Skip to content
SkillScript-led2,588 tokens in use

dbs-video-extract

Turns a Douyin, Xiaohongshu or WeChat Channels link into a data summary and a speech transcript saved as Markdown, using your own TikHub and Qingdou keys.

11,518 stars on the repository Custom / Unknowndontbesilent2025/dbskill · skills/dbs-video-extract
npx -y skills add dontbesilent2025/dbskill -g --all
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing dbs-video-extract costs

109tokens idle
2,588tokens in use
6,920tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/configure_api_key.py, scripts/extract_video.py, scripts/extract_video_transcript.py, scripts/tikhub_api.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure16/25
  • Examples12/15
  • Output5/15
  • Size15/15
  • Resources9/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 21
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/configure_api_key.py, line 67
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/extract_video_transcript.py, line 15
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    scripts/extract_video_transcript.py, line 90

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

dbs-video-extract takes a platform link or the full share text of a short video and returns two things: structured work or account data from TikHub, and a speech transcript from the Qingdou service, saved as a Markdown file named by author and title. If one side fails or has no key, the other side still completes and the summary says which part is missing.

It starts with a read-only key check, explains in everyday language what the service keys are when none are set, and walks you through buying and saving them. Both services charge for use, and the skill tells you so before it runs.

What You Get

  • A data summary of the work or account, with the tool used and any fallback noted
  • A transcript saved as author-and-title Markdown, with the original wording kept
  • A partial-success report when only one service key is available or one call fails
  • A guided key setup with a hidden-input script, so keys never appear in chat or logs

Common Use Cases

  • Collecting transcripts of competitor or benchmark videos for study
  • Pulling view and engagement figures for a work before analysing why it performed
  • Archiving the spoken content of your own videos as searchable notes

What Makes It Unique

It joins structured platform data and a speech transcript in one call and tolerates one side failing. It checks credentials first and explains them to non-technical users. A required notice states that the project has no affiliation with either vendor and that top-ups are the user’s own decision. Keys are read from environment variables, files or the macOS keychain and never written into commands or output.

Under The Hood

The skill runs bundled Python scripts that call the TikHub API and the Qingdou transcription service over the network, using your paid keys, and write Markdown files into the folder you name. Keys come from environment variables, a private config file in your home folder or the macOS keychain, and a separate script saves a key with hidden terminal input and restricted file permissions. It does not download media, publish anything or bypass privacy limits. Each call can cost money.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers