sn-infographic

1# sn-infographic
2 
3Info graphic generation scene skill (tier 1), relying on the `sn-image-generate`, `sn-image-recognize`, and `sn-text-optimize` tools provided by `sn-image-base` (tier 0).
4 
5Features:
6 
7- Evaluation of prompt quality (auto mode)
8- Prompt expansion (force/auto mode)
9- Multiple rounds of image generation and VLM review
10- Output the best result based on quality ranking
11 
12## Input Specification
13 
14| Parameter | Type | Default Value | Description |
15|-----------|------|---------------|-------------|
16| `user_prompt` | string | **Required** | Original user request. UTF-8 text; may include Markdown, URLs, or structured data. Length bounded only by the underlying LLM context budget. |
17| `max_rounds` | int | `1` | Maximum number of generation rounds. Valid range: `1`–`8`. When `max_rounds=1`, the Step 3 VLM review and the early-termination check are both skipped. |
18| `output_mode` | string | `friendly` | `friendly`: one-line content description + rank=1 single image |
19|               |        |               | `verbose`: full quality ranking + timing stats + all images (ordered by rank) |
20| `prompts_expand_mode` | string | `auto` | `auto`: evaluate `user_prompt` quality first; enter Step 2 expansion only when it falls short |
21|                       |        |          | `force`: skip evaluation, always execute Step 2 expansion |
22|                       |        |          | `disable`: skip Step 2, use `user_prompt` directly as `expanded_prompt` |
23…