---

name: video-transcript-downloader description: Extract, summarize, and download video/audio/subtitles using yt-dlp/ffmpeg. Use when the user requests downloads or transcripts.

Video Transcript Downloader

./scripts/vtd.js can:

• Print a transcript as a clean paragraph (timestamps optional).
• Download video/audio/subtitles.

Transcript behavior:

• YouTube: fetch via youtube-transcript-plus when possible.
• Otherwise: pull subtitles via yt-dlp, then clean into a paragraph.

Setup

cd ~/Projects/agent-scripts/skills/video-transcript-downloader && npm ci

Transcript (default: clean paragraph)

./scripts/vtd.js transcript --url 'https://…'
./scripts/vtd.js transcript --url 'https://…' --lang en
./scripts/vtd.js transcript --url 'https://…' --timestamps
./scripts/vtd.js transcript --url 'https://…' --keep-brackets

Download video / audio / subtitles

./scripts/vtd.js download --url 'https://…' --output-dir ~/Downloads
./scripts/vtd.js audio --url 'https://…' --output-dir ~/Downloads
./scripts/vtd.js subs --url 'https://…' --output-dir ~/Downloads --lang en

Formats (list + choose)

List available formats (format ids, resolution, container, audio-only, etc):

./scripts/vtd.js formats --url 'https://…'

Download a specific format id (example):

./scripts/vtd.js download --url 'https://…' --output-dir ~/Downloads -- --format 137+140

Prefer MP4 container without re-encoding (remux when possible):

./scripts/vtd.js download --url 'https://…' --output-dir ~/Downloads -- --remux-video mp4

Notes

• Default transcript output is a single paragraph. Use --timestamps only when asked.
• Bracketed cues like [Music] are stripped by default; keep them via --keep-brackets.
• Pass extra yt-dlp args after -- for transcript fallback, download, audio, subs, formats.

./scripts/vtd.js formats --url 'https://…' -- -v

Troubleshooting (only when needed)

• Missing yt-dlp / ffmpeg:

brew install yt-dlp ffmpeg

• Verify:

yt-dlp --version
ffmpeg -version | head -n 1

Scope and triggers

• Use this skill when the task matches its description and triggers.
• If the request is outside scope, route to the referenced skill.

Required inputs

• User request details and any relevant files/links.

Deliverables

• A structured response or artifact appropriate to the skill.
• Include schema_version: 1 if outputs are contract-bound.

Constraints

• Redact secrets/PII by default.
• Avoid destructive operations without explicit user direction.

Validation

• Run any relevant checks or scripts when available.
• Fail fast and report errors before proceeding.

Philosophy

• Favor clarity, explicit tradeoffs, and verifiable outputs.

Anti-patterns

• Avoid vague guidance without concrete steps.
• Do not invent results or commands.

Procedure

1. Clarify scope and inputs.
2. Execute the core workflow.
3. Summarize outputs and next steps.

Antipatterns

• Do not add features outside the agreed scope.

Examples

• "Provide a concise response for this task."
• "Follow the workflow and summarize outputs."

Variation

• Vary tone, depth, and structure based on context.
• Avoid repeating the same outline across outputs.

Remember

The agent is capable of extraordinary work in this domain. Use judgment, adapt to context, and push boundaries when appropriate.

References

• references/contract.yaml
• references/evals.yaml

<!-- skill-score-boost-v1 -->

Philosophy and tradeoffs

• Use this skill when consistent decision-making matters more than one-off execution because project context should drive the approach.
• Principle and mindset: prioritize tradeoffs and constraints over rigid checklists; understand why each step exists.
• Ask this to keep outcomes robust: Why is this the right default, and what could change this outcome?
• How do we adapt if constraints shift?
• What evidence is needed before choosing one path over another?

Anti-patterns and caveats

• Avoid applying this playbook generically without checking repository-specific context.
• NEVER skip required validation gates when behavior changes.
• DO NOT use this skill as a rigid replacement for engineering judgment.
• DON'T ignore warnings or assume one pattern fits all repos.
• Common pitfall: treating anti-patterns as optional.
• Incorrect assumptions here can lead to fragile guidance.
• Warning: wrong sequencing can create avoidable regressions.

Variation and adaptation

• Vary the workflow by team size, risk, and deployment target.
• Use different strategies for small, medium, and large changes.
• Adapt recommendations to the specific environment and avoid repetitive templates.
• Avoid generic or cookie-cutter responses; craft context-specific alternatives.
• Keep outputs diverse and not repetitive.
• Converge on a custom path only after evidence review.
• Different constraints should produce different, non-generic recommendations.

Empowering execution style

• Be capable of exploring multiple options and enabling the team to make safe decisions.
• Unlock confidence by explaining options and tradeoffs clearly.
• Feel free to be creative while staying rigorous and precise.
• Push boundaries with practical alternatives when simple recipes fail.
• Enable outcomes-oriented problem solving.

<!-- decision-feedback-protocol:v2 -->

Decision feedback protocol (required):

• For non-trivial outcomes, collect user feedback via AskQuestion parity (request_user_input) before closing the run.
• Capture: decision (accepted|partial|rejected|deferred), outcome (good|neutral|bad|unknown), and confidence (high|medium|low).
• Persist with: python3 utilities/skill-creator/scripts/record_skill_feedback.py --skill-path <path/to/SKILL.md> --decision <...> --outcome <...> --confidence <...> --notes "...".
• The recorder tags subject (for example ui, code_review, backend, security) for cross-domain quality analytics.

<!-- /decision-feedback-protocol -->