Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aliang2052/aliang-skills --skill aliang-picturebook-audiobookgit clone --depth 1 https://github.com/aliang2052/aliang-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aliang2052/aliang-skills/aliang-picturebook-audiobook)<a href="https://agentmods.dev/skills/aliang2052/aliang-skills/aliang-picturebook-audiobook"><img src="https://agentmods.dev/badge/skills/aliang2052/aliang-skills/aliang-picturebook-audiobook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aliang2052/aliang-skills/aliang-picturebook-audiobook"><img src="https://agentmods.dev/badge/skills/aliang2052/aliang-skills/aliang-picturebook-audiobook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00134 | $0.01198 |
| Opus 5.5 | $0.00054 | $0.00479 |
| Sonnet 5.5 | $0.00027 | $0.00240 |
| Haiku 4.5 | $0.00013 | $0.00120 |
Grade A, and why
aliang-picturebook-audiobook scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
儿童有声绘本制作
把一个主题做成有声绘本:AI 写故事 → 分段 → 多音色配音 → 统一画风配图 → 合成网页版(+可选视频/音频)。全程用百炼 bl CLI,最后用本 skill 的脚本组装。
前置
bl(百炼 CLI) 必须可用,已登录(bl auth status可查)。- 导出 mp4 / 合并音频需要
ffmpeg(网页版不需要)。
工作流(4 步)
开工前先和用户确认 2 件事(其余用默认):① 故事主题(必问);② 要哪些产物(网页版默认必出;是否再加 mp4 视频 / 纯音频 mp3)。段数默认 6、年龄默认 4-8 岁、画风默认水彩绘本,用户没特别要求就别追问。
1. 生成故事 → story.json
读 references/story_prompt.md,填好主题/段数,用 bl text chat --message "<prompt>" --output json 生成,按该文件的解析片段提取成 story.json。
- 若
json.loads报错(多为对白用了英文引号),强调 prompt 第 7 条重新生成,不要手工修补。 - 生成后把 story.json 的角色/分段简要念给用户看一眼。
2. 选画风(按故事内容推荐,用户确认)
读 references/styles.md,按故事题材匹配出推荐画风,再用 AskUserQuestion 把 7 种预设给用户挑(推荐项放第一个标「(推荐)」)。例如中国神话题材推荐「国潮插画」。用户选定后作为下一步的 --style 值。
3. 配音 + 配图(脚本一把梭)
画风定了后,直接跑构建脚本,它会逐段 TTS + 文生图并组装产物:
python3 scripts/build_audiobook.py --story story.json --outdir <项目目录> --style <画风名> [--web] [--video] [--merge-audio] [--all]
--style传预设名(见 styles.md)即可;不传默认「水彩绘本」;也可传自定义画风描述文字。- 不带产物标志默认只出网页版;
--all= 网页+音频+视频。 - 音色自动分配(旁白固定 + 角色轮流),情绪用 rate/pitch 表达。细节与坑见
references/voices.md,动手前务必读它(最关键:系统音色加--instruction会报 428,所以禁止用 instruction)。多音色生效的前提是故事 segments 的 speaker 分给了不同角色(见 story_prompt.md 第 6 条)。 - 改了文字/换画风后只重跑:换
--style重跑即可;只重建网页(不重出媒体)加--skip-media。
4. 交付
产物在 <项目目录>/:index.html(网页版,双击或 open 即看)、audio/seg_NN.wav、images/seg_NN.png,以及可选 <标题>.mp4、<标题>_audio.mp3。最后用 open index.html 给用户预览。
产物形态
- 网页版(默认):单 HTML 翻页播放器,逐段大图+字幕+朗读,音频播完自动连播,支持上/下一段、进度条、圆点跳转、键盘 ←/→/空格。模板见
assets/player_template.html。 - mp4 视频版:图片+音频用 ffmpeg 合成 720p 视频,发抖音/视频号用。
- 纯音频 mp3:各段合并成一个文件,喜马拉雅/睡前播放用。
story.json 结构
{
"title": "书名",
"characters": [{"name":"旁白","role":"narrator","trait":"温柔讲述者"}],
"segments": [{"id":1,"speaker":"旁白","text":"朗读文字(对白用中文全角引号)",
"emotion":"温柔讲述","image_prompt":"该段画面描述","voice":"<可选,覆盖音色>"}]
}
segments 数量任意;emotion 取值见 references/voices.md 的映射表。
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 62 lines · 134 tokens per session scan A d311f61276c6
aliang-picturebook-audiobook is a skill published in the GitHub repository aliang2052/aliang-skills (30 stars, last pushed 4mo ago), licensed MIT. It adds 134 tokens to every session and 1,198 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
aliang-picturebook-audiobook compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aliang-picturebook-audiobookaliang2052/aliang-skills | Skill | 30 | 4mo ago | MIT | A | 134 | Claude Code, Codex |
| freezonedramaclaw/dramaclaw | Skill | 7.3k | 2d ago | none | A | 49 | Claude Code, Codex |
| sketch-correction-workerdramaclaw/dramaclaw | Skill | 7.3k | 2d ago | none | A | 88 | Claude Code, Codex |
| dramaclaw-workflowsdramaclaw/dramaclaw | Skill | 7.3k | 2d ago | none | A | 60 | Claude Code, Codex |
| workflowsdramaclaw/dramaclaw | Skill | 7.3k | 2d ago | none | A | 56 | Claude Code, Codex |
| dramaclawdramaclaw/dramaclaw | Skill | 7.3k | 2d ago | none | A | 87 | Claude Code, Codex |
| sketch-storyboard-directordramaclaw/dramaclaw | Skill | 7.3k | 2d ago | none | A | 55 | Claude Code, Codex |