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 agentmods add skills/juliandickie/creators-studio/create-transcriptnpx skills add juliandickie/creators-studio --skill create-transcriptgit clone --depth 1 https://github.com/juliandickie/creators-studioWhat 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 | $0.00064 | $0.01948 |
| Opus 5 | $0.00032 | $0.00974 |
| Sonnet 5 | $0.00013 | $0.00390 |
| Haiku 4.5 | $0.00006 | $0.00195 |
Grade A, and why
create-transcript 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 2d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creators Studio - Transcript Creative Director
Core Principles
- One API call per file, ever. The raw Scribe JSON is cached to disk and every human format (markdown, SRT, VTT, chapters, plaintext) is a pure render of that cache. Speaker renames and added formats regenerate from the cache - never re-transcribe a file you already have JSON for.
- Faithful, not editorialised. This skill produces accurate transcripts. Summaries, action items, or rewrites are a later turn on the output, never baked into the transcript.
- Names and brands matter. Diarized speakers come back anonymous and brand names come back mangled unless you help. Use speaker naming and keyterms - they are the difference between a raw dump and a usable transcript.
- Fail loud. A file with no audio, a failed upload, or a partial batch is surfaced explicitly with counts. "Done" means every file succeeded.
Quick Reference
| Command | What it does |
|---|---|
/create-transcript <file> |
Transcribe one file with smart default formats. |
/create-transcript <file> --formats md,srt,vtt,json |
Choose output formats (all for every format; json always written). |
/create-transcript <file> --keyterm-set dental |
Activate a named keyterm set (per-category vocab from config) on this video only. |
/create-transcript <file> --keyterms "Medit,iTero,iDD" |
Add ad-hoc bias terms for this run (one-offs, unions on top of any set). |
/create-transcript <file> --speakers "0=Julian,1=Dr Ahmad" |
Name diarized speakers up front. |
/create-transcript <folder> --batch |
Transcribe every audio/video file in a folder. |
/create-transcript rename --json X.json --speakers "0=Name,1=Name" |
Re-render formats with named speakers - no API call, no charge. |
/create-transcript retitle --json X.json --title "..." |
Set a descriptive H1 + filename prefix (video name kept at the end) - no API call. |
/create-transcript cost <file or folder> |
Estimate audio-minutes before running (no fabricated price). |
/create-transcript status |
Check ElevenLabs key + ffmpeg/ffprobe + config keyterms. |
What ships with it
5 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.
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.
- 2d ago First seen · 118 lines · 64 tokens per session scan A 6abb1803c588
create-transcript is a skill published in the GitHub repository juliandickie/creators-studio (2 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,948 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
wavespeed
Generate or edit AI media (image, video, audio, 3D) by calling the wavespeed CLI on the user's machine. Use whenever the user asks to create, edit, animate, upscale, or transform a visual asset, generate audio/TTS/music, or produce marketing creatives. Every model on the WaveSpeed platform is one wavespeed run call.
1688-ecommerce-image-generation-editing
帮助电商运营、商品摄影、品牌商品团队和直播带货团队直接完成“1688 电商图片生成与编辑”：既可从文字生成，也可加入参考图帮助控制主体、构图和视觉风格；通过 AI Hive 使用时，生成前自动上传参考图，提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与角色一致性内容。 Use this skill for 1688 电商图片生成与编辑, text-to-image, reference-guided image generation, and commercial image creation, product photography…
1688-ecommerce-video-generation-editing
帮助电商运营、品牌商品团队、直播带货团队与商业内容创作者直接完成“1688 电商视频生成与编辑”：既可只输入文字从零生成，也可加入图片、视频或音频控制结果；通过 AI Hive 使用时，生成前自动上传所需素材，提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for 1688 电商视频生成与编辑, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video, video-to-video, audio-to-video, AI…
ai-model-expert-1688-ecommerce-image-generation-editing
AI大模型专家｜1688 电商图片生成与编辑。帮助电商运营、商品摄影、品牌商品团队和直播带货团队直接完成“1688 电商图片生成与编辑”：既可从文字生成，也可加入参考图帮助控制主体、构图和视觉风格；通过 AI Hive 使用时，生成前自动上传参考图，提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与角色一致性内容。 Use this skill for 1688 电商图片生成与编辑, text-to-image, reference-guided image generation, and commercial image creation…
ai-model-expert-1688-ecommerce-video-generation-editing
AI大模型专家｜1688 电商视频生成与编辑。帮助电商运营、品牌商品团队、直播带货团队与商业内容创作者直接完成“1688 电商视频生成与编辑”：既可只输入文字从零生成，也可加入图片、视频或音频控制结果；通过 AI Hive 使用时，生成前自动上传所需素材，提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for 1688 电商视频生成与编辑, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video…
ai-model-expert-ai-ad-video
AI大模型专家｜AI 广告视频。帮助品牌市场、广告代理、创意策划、制片人与投放团队直接完成“AI 广告视频”：既可只输入文字从零生成，也可加入图片、视频或音频控制结果；通过 AI Hive 使用时，生成前自动上传所需素材，提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for AI 广告视频, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video, video-to-video, audio-to-video…