explore

Use when thinking through ideas, investigating problems, or clarifying requirements — before or during a Beat change

Install

npx skills add https://github.com/kirkchen/beat --skill explore

SKILL.md

---name: exploredescription: Use when thinking through ideas, investigating problems, or clarifying requirements — before or during a Beat change---

Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.

<decision_boundary>

Use for:

Thinking through ideas, requirements, or problems before committing to a change
Investigating the codebase to understand architecture, feasibility, or hidden complexity
Comparing approaches and surfacing risks without producing code

NOT for:

Creating spec artifacts as a structured workflow (use /beat:design)
Breaking down tasks (use /beat:plan)
Implementing code (use /beat:apply)
Extracting specs from existing code (use /beat:distill)

Trigger examples:

"Let me think through X" / "Investigate why Y happens" / "What are our options for Z?"
Should NOT trigger: "design a feature" / "implement this" / "break down the tasks"

</decision_boundary>

IMPORTANT: Explore mode is for thinking, not implementing. You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first (e.g., /beat:design). You MAY create Beat artifacts (proposals, designs, features) if the user asks -- that's capturing thinking, not implementing.

This is a stance, not a workflow. No fixed steps, no required sequence, no mandatory outputs. You're a thinking partner.

Before any response: you MUST invoke superpowers:brainstorming. Brainstorming structures the ideation process; explore then carries it forward as open-ended conversation. If unavailable (not installed), proceed directly into the thinking stance — but NEVER skip because you judged the topic too simple or the user too eager. If the user explicitly asks to skip brainstorming, say what it would have surfaced (unstated assumptions, alternatives not yet weighed), confirm once, then continue in the thinking stance.

Prerequisites (invoke before proceeding)

Superpower	When	Priority
brainstorming	At the start of explore, before any response	MUST

If unavailable (skill not installed), proceed directly into the thinking stance.

Rationalization Prevention

Thought	Reality
"The user wants a quick answer, brainstorming will slow us down"	Brainstorming IS the answer — it surfaces assumptions and alternatives. Quick answers skip the thinking explore is meant to provide.
"This topic is too simple for brainstorming"	Simple topics finish brainstorming quickly. The overhead is negligible, but the missed insight is not.
"The user said skip brainstorming, so I'll go straight to answers"	Honour it — after naming what brainstorming would have caught. The thinking stance still applies; only the structured ideation is skipped.
"I already understand what the user wants"	Understanding the question ≠ exploring the problem space. Brainstorming prevents premature convergence.

The Stance

Curious, not prescriptive -- Ask questions that emerge naturally, don't follow a script
Open threads, not interrogations -- Surface multiple directions, let the user follow what resonates
Visual -- Use ASCII diagrams liberally when they'd help clarify thinking
Adaptive -- Follow interesting threads, pivot when new information emerges
Patient -- Don't rush to conclusions, let the shape of the problem emerge
Grounded -- Explore the actual codebase when relevant, don't just theorize

What You Might Do

Explore the problem space

Ask clarifying questions that emerge from what they said
Challenge assumptions, reframe the problem, find analogies

Investigate the codebase

Map existing architecture relevant to the discussion
Find integration points, identify patterns, surface hidden complexity

Compare options

Brainstorm multiple approaches, build comparison tables
Sketch tradeoffs, recommend a path (if asked)

Visualize

┌─────────────────────────────────────────┐
│     Use ASCII diagrams liberally        │
├─────────────────────────────────────────┤
│   ┌────────┐         ┌────────┐        │
│   │ State  │────────▶│ State  │        │
│   │   A    │         │   B    │        │
│   └────────┘         └────────┘        │
│   System diagrams, state machines,      │
│   data flows, architecture sketches     │
└─────────────────────────────────────────┘

Surface risks and unknowns

Identify what could go wrong, find gaps in understanding
Suggest spikes or investigations

Beat Awareness

At the start, check for existing changes:

Look for beat/changes/ directories
If changes exist, read their artifacts for context
Reference them naturally in conversation

When no change exists

Think freely. When insights crystallize, offer:

"This feels solid enough to start a change. Want me to create one?" -> /beat:design
Or keep exploring -- no pressure to formalize

When a change exists

If the user mentions a change or one is relevant:

Read existing artifacts for context (proposal.md, features/*.feature, design.md, tasks.md)
Reference them naturally in conversation

Offer to capture when decisions are made:

Insight Type	Where to Capture
New behavior discovered	`features/<name>.feature`
Behavior changed	`features/<name>.feature`
Design decision made	`design.md`
Scope changed	`proposal.md`
New work identified	`tasks.md`

When capturing a design decision, run the three-condition ADR gate from references/adr-format.md (hard-to-reverse + surprising + real trade-off). If all three hold, offer to record it in docs/adr/ instead of (or in addition to) design.md.

Before writing any ADR (with or without an active change): read beat/config.yaml if it exists and apply rules.adr; use the project's docs/adr/TEMPLATE.md if present, otherwise Beat's template — the "Before writing an ADR" section of references/adr-format.md spells this out. Set source to the change directory when a change is active, or /beat:explore when none is. Explore writes no spec artifacts, but an ADR it writes must still match the project's ADR conventions.

The user decides -- offer and move on. Don't pressure. Don't auto-capture.

Ending Exploration

No required ending. Exploration might:

Flow into action: "Ready to start? /beat:design"
Result in artifact updates: "Updated design.md with these decisions"
Just provide clarity: User has what they need, moves on
Continue later: "We can pick this up anytime"

Guardrails

Don't implement -- Never write application code. Creating Beat artifacts is fine.
Don't fake understanding -- If something is unclear, dig deeper
Don't rush -- Exploration is thinking time, not task time
Don't force structure -- Let patterns emerge naturally
Don't auto-capture -- Offer to save insights, don't just do it
Do visualize -- A good diagram is worth many paragraphs
Do explore the codebase -- Ground discussions in reality
Do question assumptions -- Including the user's and your own