← Browse

@hamsterider-m/bilibili-subtitle

B

Extract Bilibili subtitles with BBDown and render transcript outputs.

skillclaude

Install

agr install @hamsterider-m/bilibili-subtitle --target claude

Writes 7 files into .claude/skills/, pinned to git-ef8b313f.

  • .claude/skills/bilibili-subtitle/.gitignore
  • .claude/skills/bilibili-subtitle/README.md
  • .claude/skills/bilibili-subtitle/SKILL.md
  • .claude/skills/bilibili-subtitle/install.sh
  • .claude/skills/bilibili-subtitle/opencode.json
  • .claude/skills/bilibili-subtitle/pixi.toml
  • .claude/skills/bilibili-subtitle/pyproject.toml

Document

Bilibili Subtitle Skill

Extract Bilibili subtitles with BBDown and render transcript outputs.

When To Use

Use this skill when a Bilibili video already has downloadable subtitles, including Bilibili AI subtitles exposed by BBDown. This skill only extracts subtitle files exposed by BBDown.

Commands

TaskCommand
Preflightpixi run python -m bilibili_subtitle --check
JSON preflightpixi run python -m bilibili_subtitle --check-json
Extractpixi run python -m bilibili_subtitle "URL" -o ./output
Extract JSONpixi run python -m bilibili_subtitle "URL" -o ./output --json-output
Select languagepixi run python -m bilibili_subtitle "URL" --language zh-Hans -o ./output

Workflow

  1. Parse the Bilibili URL, BV ID, or av ID.
  2. Run BBDown in subtitle-only mode.
  3. Load the downloaded subtitle file.
  4. Render Markdown transcript, SRT, and VTT files.
  5. Optionally emit JSON for parent skills.

Outputs

output/
├── {title}.transcript.md
├── {title}.srt
└── {title}.vtt

JSON Contract

pixi run python -m bilibili_subtitle "URL"   -o /tmp/output   --json-output

The response includes exit_code, output.files, warnings, and errors.

Dependencies

  • pixi for the Python environment
  • BBDown for subtitle extraction
  • gh for installer-driven BBDown nightly downloads

Error Handling

CodeLevelMeaningRemediation
E001FATALBBDown missingRun ./install.sh
E002FATALBBDown auth requiredRun BBDown login
E003RECOVERABLEDownload failedCheck URL/network/login/language
E004RECOVERABLENo downloadable subtitlesTry another language or video
E005FATALInvalid URL/IDProvide a Bilibili URL, BV ID, or av ID
E006FATALOutput write failedCheck output directory permissions
E007RECOVERABLEInvalid subtitle contentRetry or inspect BBDown output

Trustgrade B

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • warnLicenseno SPDX license detected

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-ef8b313f50982026-07-31