youtube-bilingual-subtitle-delivery

youtube-bilingual-subtitle-delivery is a skill for Claude Code, Codex from davidtoby/agent-skills. It costs 73 tokens per session (2,519 once invoked), scanned A, original, MIT.

A workflow for downloading a YouTube video and delivering English and Chinese subtitles as subtitle files and MP4 videos. It can create both soft subtitles, which can be turned on or off, and hardcoded subtitles, which are permanently shown in the picture.

In plain words
What is it for?
Use it when given a YouTube URL and asked for a bilingual subtitle file, a soft-subtitle MP4, and a hardcoded MP4.
Why use it?
It handles video conversion, incomplete or rate-limited captions, translation, subtitle checking, and final export in one process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/audit_bilingual_srt.py /path/final_bilingual.srt.

Good fit Use it when given a YouTube URL and asked for a bilingual subtitle file, a soft-subtitle MP4, and a hardcoded MP4.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/davidtoby/agent-skills
agentmods
npx agentmods add skills/davidtoby/agent-skills/youtube-bilingual-subtitle-delivery

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for youtube-bilingual-subtitle-delivery

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidtoby/agent-skills/youtube-bilingual-subtitle-delivery/github.svg)](https://agentmods.dev/skills/davidtoby/agent-skills/youtube-bilingual-subtitle-delivery)
Your own site
<a href="https://agentmods.dev/skills/davidtoby/agent-skills/youtube-bilingual-subtitle-delivery"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/youtube-bilingual-subtitle-delivery/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for youtube-bilingual-subtitle-delivery

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidtoby/agent-skills/youtube-bilingual-subtitle-delivery"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/youtube-bilingual-subtitle-delivery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,519 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.02519
Opus 5 $0.00036 $0.01260
Sonnet 5 $0.00015 $0.00504
Haiku 4.5 $0.00007 $0.00252

Measured 12d ago against content hash 2429ed2718da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

youtube-bilingual-subtitle-delivery scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

import json, urllib.request, pathlib
skills/.archive/umbrella-curation-2026-04-29/media/youtube-bilingual-subtitle-delivery/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Bilingual Subtitle Delivery

Use when the user gives a YouTube URL and wants an MP4 with English/Chinese subtitles.

When this skill is especially useful

  • YouTube downloads as webm and must become mp4
  • English auto-captions are available but Chinese captions fail or get HTTP 429
  • You need a practical delivery result more than a perfect fully-automated translation pipeline
  • You want both .srt, softsub .mp4, and hardcode .mp4

Output standard

Deliver in this order:

  1. bilingual .srt
  2. softsub .mp4
  3. hardcode .mp4

Use self-descriptive names under ~/.Hermes/workspace/output/<task-folder>/.

Proven workflow

1) Prepare output folder

mkdir -p ~/.Hermes/workspace/output/<topic-folder>

2) Download the YouTube source

Prefer yt-dlp with a descriptive filename.

yt-dlp --no-playlist -o '%(title).120s [%(id)s].%(ext)s' '<youtube-url>'

3) Convert to MP4 if needed

If the merged output is webm, transcode to H.264/AAC MP4.

ffmpeg -y -i input.webm -c:v libx264 -preset fast -crf 18 -c:a aac -b:a 192k -movflags +faststart output.mp4

Verify the cut duration before subtitle work:

ffprobe -v error -show_entries format=duration:stream=codec_name,codec_type,width,height -of json output.mp4

4) Check subtitle availability first

List available YouTube subtitle tracks:

yt-dlp --list-subs '<youtube-url>'

If English auto-captions exist, try downloading them first:

yt-dlp --skip-download --write-auto-sub --sub-langs 'en-orig,en' --sub-format srt -o '<basename>.%(ext)s' '<youtube-url>'

If Chinese auto-captions also exist, try:

yt-dlp --skip-download --write-auto-sub --sub-langs 'zh-Hans,zh-Hant' --sub-format srt -o '<basename>.%(ext)s' '<youtube-url>'

Important fallback: Chinese caption download may fail with HTTP 429

This happened in practice even when --list-subs showed Chinese tracks. If that happens:

  • keep the English auto-caption time axis
  • create Chinese lines manually and attach them to the same subtitle event
  • do not block the delivery waiting on the Chinese download endpoint to recover

Read the full file on GitHub · 235 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 235 lines · 73 tokens per session scan A 2429ed2718da

Subscribe to this mod's changes

youtube-bilingual-subtitle-delivery is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,519 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

translate

Translate text to a target language.

oujingzhou/build-your-own-openclaw · 8 tokens

morph-ppt

Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…

iOfficeAI/OfficeCLI · 169 tokens

officecli-word-form

Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…

iOfficeAI/OfficeCLI · 224 tokens

officecli-academic-paper

Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper'…

iOfficeAI/OfficeCLI · 141 tokens

officecli

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

iOfficeAI/OfficeCLI · 56 tokens

iflytek-text-proofread

A tool that checks Chinese writing through iFlytek’s official document-proofreading service. It looks for spelling, punctuation, wording, factual, terminology, and sensitive-content problems.

iflytek/iFly-Skills · 88 tokens