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 Morningstar202604/awesome-skillkit --skill ai-baby-podcastgit clone --depth 1 https://github.com/Morningstar202604/awesome-skillkitWrote 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/morningstar202604/awesome-skillkit/ai-baby-podcast)<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/ai-baby-podcast"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/ai-baby-podcast/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/morningstar202604/awesome-skillkit/ai-baby-podcast"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/ai-baby-podcast.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 | $0.00115 | $0.01871 |
| Opus 5 | $0.00057 | $0.00936 |
| Sonnet 5 | $0.00023 | $0.00374 |
| Haiku 4.5 | $0.00012 | $0.00187 |
Grade A, and why
ai-baby-podcast 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Baby Podcast (viral talking-character shorts)
The format: a baby (or toddler) face with an ADULT voice delivering confident opinions — the contrast IS the joke. Mature four-stage pipeline: 形象图 → 脚本 → 成人声 TTS → 口型驱动 → 剪辑发布. This skill orchestrates the whole line and enforces the two disciplines that separate hit accounts from one-hit wonders: character locking and platform compliance.
Red lines — read before anything else
- 必须声明 AI 生成:发布时勾选平台"内容由 AI 生成"声明,视频起始画面加显式提示 (文字高度 ≥ 画面最短边 5%、持续 ≥ 2 秒)。依据《人工智能生成合成内容标识办法》 (2025-09-01 施行);不标 → 平台检测后打"疑似AI"标签并限流/下架。
- 只用纯 AI 虚构婴儿形象。真实儿童照片即使自家孩子也不建议;绝不给真实未成年人 做口型让"他说了没说过的话"。原因:肖像权+平台对未成年人内容的重点审查。
- 不克隆名人声音/肖像(明星音色、名人婴儿化)除非拿到授权——平台与法律双重风险。
- 不做"AI幼儿专家育儿课"式误导题材——这是监管文件点名的整治对象。
Inputs
| Input | Required | Default | Notes |
|---|---|---|---|
| topic / 热梗 | yes | — | the baby's take |
| persona | no | 新建角色 | 新建 or 沿用既有角色卡 |
| format | no | 单人独白 | 单人 / 双人对谈 |
| target_platform | no | 抖音 | 决定画幅与标识细节 |
If topic is missing, ask ONCE:
请给出这期主题(蹭什么热梗/聊什么观点)。可选:用已有角色还是新建、 单人还是双人对话、发哪个平台(默认抖音竖屏)。
Character lock discipline (do this once, reuse forever)
Create character_bible.md containing:
① 形象参考图 prompt 原文;② 参考图文件(正面 + 左右侧 + 说话中表情 共 4–6 张,
同一 seed 生成);③ 锁定的 TTS 音色 ID 与参数;④ 3–5 条"不要"规则
(如"永远戴黑框眼镜""不换衣服颜色")。此后每期只用参考图驱动,永不从文字
重新生成角色;每 10 条视频把最新一帧与参考图并排对比一次(眼距/鼻形/发际线),
发现漂移立即从原始参考图重来。原因:漂移是掉粉第一杀手,观众认的是同一张脸。
Workflow
Step 1: 形象图
Prompt 公式(任何文生图工具均可,含本仓 image-generation 技能):
一个可爱婴儿坐在专业播客演播室里,戴黑框眼镜和头戴式耳机,对着嘴下方的 专业麦克风,正脸看镜头,嘴巴自然闭合,演播室灯光与吸音棉背景, 超写实照片风格,喜剧感。
Expected: 正面清晰单人脸、麦克风不遮挡嘴唇、光线均匀。失败分支:多人脸/ 侧脸/手挡嘴 → 加"single character, front-facing"重生成。生成后存入角色卡。
Step 2: 脚本(15–40 秒)
公式:前2秒钩子(反差宣言)→ 一个具体而自信的观点 → 一句反转或金句 → 固定结尾口癖。
Example skeleton: "关于<话题>,你们大人都想错了。<一个具体主张+理由>。
<金句反转>。我是XX,下次摇篮里接着聊。"
Rules: 口语短句(每句 ≤15 字);观点越成人化越好——反差来自内容与脸的错位;
双人对谈则写 A/B 交替台词并标注角色。
Step 3: TTS 配音
用任意 TTS 工具生成成人成熟声音(低音播音腔=经典配方;软萌童声只适合 亲子向温和内容)。语速调至 1.2–1.4 倍更贴短视频节奏。Expected: 干声 mp3/wav, 无 BGM 无混响——口型工具吃干净音频。锁定该音色写进角色卡,之后每期同一个声音。
What ships with it
1 file 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.
- 12d ago First seen · 122 lines · 115 tokens per session scan A aa1f0d5df44e
ai-baby-podcast is a skill published in the GitHub repository Morningstar202604/awesome-skillkit (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 115 tokens to every session and 1,871 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other skills, from other repositories
agentic-webdesign-html-anything
Install and use html-anything — the agentic HTML editor where your local AI agent writes HTML and you ship it. 75 skills × 9 surfaces, BYOK, zero API key. Use when building magazine articles, keynote decks, resumes, posters, social cards, web prototypes, data reports, or Hyperframes videos with AI coding agents.
blog-post
Full-stack blog post production — turns a topic, idea, or brief into a complete publishing package across written, social, and multimedia surfaces. Generates broomva.tech .mdx posts (or Substack/other long-form), X posts and threads, LinkedIn posts, Instagram posts and reel scripts, plus multimedia asset plans…
content-creation
Full-stack content creation pipeline: idea or reference to published blog post, audio narration, video, and social media distribution. Orchestrates research, reference extraction, storytelling, AI visual assets (Nano Banana, Veo 3.1), TTS audio (Voicebox, kokoro-tts, Edge TTS), Remotion video, and social copy into a…
citable
Make authored content survive the two selection surfaces it now faces: human engagement and LLM retrieval for citation. These partially anti-correlate, and the tactics that raise reactions are in two measured cases the ones that suppress citation. Encodes effect sizes from published causal studies (Scrunch, 12,000…
revenuecast
/revenuecast is the verb that turns what you can do into a machine that makes the world want it. You have a real capability — a craft, an expertise, a running system. revenuecast builds the loop where the capability's output becomes its own advertisement, and the demand that output creates is monetized by selling the…
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…