.

Brainstorming Protocol — explore before committing. /insight-explore generates alternatives (divergent). /insight-assess evaluates them (convergent). /plan-create designs the chosen approach.

Phase 1 — Divergence

1. Analyze constraints — what are we optimizing for? What are the hard requirements vs. preferences?
2. Option A: The Standard Pattern — the obvious, well-trodden approach. What would most engineers reach for first?
3. Option B: The Performance Way — optimized for speed, scale, or efficiency. Possibly more complex.
4. Option C: The Minimalist — YAGNI. Smallest footprint that still solves the problem.

Additional options may be added if the problem space warrants them (e.g., event-driven, type-safe, or zero-dependency variants).

Phase 2 — Convergence

Compare all options across:

• DX — developer experience, API ergonomics, debuggability
• Robustness — error handling, edge case coverage, failure modes
• Timeline fit — how long does each take to implement and validate?
• Alignment — does it match existing patterns and coding standards in the repo?

Phase 3 — Recommendation

Output:

• Winner — which supported option and why, or an explicit constrained/unresolved outcome with its decisive gap
• Reason — 1–2 sentences, referencing the comparison
• Next step — ask the user: "Shall I /plan-create this?"

Rules

• Target three distinct feasible options and search for at least two; if evidence supports only one or none, report that constrained or unresolved result, the bounded search scope and decisive gap. Never invent cosmetic alternatives or a winner.
• MUST NOT write code or make changes — this is ideation only.

Next Steps

• /insight-assess — evaluate the winner in depth before committing
• /plan-create — design the chosen approach

Human output. This skill's handler-facing output obeys the human-output contract (human-output/SKILL.md).

Next skills. On completion, run the Next Skills protocol (next-skills/SKILL.md): surface the next-skills recommendations from front-matter for the caller to pick. Offer only — never auto-invoke.

Self-improvement. On completion, run the Self-Improvement Protocol (self-improve/SKILL.md): apply its signal taxonomy and threshold to this run; surface any surviving proposal for handler approval. Conservative — silent otherwise. Never auto-apply.