Subtitle Correction

If you've ever tried to edit auto-generated subtitles for technical content, you know the pain: "Luncheon" instead of "LangChain", "绘画" (painting) instead of "会话" (conversation). This skill fixes speech recognition errors in SRT files while keeping timestamps untouched. It asks you upfront for domain terms (framework names, technical jargon, proper nouns), then uses those to intelligently correct phonetic mistakes and mangled technical vocabulary throughout the file. Works for both Chinese and English, and includes a validation script to diff your changes. Best for programming tutorials, AI courses, or anything where ASR chokes on specialized terminology.

skills.sh installs: 545
GitHub stars: 139
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sugarforever/01coder-agent-skills --skill subtitle-correction --agent claude-code

Installs into .claude/skills of the current project.

Files

Subtitle Correction Skill

This skill corrects speech recognition errors in subtitle files while strictly preserving timeline information.

Interactive Workflow

Step 1: Request Terminology from User

IMPORTANT: Before starting any correction, ALWAYS ask the user for domain-specific terms.

Prompt the user with:

在开始修正之前，请提供一些关键术语，帮助我更准确地识别和修正语音识别错误：

1. **专有名词**：人名、品牌名、产品名等（如：Anthropic、Claude）
2. **技术术语**：框架、库、工具名称（如：LangChain、OpenAI、PyTorch）
3. **领域词汇**：行业特定词汇（如：checkpointer、middleware、runtime）
4. **其他关键词**：视频中频繁出现的重要词汇

请用逗号分隔，例如：`LangChain, Agent, OpenAI, checkpointer`

For English users:

Before I begin correction, please provide key terms to help me accurately identify speech recognition errors:

1. **Proper nouns**: Names, brands, products (e.g., Anthropic, Claude)
2. **Technical terms**: Frameworks, libraries, tools (e.g., LangChain, PyTorch)
3. **Domain vocabulary**: Industry-specific terms (e.g., checkpointer, middleware)
4. **Other keywords**: Important words that appear frequently

Please separate with commas, e.g.: `LangChain, Agent, OpenAI, checkpointer`