huashu-nuwa
Verified女娲造人:输入人名/主题/甚至只是模糊需求,自动深度调研→思维框架提炼→生成可运行的人物Skill。 两种入口:(1)明确人名→直接蒸馏 (2)模糊需求→诊断推荐→再蒸馏。 触发词:「造skill」「蒸馏XX」「女娲」「造人」「XX的思维方式」「做个XX视角」「更新XX的skill」「升级XX的skill」。 模糊需求也触发:「我想提升决策质量」「有没有一种思维方式能帮我...」「我需要一个思维顾问」。 English triggers: "distill [person]", "nuwa", "create a [person] perspective skill", "how does [person] think", "I need a thinking advisor".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 19.1 KB |
| assets/banner.svg | other | 10.2 KB |
| assets/hero.gif | binary | 9.5 MB |
| assets/icon.png | binary | 15.9 KB |
| assets/mcstomach-promo-202610.png | binary | 2.1 MB |
| references/about-author.md | markdown | 10.4 KB |
| references/diagnose-playbook.md | markdown | 4.5 KB |
| references/extraction-framework.md | markdown | 8.2 KB |
| references/fidelity-scorecard.md | markdown | 5.2 KB |
| references/research-playbook.md | markdown | 9.9 KB |
| references/skill-template.md | markdown | 12.1 KB |
| references/special-cases.md | markdown | 3.5 KB |
| references/validation-playbook.md | markdown | 8.8 KB |
| scripts/download_subtitles.shexecutable | script | 1.9 KB |
| scripts/merge_research.py | script | 8.4 KB |
| scripts/quality_check.py | script | 18.9 KB |
| scripts/srt_to_transcript.py | script | 3.3 KB |
scripts/srt_to_transcript.py
View on GitHub#!/usr/bin/env python3
"""
将SRT/VTT字幕文件清洗为干净的纯文本transcript。
去除时间戳、序号、重复行、HTML标签,输出可直接阅读的文本。
用法:
python3 srt_to_transcript.py input.srt [output.txt]
python3 srt_to_transcript.py input.vtt [output.txt]
如果不指定输出文件,默认输出到 input_transcript.txt
"""
import sys
import re
from pathlib import Path
# Windows 的 GBK 控制台打不出 ✅ 和中文,统一成 UTF-8
for _s in (sys.stdout, sys.stderr):
try:
_s.reconfigure(encoding="utf-8", errors="replace")
except (AttributeError, OSError):
pass
def clean_srt(content: str) -> str:
"""清洗SRT格式字幕"""
lines = content.strip().split('\n')
texts = []
for line in lines:
line = line.strip()
# 跳过序号行(纯数字)
if re.match(r'^\d+$', line):
continue
# 跳过时间戳行
if re.match(r'\d{2}:\d{2}:\d{2}', line):
continue
# 跳过空行
if not line:
continue
# 去除HTML标签
line = re.sub(r'<[^>]+>', '', line)
# 去除VTT的position标记
line = re.sub(r'align:.*$|position:.*$', '', line).strip()
if line:
texts.append(line)
# 去重(自动字幕常有连续重复行)
deduped = []
for text in texts:
if not deduped or text != deduped[-1]:
deduped.append(text)
# 合并成段落:连续的短句合并,遇到句末标点或长停顿换行
result = []
current = []
for text in deduped:
current.append(text)
# 如果当前累积文本够长或遇到句末标点,形成一个段落
joined = ' '.join(current)
if len(joined) > 200 or re.search(r'[。!?.!?]$', text):
result.append(joined)
current = []
if current:
result.append(' '.join(current))
return '\n\n'.join(result)
def clean_vtt(content: str) -> str:
"""清洗VTT格式字幕(先去掉VTT头部,然后按SRT逻辑处理)"""
# 去掉WEBVTT头部
content = re.sub(r'^WEBVTT.*?\n\n', '', content, flags=re.DOTALL)
# 去掉NOTE块
content = re.sub(r'NOTE.*?\n\n', '', content, flags=re.DOTALL)
return clean_srt(content)
def main():
if len(sys.argv) < 2:
print("用法: python3 srt_to_transcript.py <input.srt|input.vtt> [output.txt]")
sys.exit(1)
input_path = Path(sys.argv[1])
if not input_path.exists():
print(f"❌ 文件不存在: {input_path}")
sys.exit(1)
# 默认输出文件名
if len(sys.argv) >= 3:
output_path = Path(sys.argv[2])
else:
output_path = input_path.parent / f"{input_path.stem}_transcript.txt"
# 读取并检测格式
content = input_path.read_text(encoding='utf-8')
if input_path.suffix.lower() == '.vtt' or content.startswith('WEBVTT'):
transcript = clean_vtt(content)
else:
transcript = clean_srt(content)
output_path.write_text(transcript, encoding='utf-8')
# 统计
word_count = len(transcript)
line_count = transcript.count('\n') + 1
print(f"✅ 转换完成: {output_path}")
print(f" 字数: {word_count} 段落数: {line_count}")
if __name__ == '__main__':
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |