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 hanzhcn/laohan-skills --skill laohan-chuangzuogit clone --depth 1 https://github.com/hanzhcn/laohan-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/hanzhcn/laohan-skills/laohan-chuangzuo)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-chuangzuo"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-chuangzuo/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/hanzhcn/laohan-skills/laohan-chuangzuo"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-chuangzuo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 332 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- low MCP Rug Pull · line 427 pip install without ==version installs the latest release, which could include malicious changes.Fix: Pin the version: pip install package==1.2.3
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 | $0.00176 | $0.10063 |
| Opus 5 | $0.00088 | $0.05032 |
| Sonnet 5 | $0.00035 | $0.02013 |
| Haiku 4.5 | $0.00018 | $0.01006 |
Grade A, and why
laohan-chuangzuo 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 11d 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 — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
统一创作引擎
所有涉及口播稿写作统一调用本 skill。一份方法论，一个入口。
核心理念
一份方法论、一个入口——所有写作走同一个管线，避免不同入口产出质量参差不齐。素材先整理（Layer A/B）再写稿，确保口播稿建立在结构化理解之上，而非对原始素材的直接改写。
内容长度由独立内容单位决定，不由预设字数或分钟数决定。内容重复与人味废话是两条不同的审计线：同一判断换词复述必须合并；结巴、语气词、自嘲、反问和停顿继续按风格保留，不能因去重被误删，也不能冒充内容增量。
不适用场景
- 纯文本摘要/总结 → 用 summarize skill，不走创作流程
- 翻译 → 直接翻译，不需要口播稿格式
- 学术论文/技术文档写作 → 输出格式是口播稿，不适合正式文档
知识来源（唯一正本，symlink 到 OpenClaw workspace）
- 写作规则：
references/style.md（恢复 2026-07-11 前实战版本）。其中开场、转场、修辞、标题公式、场景密度、节奏、口头禅和模板均为已验证的默认方法；允许按本题增删或扩充，但不得以“防模板化”为由整体降级成可有可无的抽象建议 - 整理方法：
references/skill.md→~/.openclaw/workspace-reviewer/knowledge/skill.md（进宝 skill.md v3.5） - 转录方法：
references/transcription.md（音频提取 + 语音转文字三级降级） - 转译选题法：
references/yuanchuang-method.md（转译选题法 + 角度库 + 标题公式 + 数据基准）。本 skill 不再自带热点搜索；此方法供工作流①前置阶段复用——①用 laohan-redian/laohan-douyinsousuo 出选题后，按本文件规则生成大纲再喂入本 skill 大纲模式 - 写作风格目录：
references/styles/（每份 .md 是一种写作结构框架，Step -1 强制选择） - 创作机械合同：
references/creation-contract.md（Episode schema 4的采访/大纲确认、内容单位、逐段审计、人味、自然时长、TTS与validator；独立模式兼容schema 3）
GitHub 上是实体文件（拷贝），本地用 symlink 自动同步。
输入模式
| 模式 | 输入 | 触发场景 | 内部处理 |
|---|---|---|---|
| 大纲模式 | 结构化大纲文件 | 工作流①前置产出 / 外部传入 | 跳过整理，从 Step 2 开始 |
| 素材模式 | 原始文本/转录稿 | 录屏转录后、URL抓取后 | 先 Layer A/B 整理，再写稿 |
| 自由模式 | 主题关键词 或 无输入 | 用户直接调用 | 先生成大纲→确认→写稿 |
前置处理（将各种输入转化为三种模式）
Pre-A：录屏预处理
触发：用户提供了视频文件（mp4/mov 等）或说"录屏转口播""视频转口播稿"。
- 提取音频：
ffmpeg -i "<视频路径>" -vn -acodec libmp3lame -q:a 2 "/tmp/录屏音频_$(date +%s).mp3" -y - 语音转文字：三级降级（详见
references/transcription.md）- 硅基流动 API（免费，秒级）→ whisper-cli（本地快）→ Python whisper（最准）
- 独立写作时转录结果保存为
output/transcript-YYYY-MM-DD.md；Episode 模式保存为episodes/<slug>/02-创作工作稿/transcript.md，自动进入素材模式。
Pre-B：URL 队列预处理
触发：用户说"根据链接改写""链接内容改写""改写文档"。
- 读取队列：独立写作检查
<cwd>/url.md；Episode 模式只检查episodes/<slug>/02-创作工作稿/url.md，找第一个- [ ]且后面有 URL 的行- 没有待处理 → 告诉用户"队列为空"，结束
- 抓取内容：根据平台自动选择方法（参考 laohan-xiazai 路由）
- 抖音：移动端 UA → iesdouyin.com
- B站：opencli bilibili
- 其他：Jina Reader / agent-reach
- 独立写作时内容保存为
output/content-YYYY-MM-DD.md；Episode 模式保存为episodes/<slug>/02-创作工作稿/content.md，进入素材模式。 - 完成后更新队列：将 url.md 中对应行改为
- [x] URL 关键词 ✅ YYYY-MM-DD
What ships with it
9 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.
- references/creation-contract.md 14 KB
- references/multi-platform-publish-contract.md 2.9 KB
- references/skill.md 12 KB
- references/style.md 22 KB
- references/styles/教程型口播稿.md 15 KB
- references/transcription.md 1.7 KB
- references/yuanchuang-method.md 6.5 KB
- scripts/check-research-source-contract.mjs 6.3 KB runs code
- scripts/check-script-contract.mjs 38 KB runs code
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.
- 11d ago First seen · 467 lines · 176 tokens per session scan A 8d22bff81e01
laohan-chuangzuo is a skill published in the GitHub repository hanzhcn/laohan-skills (11 stars, last pushed today), licensed MIT. It adds 176 tokens to every session and 10,063 once invoked, about $0.0009 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
officecli-pitch-deck
Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet…
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
morph-ppt-3d
3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.
bilibili-upload
A workflow for using the sau command-line tool to log in to Bilibili, a Chinese video-sharing platform, check an account, and upload videos.
video-director
A general workflow for AI video requests, covering video creation, planning, editing, storyboards, keyframes, reference images, and talking-head characters.
cosyvoice-ssml
An internal skill for the CosyVoice text-to-speech step in approved digital-person and character voice-video workflows. It is not intended for ordinary chat, audio, short-video, product-video, or advertising requests.