agentmods.dev

laohan-chuangzuo

laohan-chuangzuo is a skill for Claude Code, Codex from hanzhcn/laohan-skills. It costs 177 tokens per session (15,083 once invoked), scanned A, original, MIT.

A writing workflow for spoken-video scripts. It accepts an outline, raw text, a recording, a web-link queue, or a free-form topic, then organizes the material before writing the script.

In plain words
What is it for?
Use it to write or rewrite a spoken script, turn a recording into a script, or create a script from an outline or source material.
Why use it?
It gives script writing one consistent process and helps keep repeated ideas separate from natural speech habits such as pauses, questions, and self-corrections.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

not rated 15repo changed 8d ago A scan SkillSpector: warn 177 tokens original MIT

Good fit Use it to write or rewrite a spoken script, turn a recording into a script, or create a script from an outline or source material.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hanzhcn/laohan-skills/laohan-chuangzuo
View source ↗ hanzhcn/laohan-skills
Install

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.

Any agent
npx skills add hanzhcn/laohan-skills --skill laohan-chuangzuo
Clone the repo
git clone --depth 1 https://github.com/hanzhcn/laohan-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for laohan-chuangzuo

README.md
[![agentmods](https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-chuangzuo/github.svg)](https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-chuangzuo)
Your own site
<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.

agentmods 80×15 button for laohan-chuangzuo

Your own site · 80×15
<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>
Per session 177 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00177 $0.15083
Opus 5.5 $0.00071 $0.06033
Sonnet 5.5 $0.00035 $0.03017
Haiku 4.5 $0.00018 $0.01508

Measured 8d ago against content hash cdff8dfd7f0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 8d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check-research-source-contract.mjs, scripts/check-script-contract.mjs, scripts/sepia-contract.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

laohan-chuangzuo/SKILL.md · 560 lines

How it starts

The opening of the file, as written. The whole thing — 560 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。

写作前材料交接

先执行references/creation-contract.md的“选题→写作的创作交接”：真实源文/主稿论证、核心判断、承诺所需材料和独立材料审核齐全才写。大纲只可跳重复抽取，不能跳知识理解；五种输入共用判据。操作/效果承诺实跑前置，Sepia不补论证。普通独立/系列草稿同样检查，历史已录制输入不重创作。

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。

正文立场与观众收获

执行视频项目docs/老韩创作六步法.md第1/4/5步：资料是论证依据，正文由老韩的有据判断和观众任务组织，不是原博主/文档的解说。来源与拆解记录保留在资料包；必要引用不冒充本人经历。观点稿交付具体立场与能改变的判断，教学稿兑现真实可完成的任务，不把两者写成泛泛提醒。内容不足回规划/材料，不交Sepia补观点。具体映射复用argument_plan、original_contributions和content_units.viewer_value，不另建轻合同或评分表。

教学按同一六步法“教学动作主线”：先提炼从起点到结果的真实操作，正文用连续1、2、3……编号及“第一步、第二步”口播，动作之间用完成状态、对象或因果自然衔接。每步讲清在哪里做什么、必要输入和可核结果；AI代办也要给具体发起方法，不能只说“交给AI”。不固定三步、不硬套五层铺垫；用户已要教学而材料不足，先补材料/验证，不静默改成只讲原理。视频项目默认作者分工以其生产合同§二为准，本skill不自行替换作者模型。

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
  • 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、标题公式和口头禅作为可选工具；按当前六步法判断适用性，不以数量/句长/禁词密度或旧稿节奏限制新题
  • 整理方法：references/skill.md → ~/.openclaw/workspace-reviewer/knowledge/skill.md（进宝 Layer A/B；材料完整不等于成稿全文照搬）
  • 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-xuanti/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
  • 镜头友好模式（可选扩展，默认关闭）：references/camera-friendly.md（四句式偏好 + 镜头结构 sidecar 契约；只在 Step 4 句式层叠加，不覆盖既有方法）
  • 写作风格目录：references/styles/（每份 .md 是一种写作结构框架，Step -1 明确选择依据）
  • 创作机械合同：references/creation-contract.md（Episode schema 4的选题/表达池绑定、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，历史采访合同仅对旧schema 3选题生效）
  • 方法论真源：项目docs/老韩创作六步法.md（定结构→选钩子三变体读选→铺内容含爆点分布/节奏锚点/情绪弧线→造记忆点含金句/评论区预设→HKRR自检→人味定稿+机械验收）；五波调研依据见script-pool/口播稿方法论调研-2026-09-17.md
  • 否稿改稿案例库：references/case-book.md（Jeffrey 真实裁决按"为何这样改/换条件怎么办/哪些用法会错"组织；修稿与吸收否稿意见前先查库，条件吻合按案例判断走，新裁决由当轮登记）

Read the full file on GitHub · 560 lines

Files

What ships with it

14 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.

Changes

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.

  1. 8d ago Changed · +18 lines cdff8dfd7f0b
  2. 10d ago Changed · +1 lines 5d06a96f53d7
  3. 12d ago Changed · +21 lines 1143dbf244d9
  4. 13d ago Changed · +3 lines 2bfff5759c80
  5. 14d ago Changed · +5 lines 5f7f8bcf5a68
  6. 15d ago Changed · +4 lines b7efa16232b4
  7. 20d ago Changed · +19 lines 3c2638ff9ff4
  8. 1mo ago Changed 1003a8ece20e
  9. 1mo ago Changed 60619296db17
  10. 1mo ago First seen · 489 lines · 177 tokens per session scan A c40a46ff0284

Subscribe to this mod's changes

laohan-chuangzuo is a skill published in the GitHub repository hanzhcn/laohan-skills (15 stars, last pushed yesterday), licensed MIT. It adds 177 tokens to every session and 15,083 once invoked, about $0.0007 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.

Claude CodeCreative and mediaWriting and docsai-contentbilibilidouyinopenclawskills
Related

laohan-chuangzuo compared with skills from other repositories

laohan-chuangzuo next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
laohan-chuangzuohanzhcn/laohan-skillsSkill15yesterdayMITA177Claude Code, Codex
baijiahao-uploaddreammis/social-auto-uploadSkill16k15d agoMITA49Claude Code, Codex
hupu-uploaddreammis/social-auto-uploadSkill16k15d agoMITA42Claude Code, Codex
douyin-uploaddreammis/social-auto-uploadSkill16k15d agoMITA93Claude Code, Codex
xiaohongshu-uploaddreammis/social-auto-uploadSkill16k15d agoMITA95Claude Code, Codex
adme-property-predictorLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA61Claude Code
Email Marketing Command CenterLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA29Claude Code, Codex