Skills youtube-transcript-pipeline-lite
Run a lightweight YouTube transcript workflow: transcribe, attribution cleanup, translation, and packaging with minimal tooling. Use for repeatable transcript handoff tasks when you need a concise, auditable process over custom automation.
install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/bluebirdback/youtube-transcript-pipeline-lite" ~/.claude/skills/openclaw-skills-youtube-transcript-pipeline-lite && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/bluebirdback/youtube-transcript-pipeline-lite" ~/.openclaw/skills/openclaw-skills-youtube-transcript-pipeline-lite && rm -rf "$T"
manifest:
skills/bluebirdback/youtube-transcript-pipeline-lite/SKILL.mdsource content
YouTube Transcript Pipeline (Lite)
Quick Start
Use this when a user asks for:
- YouTube transcript generation and cleanup
- speaker correction around interview/interjector vs main speaker
- translated transcript output while preserving timestamps/speakers
- ready-to-share folder packaging
Minimal Workflow
-
Transcribe
- Run your existing transcript flow for the target video (word-level preferred for reliable speaker calibration).
- Keep all raw outputs.
-
Speaker cleanup (small-impact)
- Preserve the default/primary speaker mapping.
- Only flip clearly short-interjection/question lines when they are obviously misattributed.
- Keep line count and timestamps unchanged.
-
Translate (optional)
- Translate content line-by-line.
- Keep format exactly:
.[HH:MM:SS] Speaker: text - Keep technical terms unless explicitly asked to simplify.
-
Package for handoff
- Create concise structure:
,transcripts/
,artifacts/
.MANIFEST.txt - Include one reviewed transcript + one translated version when asked.
- Create concise structure:
What not to do in this skill
- Do not introduce heavy automation assumptions.
- Do not change line/timestamp structure unless user explicitly asks.
- Do not aggressively relabel all speaker turns; prefer conservative flips.
Quality checks
- Validate final line counts against source.
- Confirm active final files are present and clearly named.
- Keep every major handoff stage discoverable in manifest.
Reference
See
references/limits.md for quick trade-offs and rollback guidance.