feat(baoyu-comic): add batch generation policy with configurable batch size

skills/baoyu-comic/references/config/first-time-setup.md

@@ -143,12 +143,15 @@ preferred_layout: null
 preferred_aspect: null
 language: [selected or null]
 preferred_image_backend: auto
+generation_batch_size: 4
 character_presets: []
 ---
 ```
 
 `preferred_image_backend: auto` is the baked-in default — first-time setup does not ask about it. The `## Image Generation Tools` rule in SKILL.md then picks the runtime-native tool (Codex `imagegen`, Hermes `image_generate`, etc.) when available, and falls back to installed backends.
 
+`generation_batch_size: 4` is the baked-in default for page batch rendering. The current user request may override it for one run.
+
 ## Modifying Preferences Later
 
 See the `## Changing Preferences` section in `SKILL.md` for the canonical list of common edits (pin backend, change defaults, retrigger setup). Full schema: `config/preferences-schema.md`.

skills/baoyu-comic/references/config/preferences-schema.md

@@ -25,6 +25,8 @@ language: null            # zh|en|ja|ko|auto
 
 preferred_image_backend: auto  # auto|ask|<backend-id>
 
+generation_batch_size: 4       # 1-8, used when backend/runtime supports batch or parallel page generation
+
 character_presets:
   - name: my-characters
     roles:
@@ -49,6 +51,7 @@ character_presets:
 | `preferred_aspect` | string | null | Aspect ratio (3:4, 4:3, 16:9) |
 | `language` | string | null | Output language (null = auto-detect) |
 | `preferred_image_backend` | string | `auto` | Image backend selection. `auto` = prefer runtime-native tool, fall back to the only installed backend, ask if multiple non-native are present. `ask` = always confirm on every run. `<backend-id>` (e.g., `codex-imagegen`, `baoyu-imagine`, `image_generate`) = pin this backend when available; fall back to `auto` when it isn't. Absent = `auto`. Resolution logic is documented in `SKILL.md`'s `## Image Generation Tools` section. |
+| `generation_batch_size` | int | 4 | Number of page images to dispatch per batch when the backend has native batch support or the runtime can issue parallel generation calls. Clamp invalid values to 1-8. Current user request overrides this value. |
 | `character_presets` | array | [] | Preset character roles for styles like ohmsha |
 
 ## Art Style Options
@@ -127,6 +130,8 @@ language: zh
 
 preferred_image_backend: codex-imagegen
 
+generation_batch_size: 4
+
 character_presets:
   - name: tech-tutorial
     roles:

skills/baoyu-comic/references/workflow.md

@@ -488,12 +488,19 @@ When character sheet was skipped or `--ref` failed:
 - No `--ref` parameter needed
 - Rely on detailed text descriptions for character consistency
 
-**For each page (cover + pages)**:
-1. Read prompt from `prompts/NN-{cover|page}-[slug].md`
-2. **Backup rule**: If image file exists, rename to `NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.png`
-3. Generate image using Strategy A, B, or C
-4. Save to `NN-{cover|page}-[slug].png`
-5. Report progress after each generation: "Generated X/N: [page title]"
+**Page batch generation (cover + pages)**:
+1. Build a page task list from selected saved prompts:
+   - `prompt_file`: `prompts/NN-{cover|page}-[slug].md`
+   - `output_file`: `NN-{cover|page}-[slug].png`
+   - `aspect_ratio`: from storyboard (default `3:4`; preset may override)
+   - `refs`: character sheet and verified direct user refs when Strategy A is active
+2. **Backup rule**: Before dispatching a task, if its image file exists, rename it to `NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.png`.
+3. Dispatch tasks in batches:
+   - Native batch backend: send all eligible page tasks, or chunks of `generation_batch_size` if the backend has a practical limit.
+   - Runtime parallel calls: issue up to `generation_batch_size` image calls concurrently, then continue with the next chunk.
+   - Sequential fallback: process one page at a time.
+4. After each completed task, report: "Generated X/N: [page title]".
+5. On failure, retry the failed task once from the same saved prompt file. Keep successful outputs and continue.
 
 **Session Management**:
 If image generation skill supports `--sessionId`: