scoutlisted
Install: claude install-skill mickeyyaya/evolve-loop
# scout
> Sprint 3 composable skill (v8.16+). Inspired by `addyosmani/agent-skills/spec-driven-development`. Invoked as `/evolve-loop:scout` and called by the `loop` macro.
## When to invoke
- Cycle goal is one line ("add fan-out to auditor") and details haven't been fleshed out
- The change touches multiple files
- About to make an architectural decision
## When NOT to invoke
- Cycle goal already has explicit task list with file paths
- Single-line bug fix
- Pre-defined task from `failedApproaches` retry queue (the spec already exists)
## Workflow
| Step | Action | Exit criteria |
|---|---|---|
| 1 | Read cycle goal from `.evolve/state.json` | Goal extracted |
| 2 | List explicit assumptions about scope, stack, constraints | At least 3 numbered assumptions |
| 3 | Identify dependency graph (what depends on what) | Dependency tree drawn |
| 4 | Surface unknowns + risks | Risks enumerated with mitigation hints |
| 5 | Write spec to `<workspace>/spec.md` | File present, fresh, contains challenge token |
## Spec format (standalone deliverable)
Spec at `<workspace>/spec.md` with sections:
- `## Goal` (one paragraph)
- `## Assumptions` (numbered list)
- `## Dependency Graph` (text or ASCII)
- `## Risks` (table: risk / likelihood / mitigation)
- `## Out of Scope` (explicit deferrals)
<!-- GENERATED:phase-facts BEGIN — do not edit; run `evolve skills generate`. Sources: docs/architecture/phase-registry.json · go/internal/phasecontract · .evolve/profiles/scout.json -->
## P