Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add davidtoby/agent-skills --skill youtube-bilingual-transcript-reportgit clone --depth 1 https://github.com/davidtoby/agent-skillsWrote 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.
[](https://agentmods.dev/skills/davidtoby/agent-skills/youtube-bilingual-transcript-report)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/youtube-bilingual-transcript-report"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/youtube-bilingual-transcript-report/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.
<a href="https://agentmods.dev/skills/davidtoby/agent-skills/youtube-bilingual-transcript-report"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/youtube-bilingual-transcript-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01907 |
| Opus 5 | $0.00028 | $0.00954 |
| Sonnet 5 | $0.00011 | $0.00381 |
| Haiku 4.5 | $0.00006 | $0.00191 |
Grade A, and why
youtube-bilingual-transcript-report scanned grade A with 0 findings 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 9d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Bilingual Transcript Report
Use when the user gives a YouTube URL and wants:
- the video downloaded locally
- English and Chinese transcripts
- a structured summary
- original insights / commentary
- a polished PDF deliverable
This is a report workflow, not just a subtitle workflow.
Output standard
Save everything under:
~/.Hermes/workspace/output/<self-descriptive-task-folder>/
Preferred deliverables:
- source video (practical resolution if full quality is unnecessary)
- English structured transcript
- Chinese structured transcript
- summary + insights markdown
- final combined markdown report
- final PDF
Use self-descriptive filenames.
Proven workflow
1) Prepare task folder and inspect metadata
mkdir -p ~/.Hermes/workspace/output/<task-folder>
yt-dlp --dump-single-json --no-warnings '<youtube-url>' > video_info.json
yt-dlp --list-subs '<youtube-url>' > subs_list.txt 2>&1 || true
Capture at least:
- title
- uploader/channel
- duration
- upload date
2) Do not blindly download a massive source first
For transcript/report tasks, full-resolution download is often wasteful.
A real run encountered a 2.54 GB source that timed out and was unnecessary for PDF/report delivery.
Prefer a practical MP4 such as 360p unless the user explicitly needs high quality:
yt-dlp --no-playlist \
-f 'bv*[height<=360][ext=mp4]+ba[ext=m4a]/b[height<=360][ext=mp4]/b[height<=360]' \
-o '<descriptive-name>_[%(id)s].%(ext)s' \
'<youtube-url>'
Guideline:
- if the task is transcript/summary/PDF first, optimize for completion speed
- only fetch huge source media when downstream work truly needs it
3) Download English subtitle tracks first
Try English auto-captions first:
yt-dlp --skip-download --write-auto-sub --sub-langs 'en-orig,en' --sub-format srt \
-o '%(title).120s [%(id)s].%(ext)s' '<youtube-url>'
4) Chinese subtitle download may fail with HTTP 429
A real run had this exact failure even though --list-subs showed zh-Hans / zh-Hant tracks.
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.
- 9d ago First seen · 257 lines · 57 tokens per session scan A 9399ba496842
youtube-bilingual-transcript-report is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 1,907 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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…
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'…
officecli-docx
Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments…
officecli-financial-model
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value'…
officecli-pptx
Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with…
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'…