li-transcript

Original：🇨🇳 Chinese

Translated

1 scriptsChecked / no sensitive code detected

Use this skill when the user says phrases like "get transcript", "transcribe video", "extract script", "help me extract it", "what does this video say", "what did this blogger say", or directly provides a video link requesting content extraction. Even if the user only sends a video link without stating their request, proactively trigger this skill if the context involves benchmark analysis or content extraction. Call video2text.py to obtain the raw transcript, use AI to correct common speech recognition errors, identify the author, and archive it to the benchmark blogger directory. Do NOT trigger for: analyzing viral content patterns (use li-analyzer), recording own topic ideas (use li-recorder), writing own scripts (use li-writer). Use when the user wants to "get transcript", "transcribe video", "extract script", or gives a video link for content extraction. Runs speech-to-text, AI proofreads, and archives to benchmark blogger directory.

4installs

Sourcejiangjiax/li-skills

Added on2026-05-23

NPX Install

npx skill4agent add jiangjiax/li-skills li-transcript

SKILL.md Content (Chinese)

View Translation Comparison →

Video Transcript Extraction + Benchmark Archiving

Extract transcript from video link, archive to benchmark blogger directory after AI proofreading.

Workflow

Step 0: Environment Preparation Before First Use (Only Required Once)

If you've just installed this skill from an open-source repository, you need to prepare the runtime environment first:

bash

# 1. System Dependencies (macOS)
brew install yt-dlp ffmpeg

# 2. Python Virtual Environment + Tencent Cloud ASR SDK
python3 -m venv .claude/skills/li-transcript/scripts/.venv
.claude/skills/li-transcript/scripts/.venv/bin/pip install tencentcloud-sdk-python-asr

# 3. Create a .env file in the project root directory and fill in Tencent Cloud keys (apply at console https://console.cloud.tencent.com/cam/capi)
# Format:
# TENCENT_SECRET_ID=your_id
# TENCENT_SECRET_KEY=your_key

Once the environment is ready, proceed to Step 1.

Step 1: Transcribe Video

Run the transcription script (both the script and venv are in the skill directory, self-contained):

bash

.claude/skills/li-transcript/scripts/.venv/bin/python3 .claude/skills/li-transcript/scripts/video2text.py "video link"

The script will output:

stderr: Progress information +
```
[标题] xxx
```
(original video title)
stdout: Plain text transcript without timestamps

Troubleshooting order for script errors:

Does the
```
.env
```
file in the project root directory contain
```
TENCENT_SECRET_ID
```
and
```
TENCENT_SECRET_KEY
```
(the script will search up to 6 levels upward from the current directory)

.claude/skills/li-transcript/scripts/.venv/

functioning properly (rebuild:

python3 -m venv .claude/skills/li-transcript/scripts/.venv && .claude/skills/li-transcript/scripts/.venv/bin/pip install tencentcloud-sdk-python-asr

)

Is the video link supported by yt-dlp

Step 2: AI Proofreading

Perform text proofreading on the raw transcript, only correcting typos without altering content:

Homophone/near-homophone correction: Infer based on context (e.g., "艺人公司" → "一人公司", "四动会" → "私董会", "体校" → "提效")
Proper noun correction: Technical terms, product names, personal names, English vocabulary
Obvious ASR garbled text: Replace with reasonable inferences

Retain spoken expressions (e.g., "ah", "um", "you know"), do not rewrite sentence structure, and do not polish the style.

Execute proofreading directly without listing differences one by one—users can compare with the original text themselves if they want to check.

Step 3: Identify Author & Archive

Identify Author — Priority order:

User has informed → Use directly
Self-introduction in transcript (e.g., "Hello everyone, I'm XXX", "I'm XXX") → Extract
Neither → Ask the user

Match Benchmark — Read the directory list of

05-选题研究/对标博主/短视频/

If a matching existing blogger is found → Archive to that directory
If no match is found → Ask the user "[Name] is not in the benchmark list yet, create it?", create the directory if agreed

Combine the questions about the author and whether to create a benchmark to reduce back-and-forth communication.

Determine Title — Prioritize the original title obtained by yt-dlp (the

[标题]

line in stderr), if unavailable, summarize one from the transcript content.

Step 4: Save File

Path:

05-选题研究/对标博主/短视频/[博主名]/[YYYY年M月]/[视频标题].md

Create the time directory if it doesn't exist.

Format — Adjust YAML field names according to the video source platform:

markdown

---
[Platform]数据:
  点赞数: 
  收藏数: 
  评论数: 
  分享数: 
  观看数: 
tags: 
---

# 标题

[视频标题]

# 封面花字



# 视频脚本

[校对后的完整逐字稿]

Platform judgment rules:

URL contains
```
xiaohongshu.com
```
→
```
小红书数据
```
URL contains
```
bilibili.com
```
→
```
B站数据
```
URL contains
```
douyin.com
```
→
```
抖音数据
```
URL contains
```
youtube.com
```
or
```
youtu.be
```
→
```
YouTube数据
```
Others →
```
平台数据
```

Inform the user of the path in one sentence after saving.

Video Transcript Extraction + Benchmark Archiving

Extract transcript from video link, archive to benchmark blogger directory after AI proofreading.

Workflow

Step 0: Environment Preparation Before First Use (Only Required Once)

If you've just installed this skill from an open-source repository, you need to prepare the runtime environment first:

bash

# 1. System Dependencies (macOS)
brew install yt-dlp ffmpeg

# 2. Python Virtual Environment + Tencent Cloud ASR SDK
python3 -m venv .claude/skills/li-transcript/scripts/.venv
.claude/skills/li-transcript/scripts/.venv/bin/pip install tencentcloud-sdk-python-asr

# 3. Create a .env file in the project root directory and fill in Tencent Cloud keys (apply at console https://console.cloud.tencent.com/cam/capi)
# Format:
# TENCENT_SECRET_ID=your_id
# TENCENT_SECRET_KEY=your_key

Once the environment is ready, proceed to Step 1.

Step 1: Transcribe Video

Run the transcription script (both the script and venv are in the skill directory, self-contained):

bash

.claude/skills/li-transcript/scripts/.venv/bin/python3 .claude/skills/li-transcript/scripts/video2text.py "video link"

The script will output:

stderr: Progress information +
```
[标题] xxx
```
(original video title)
stdout: Plain text transcript without timestamps

Troubleshooting order for script errors:

Does the
```
.env
```
file in the project root directory contain
```
TENCENT_SECRET_ID
```
and
```
TENCENT_SECRET_KEY
```
(the script will search up to 6 levels upward from the current directory)

.claude/skills/li-transcript/scripts/.venv/

functioning properly (rebuild:

python3 -m venv .claude/skills/li-transcript/scripts/.venv && .claude/skills/li-transcript/scripts/.venv/bin/pip install tencentcloud-sdk-python-asr

)

Is the video link supported by yt-dlp

Step 2: AI Proofreading

Perform text proofreading on the raw transcript, only correcting typos without altering content:

Homophone/near-homophone correction: Infer based on context (e.g., "艺人公司" → "一人公司", "四动会" → "私董会", "体校" → "提效")
Proper noun correction: Technical terms, product names, personal names, English vocabulary
Obvious ASR garbled text: Replace with reasonable inferences

Retain spoken expressions (e.g., "ah", "um", "you know"), do not rewrite sentence structure, and do not polish the style.

Execute proofreading directly without listing differences one by one—users can compare with the original text themselves if they want to check.

Step 3: Identify Author & Archive

Identify Author — Priority order:

User has informed → Use directly
Self-introduction in transcript (e.g., "Hello everyone, I'm XXX", "I'm XXX") → Extract
Neither → Ask the user

Match Benchmark — Read the directory list of

05-选题研究/对标博主/短视频/

If a matching existing blogger is found → Archive to that directory
If no match is found → Ask the user "[Name] is not in the benchmark list yet, create it?", create the directory if agreed

Combine the questions about the author and whether to create a benchmark to reduce back-and-forth communication.

Determine Title — Prioritize the original title obtained by yt-dlp (the

[标题]

line in stderr), if unavailable, summarize one from the transcript content.

Step 4: Save File

Path:

05-选题研究/对标博主/短视频/[博主名]/[YYYY年M月]/[视频标题].md

Create the time directory if it doesn't exist.

Format — Adjust YAML field names according to the video source platform:

markdown

---
[Platform]数据:
  点赞数: 
  收藏数: 
  评论数: 
  分享数: 
  观看数: 
tags: 
---

# 标题

[视频标题]

# 封面花字



# 视频脚本

[校对后的完整逐字稿]

Platform judgment rules:

URL contains
```
xiaohongshu.com
```
→
```
小红书数据
```
URL contains
```
bilibili.com
```
→
```
B站数据
```
URL contains
```
douyin.com
```
→
```
抖音数据
```
URL contains
```
youtube.com
```
or
```
youtu.be
```
→
```
YouTube数据
```
Others →
```
平台数据
```

Inform the user of the path in one sentence after saving.

li-transcript

NPX Install

Tags

SKILL.md Content (Chinese)

Video Transcript Extraction + Benchmark Archiving

Workflow

Step 0: Environment Preparation Before First Use (Only Required Once)

Step 1: Transcribe Video

Step 2: AI Proofreading

Step 3: Identify Author & Archive

Step 4: Save File

li-transcript

NPX Install

Tags

SKILL.md Content (Chinese)

Video Transcript Extraction + Benchmark Archiving

Workflow

Step 0: Environment Preparation Before First Use (Only Required Once)

Step 1: Transcribe Video

Step 2: AI Proofreading

Step 3: Identify Author & Archive

Step 4: Save File