analyze

# Analyze — Tour Spec Authoring Read input artifact(s) and write a `tour-spec.json` that the renderer consumes. Hand off to `learning-guide:render` at the end. ## Trigger phrases - "create a learning guide for X" - "make an interactive tour" - "generate onboarding doc" - "build a learning module from this session" ## Inputs to collect from the user 1. **Source artifact path(s)** — required. One or more files/folders. 2. **Output directory** — default `<input-parent>/learning/`. 3. **Archetype hint** — optional; auto-detect with these rules: - Filename ends `.observations.md` OR YAML frontmatter contains `session_date:` → `planning-session`. - Input is a directory of source files with no obvious doc layer → `codebase`. - Input contains "Phase 1", "Phase 2", "rollout", "blockers" structure → `refactor-plan`. - Otherwise → `generic`. 4. **Language** — auto-detect from input text dominance; require >80% single-locale tokens to commit, otherwise default `en`. Always state the detected language and offer an override before drafting. ## Flow 1. **Resolve inputs.** Confirm path(s) and output dir before reading anything large. Reject non-existent paths. 2. **Pick archetype.** Auto-detect, state the choice, ask the user to confirm or override. 3. **Load archetype reference.** Read `references/archetype-<name>.md`. 4. **Survey the input.** - Codebase: structured exploration — entry points, module map, control flow. - Doc: top-to-bottom read. - Session: lift d...