⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

transcript-polish

@codingnoob4ever⭐ 1 stars

This skill should be used when the user wants to polish a raw spoken transcript from a recording into a clean verbatim script (逐字稿). It handles very long texts of 30000 or more characters by processing in chunks. Before starting, it asks the user 4 questions to calibrate: (1) polish intensity A/B/C, (2) style preference — oral/written/custom-described, (3) paragraph handling, (4) whether to generate a PPT outline. The PPT outline uses a 3-level structure: chapter titles, per-slide bullet points, and speaker notes. Output can be merged or separate. Trigger phrases: 润色口水稿, 整理逐字稿, 把录音稿整理成逐字稿, polish transcript, 整理录音稿, 润色讲稿.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐ 1 on GitHubGitHub ↗

New / niche

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

transcript-polish

WorkBuddy / OpenClaw Skill — 将录音口水稿润色为可用逐字稿,支持 30,000+ 字超长文本,可同时输出 PPT 框架大纲。


功能简介

  • ✅ 去除口水词:嗯、呃、啊、就是、那个、对不对……系统性清理
  • ✅ 保留讲授风格:不压缩内容,不改变讲师个人表达特色
  • ✅ 支持超长文本:30,000 字以上分块处理,自动汇报进度
  • ✅ 4 个参数可调:润色力度 × 风格偏好 × 段落处理 × 是否输出 PPT 框架
  • ✅ PPT 三级大纲:章节标题 + 每页要点 + 备注/讲解提示,Markdown 格式

安装方式

方式一:直接安装(推荐)

在 WorkBuddy 或 OpenClaw 对话框中输入:

安装 skill:https://github.com/codingnoob4ever/transcript-polish

方式二:手动安装

  1. 下载本仓库(git clone 或下载 ZIP)
  2. 将 transcript-polish/ 文件夹放入 ~/.workbuddy/skills/ 目录
  3. 重启 WorkBuddy 或重新加载 skill

使用方法

将口水稿文字粘贴到对话框,或上传 .txt 文件,然后说:

帮我润色这段口水稿

或:

整理成逐字稿
把录音稿整理成逐字稿
润色讲稿

Skill 启动后会先问你 4 个问题来校准参数:

#问题选项
①润色力度A 轻度 / B 标准(默认)/ C 深度
②风格偏好A 口语风 / B 书面风 / C 我来描述
③段落处理A 保持原结构 / B 优化段落划分
④PPT 框架A 附在末尾 / B 分开输出 / C 不需要

回答后 AI 会确认参数,然后开始处理。超长文本会分块并报进度。


参数说明

润色力度

选项处理范围适合场景
A 轻度只删纯语气音(嗯/呃/啊)想保留原始讲法,只做最小清理
B 标准删填充词 + 整理假起步 + 去重复大多数教学/讲座场景(默认推荐)
C 深度在 B 基础上规范句式需要更接近书面稿的场景

风格偏好

选项效果
A 口语风保留"那么"、"你看"、"大家注意"等教学腔,保持说话节奏
B 书面风去多余口语化表达,更接近文章或讲义
C 我来描述AI 引导你从 4 个维度描述目标风格,完全按你的要求执行

PPT 框架输出格式(三级结构)

# 总标题

## 第一章:章节名

### Slide 1:页面标题
- 要点一
- 要点二
> 备注:从逐字稿原话提取的讲解提示,方便演讲者展开

内容原则

本 skill 严格遵守以下原则,绝不违反:

  1. 不发明内容:输出中出现的每个信息点,都必须能在原文中找到
  2. 不压缩长度:输出字数与原文偏差 ≤ 15%
  3. 不替换专业术语:英文缩写、领域术语保持原样
  4. PPT 要点从逐字稿提取:不基于常识"补充"内容

文件结构

transcript-polish/
├── SKILL.md                    ← Skill 主文件(触发条件 + 工作流程)
├── README.md                   ← 本文件
└── references/
    ├── filler_words.md         ← 口水词分类表(轻/标准/深度三档)
    └── polish_examples.md      ← Before/After 示例 + PPT 框架示例

适用平台


License

MIT

// HOW IT'S BUILT

KEY FILES

SKILL.mdREADME.md

// REPO STATS

1 stars