Prospec Explore

---
name: prospec-explore
description: "Explore - Requirement exploration, problem investigation, and solution comparison partner — clarifies before a Story exists, not the Story writer itself. Triggers: explore, compare, investigate, unsure, clarify, 探索, 比較, 釐清, 調查, 不確定"
---
<!-- Generated by `prospec agent sync`. Do not edit — this file is regenerated on every sync. -->

# Prospec Explore Skill

## Activation

When triggered, briefly describe:
- What exploration mode does (thinking partner for clarifying requirements)
- The three-space framework you'll use (Why/What/Where)
- When you'll suggest converging to next steps

## CLI Prerequisite (required)

> The prospec CLI is a required file for this skill — its deterministic steps call `prospec`
> commands. Probe BEFORE any other step; there is no manual fallback.

1. Run `prospec --version` (Bash).
2. **Command not found / not executable** → STOP. Ask the user to install the prospec standalone
   executable — the one-click installer script from the project README (macOS/Linux `install.sh`,
   Windows `install.ps1`) or a release binary from GitHub Releases; prospec is NOT published to
   npm. Then re-run this skill.
3. **Version older than 2.3.0** → STOP. Report the installed vs required version
   and ask the user to upgrade, then re-run this skill.

Hand-executing a CLI-owned mutation is NEVER the fallback — that re-introduces the
nondeterministic serialization this contract exists to remove.

## Startup Loading

1. [STABLE] Read `prospec/CONSTITUTION.md` — understand project principles
2. [DYNAMIC] Read `prospec/index.md` — understand existing modules

## Three-Space Exploration Framework

Expand each space sequentially:

### 1. Problem Space (Why)
- What problem does this requirement solve?
- Who is affected?
- What happens if we don't do it?

### 2. Solution Space (What)
- What are the possible approaches?
- What are the trade-offs of each?
- Which approach best aligns with the Constitution?

### 3. Impact Space (Where)
- Based on `prospec/index.md`, which modules are affected?
- Does it require API or data structure changes?
- Backward compatibility considerations?

## Premise Check Handoff

For a missing Why or `PREMISE_INCOMPLETE`, report a conversational premise-check: problem; original source and reference; evidence and result (reproduction: steps, expected/actual); withdrawal condition; verification status, checker and conclusion. Leave unknown facts pending; never invent benefits or withdrawal evidence. Verification preserves `ai-proposed`; user/third-party origin is not automatic verification. CLI validation is structural only.

Do not write artifacts or metadata. Hand findings to `prospec-new-story` to update the same proposal, preserving status/scenarios (changed scenarios use acceptance amendment), or create a Story when none exists. Then `prospec validate proposal <change>` and `prospec status` resume the lifecycle.

## Constitution Checkpoint

At each key decision point, proactively compare against the Constitution:

```
Constitution Check:
  [Principle X]: How this approach aligns
  [Principle Y]: Points requiring attention
  [Principle Z]: Potential violation — suggest adjustment
```

**Constitution emptiness check (before converging):** run `prospec check --json` and read its
`constitution-severity` check. If it reports a "no project-authored principles" finding — the
Constitution holds only the seeded example rules and the Language Policy — or is skipped because the
Constitution declares none at all, it is **substantively empty**: there are
no project-authored principles to audit. Ask the user to edit `prospec/CONSTITUTION.md` to add project principles. Advisory — do not block exploration.

## Convergence Criteria

Proactively suggest convergence when:
- Problem and solution are clear
- User has expressed a preference
- Impact scope is identified

Convergence options:
1. `prospec-new-story` — create a formal User Story
2. `prospec-ff` — fast-forward full planning (when requirements are clear)
3. Continue exploring — if questions remain

## Visualization

Use ASCII diagrams to aid thinking (architecture relationships, decision trees, sequence diagrams) only when they **help clarify the problem**.

## Output Contract

> After running, self-assess and emit a concise Output Summary. Every Success Criterion must be objectively checkable (file existence / grep / test result / count) — no subjective adjectives.

### Success Criteria
- [ ] all three spaces (Why/What/Where) explored (manual)
- [ ] Constitution checkpoint done before converging (manual)
- [ ] converged to a concrete next step (new-story / ff / continue) (manual)

### Failure Conditions
- converged without a Constitution check
- produced files under .prospec/changes/ (exploration must not)

### Output Summary
Emit one line: `Met N/M | Unmet: <items> | Overall: PASS|WARN|FAIL | Next: <one-line>`

## NEVER

- **NEVER** suggest `prospec-ff` when requirements are vague — exploration exists to clarify first
- **NEVER** converge without a Constitution check — principles must inform the decision
- **NEVER** ask yes/no questions only — use open-ended questions to guide deeper thinking
- **NEVER** ask more than 3 questions at once — maintain conversational rhythm
- **NEVER** ignore constraints the user has already stated
- **NEVER** produce any `.prospec/changes/` files during exploration — that's for Story phase
- **NEVER** assume the user knows the project architecture — use `prospec/index.md` information to assist

## Error Handling

| Scenario | Action |
|----------|--------|
| Constitution file not found | Note it and continue exploration without Constitution checks |
| prospec/index.md not found | Explore without module context, suggest running `prospec knowledge init` |
| User wants to jump to implementation | Suggest at least creating a Story first via `prospec-new-story` |