sfd-video-director
Video Director
Produce multi-scene AI videos with automated QA. This skill handles the production pipeline — generation, speech verification, visual QA, assembly, and voice swap. It works with any format by converting the format's recording brief or prompt template into a vidlang spec.
The process is always the same:
- Pick a format (talking-head, ugc-b2c, ugc-yapper, etc.)
- Write a vidlang spec using that format's structure
- Run the production pipeline below
Step 0: Choose a Format
The format determines the scene structure, setting, and tone. The production pipeline stays the same regardless of format.
| Format skill | Use when | Spec adaption |
|---|---|---|
| talking-head | One person speaking to camera | Single character, varied settings per scene |
| podcast | Conversation at a desk with mic | Two characters or solo with mic visible |
More from tfcbot/shortform-distribution-skills
sfd-model-provider
>-
4sfd-api
VidJutsu — Video Intelligence API. Watch, extract, transcribe, check. The server-side gaps your agent can't fill.
3sfd-analytics
Pull performance data across connected accounts. Content audit, engagement report, and growth trends using Zernio post data and Instagram Insights.
3sfd-media-critic
Analyze video and image content using watch prompts for quality checks, verification, and deep analysis. QA gate before posting.
3sfd-schedule-posts
Schedule content to connected accounts with optimized timing and captions via Zernio.
3sfd-channel-strategy
Create a one-page channel spec — character, handle, format, niche, and 30-day content calendar for a managed account.
3