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 staruhub/ClaudeSkills --skill geek-skills-podcast-generatorgit clone --depth 1 https://github.com/staruhub/ClaudeSkillsWrote 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/staruhub/claudeskills/geek-skills-podcast-generator)<a href="https://agentmods.dev/skills/staruhub/claudeskills/geek-skills-podcast-generator"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-podcast-generator/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/staruhub/claudeskills/geek-skills-podcast-generator"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-podcast-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00140 | $0.01053 |
| Opus 5 | $0.00070 | $0.00526 |
| Sonnet 5 | $0.00028 | $0.00211 |
| Haiku 4.5 | $0.00014 | $0.00105 |
Grade A, and why
podcast-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
播客生成器（火山引擎双人对话）
把中文文本变成双人对话播客音频，接口封装在 scripts/generate_podcast.py。
验收标准（每次生成完成前自查）
- 音频文件已落盘，把实际路径与文件大小回报用户
- 输入文本 ≤25,000 字符（超长必须先与用户确认拆分方案，不能让模型静默截断）
- 生成中断时使用了 retry_info 续传而不是从头重来
- 参数选择有依据：分发用 mp3，后期加工用 pcm；教学内容语速 -20 左右
- 凭证缺失时未硬试：告知用户去火山引擎控制台（speech/service/10028）获取
不做什么
- 不写播客文稿——输入文本的质量是上游任务（文稿创作找写作类 skill）
- 不做单人朗读、配音、音效制作
- 不在输出里回显用户的 ACCESS_KEY
工作流程
1. 准备输入
必需：中文文本（≤25k 字符）+ APP_ID + ACCESS_KEY（无则告知获取方式后停止）。 可选：格式（默认 mp3）/ 采样率（默认 24000）/ 语速（-50~100，0=正常，100=2 倍速）/ 音色 / 开场音乐（默认关）。
最佳文本长度 500-3000 字——播客时长与听感的最优区间；一篇长文建议先摘要再生成。
2. 生成
python scripts/generate_podcast.py \
--text "播客话题或内容文本" \
--output "/path/to/output.mp3" \
--app-id "$VOLC_APP_ID" --access-key "$VOLC_ACCESS_KEY" \
--format mp3 --sample-rate 24000 --speech-rate 0
脚本会流式接收音频、按轮次显示进度、落盘后返回统计（大小/轮次数）。
Python 模块调用、自定义音色 ID、断点续传 retry_info 的写法见脚本内 docstring 与 references/api_reference.md。
3. 交付
回报文件路径、大小、时长预估;失败时给出具体错误与下一步(见陷阱表)。
已知陷阱
| 陷阱 | 具体表现 | 应对 |
|---|---|---|
| 超长静默截断 | >25k 字符时模型直接截断，播客缺尾 | 生成前校验长度，超长先与用户确认拆分或摘要 |
| WebSocket 连不上 | 连接错误/超时 | 依次排查：凭证是否正确 → 网络 → 防火墙是否放行 WebSocket |
| 中断后从头重试 | 长文本生成到一半断了，重跑烧双倍额度 | 从日志取 task_id 和 last_finished_round_id，用 retry_info 续传 |
| 输出路径不可写 | 生成完成但保存失败 | 生成前检查目录存在且可写、磁盘空间充足 |
| 文本结构差出烂稿 | 口水文本生成的对话生硬 | 输入用结构清晰的中文文本；效果差时先改文本再调参数 |
依赖与凭证
pip install websockets
凭证从火山引擎控制台获取（console.volcengine.com/speech/service/10028）。建议走环境变量,不要写进代码。
参考文档（按需加载）
references/api_reference.md— 完整参数规格、WebSocket 协议细节、事件类型、错误码;协议级调试时读scripts/generate_podcast.py— CLI 与模块双接口,含自动重试与流式接收实现
What ships with it
2 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.
- 13d ago First seen · 70 lines · 140 tokens per session scan A a60f9cd5c821
podcast-generator is a skill published in the GitHub repository staruhub/ClaudeSkills (712 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session and 1,053 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
report-helper
A Chinese-language research workflow that searches the internet and produces a formatted PDF report about a specified topic.
giasip-dispatch
A skill for sending a task to other AI models and collecting their results. It supports direct API calls, command-line tools and built-in internal agents, depending on the model.
searchcans-deep-research
Conduct bounded, evidence-led, account-aware web research with SearchCans SERP API and Reader API. Use for cited-source research that needs current localized web evidence, such as market, competitor, technology, policy, company, or product research; plan 3–5 subquestions, set a source budget, read selected pages…
searchcans-serp-content-gap
Analyze a current, geo-targeted Google or Bing SERP with SearchCans and turn observed result features, People Also Ask questions, related searches, knowledge graph, and news signals into an evidence-backed, account-aware content decision brief. Use for localized SEO/GEO planning, keyword research, competitor-page…
searchcans-market-watch
Build a current, geo-targeted market-watch snapshot from Google Search, Google News, Bing Search, and selected Reader extracts. Use for competitor and category monitoring, PR/news tracking, launch intelligence, and URL-level change checks between two bounded runs; reject malformed, placeholder, or un-attributable News…
searchcans-product-serp-brief
Create a localized product-search evidence brief from Google Shopping, Google web results, Google Images, and optional Reader extracts of explicit merchant URLs. Use for e-commerce category research, competitor assortment discovery, product-page planning, and market-specific merchandising briefs.