# Headless Mode Load this file when xiaoma-create-story is invoked headless (no interactive user — e.g. by auto-prd-to-stories step-04, auto-story-pipeline, or auto-story-pipeline-batch). Follow it for the whole run. ## Detection Headless mode is in effect when any of the following is true: - the invoking caller sets a `headless: true` flag (or equivalent argument the harness exposes), - the invocation is from another skill or a non-interactive runner (no TTY, no user message stream), - `{workflow.activation_steps_prepend}` includes an entry that explicitly declares headless, - the first message comes from an automation context that pre-supplies the story key + inputs and asks for the story-file path back. When ambiguous, default to interactive. ## Inputs the caller is expected to provide - `sprint-status.yaml` (the story queue) and `epics.md` / `prd.md` (story source), - a target story key if a specific story is required; otherwise auto-discover the first `backlog` story, - `architecture_absent` (boolean) — whether architecture docs exist. ## General Do not ask, do not greet. Auto-discover (or use the provided) story key and walk every step to completion; auto-proceed through any prompt — never halt for input. The Step-6 checklist (`checklist.md`) is an interactive "quality-competition" review by default. In headless, perform that review **internally** — apply the warranted improvements to the story directly — instead of presenting the all/critical/select/none menu. Honor `architecture_absent`: when no architecture source covers a story's data model or logic, write the literal `TBD by architect — ` rather than fabricating detail or silently omitting the subsection. Record every inferred value as an assumption. ## Completion End by writing the story file `{story-key}.md` at status `ready-for-dev` (using the same slug convention as sprint-planning) and returning its path. Ignore the Step-6 "next steps" guidance (run dev-story / code-review) — the calling pipeline handles what comes next.