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 video-transcription-subtitle-workflowsgit 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/video-transcription-subtitle-workflows)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/video-transcription-subtitle-workflows"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/video-transcription-subtitle-workflows/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/video-transcription-subtitle-workflows"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/video-transcription-subtitle-workflows.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 | $0.00084 | $0.02381 |
| Opus 5 | $0.00042 | $0.01190 |
| Sonnet 5 | $0.00017 | $0.00476 |
| Haiku 4.5 | $0.00008 | $0.00238 |
Grade A, and why
video-transcription-subtitle-workflows 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 8d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Transcription and Subtitle Workflows
Use this umbrella for media-to-text and subtitle delivery tasks. Start by identifying the deliverable: plain transcript, bilingual transcript, subtitle files, hardcoded video, Chinese PDF report, downloaded normalized video, or frame/clip extraction.
Core workflow
- Acquire media reliably: YouTube/X URL, local file, audio file, or user upload.
- Normalize input before downstream work: prefer MP4 for video, WAV/M4A for audio, and keep an untouched source copy.
- Choose transcript source in priority order:
- Existing human captions or YouTube auto-captions when complete and aligned.
- Local Whisper when privacy/offline control matters or captions are missing.
- OpenAI Whisper API when local runtime is unavailable or speed matters.
- Audit timing and completeness before delivery: check duration coverage, missing segments, malformed SRT/VTT blocks, line lengths, and language alignment.
- Package outputs:
.srt/.vtt/.ass, transcript markdown, bilingual report, and/or hardcoded MP4.
Labeled playbooks
Bilingual subtitles (EN + Chinese)
- Keep English speech timing as the primary event grid.
- Align Chinese translation to the same subtitle event unless the user explicitly wants separate tracks.
- Use ASS for styled hardcoding when font, color, stroke, or placement matters.
- Always preview/audit a few early, middle, and late segments plus final duration coverage.
Precise word-level timing
Use Whisper word timestamps when subtitle sync must be accurate. Regenerate segments when auto-caption timing drifts, then rebuild SRT/ASS from the word-level data.
Whisper video hang workaround
If Whisper on a video file stalls with low CPU/memory and no output, extract audio first with ffmpeg, then transcribe the audio file. For the original session recipe, see references/from-media-whisper-video-transcribe-workaround.md.
YouTube transcript/report jobs
Use captions first, then Whisper fallback. Preserve timestamps and source URL. For Chinese reports, produce a structured Chinese narrative with key insights, not only a literal transcript.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/from-media-precise-bilingual-subtitle.md 8.9 KB
- references/from-media-whisper-video-transcribe-workaround.md 3.2 KB
- references/from-media-youtube-bilingual-subtitle-delivery.md 8.5 KB
- references/from-openclaw-imports-openai-whisper-api.md 3.1 KB
- references/from-openclaw-imports-openai-whisper.md 1.3 KB
- references/from-openclaw-imports-video-frames.md 2.6 KB
- references/from-social-media-x-video-download-normalization.md 2.6 KB
- references/from-user-imports-precise-bilingual-subtitle.md 18 KB
- references/from-user-imports-video-bilingual-subtitle-delivery.md 69 KB
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.
- 8d ago First seen · 196 lines · 84 tokens per session scan A d98f9ba9c2b6
video-transcription-subtitle-workflows is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 2,381 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
officecli-pitch-deck
Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet…
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…
morph-ppt-3d
3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.
draw
Draw - command-line tool for everyday use.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
blockrun
Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek").