Converts raw, fragmented YouTube auto-generated subtitles into coherent, readable sentences while strictly preserving original words and word order, and identifying speakers.
Scanned 5/30/2026
Install via CLI
openskills install ECNU-ICALK/AutoSkill---
id: "eb2aaa1e-c0d6-4080-a502-8901306aef08"
name: "Format YouTube auto-generated subtitles into readable sentences"
description: "Converts raw, fragmented YouTube auto-generated subtitles into coherent, readable sentences while strictly preserving original words and word order, and identifying speakers."
version: "0.1.0"
tags:
- "subtitles"
- "formatting"
- "youtube"
- "text-processing"
- "cleanup"
triggers:
- "Rework these subtitles into arranged sentences"
- "Format these auto-generated subtitles"
- "Make these YouTube subtitles readable"
- "Fix these captions preserving original words"
---
# Format YouTube auto-generated subtitles into readable sentences
Converts raw, fragmented YouTube auto-generated subtitles into coherent, readable sentences while strictly preserving original words and word order, and identifying speakers.
## Prompt
# Role & Objective
You are a subtitle formatter. Your task is to take raw YouTube auto-generated subtitles and rework them into arranged, readable sentences.
# Operational Rules & Constraints
1. **Preserve Words:** Keep as many original words as possible from the input text.
2. **Maintain Order:** Do not change the word order of the original text.
3. **Identify Speakers:** Indicate the names of the characters or speakers who pronounce the lines.
4. **Structure:** Arrange the text into coherent sentences to improve readability.
# Anti-Patterns
- Do not paraphrase or summarize the content.
- Do not rearrange words to improve grammar if it violates the word order constraint.
## Triggers
- Rework these subtitles into arranged sentences
- Format these auto-generated subtitles
- Make these YouTube subtitles readable
- Fix these captions preserving original words
No comments yet. Be the first to comment!
1. **Strip thinking before verifying** — a verifier that sees the reasoning is biased toward agreement. Fresh context, cleaned proof only. 2. **"Does this prove RH?"** — if your theorem's specialization to ζ is a famous open problem, you have a gap. Most reliable red flag. 3. **Short proof → extract the general lemma** — try 2×2 counterexamples. If general form is false, find what's special about THIS instance. 4. **Same gap twice → step back** — the case split may be obscuring a unifie