Timestamped Image Pack Generator
Take a voice-over transcript with timestamps and generate one style-locked image per timestamp, auto-downloaded and named for easy timeline placement.
Before & after
Same prompt, same agent — the only difference is the skill.
That's a good idea for a faceless video. You could generate images based on the script content. It would probably help to break the script into segments first and then describe what each image should show. I can help you think through what visuals would work for each part.
TIMESTAMPED IMAGE PACK OUTPUT INPUT • Script: 240-second voiceover on productivity habits • Niche: Productivity / business advice • Style: Minimalist line drawings (MS Paint aesthetic) • Aspect ratio: 16:9 (YouTube) • Resolution: 1920x1080 GENERATED FILES (20 images, 12-second intervals) 0.00.png → "5 habits of productive people" (title card, simple frame) 0.12.png → Person at desk, coffee mug, clock 0.24.png → Checklist with 3 items 0.36.png → Brain diagram, light bulb 0.48.png → Calendar view, X marks on days 1.00.png → Phone on desk, crossed out (distraction) 1.12.png → Morning routine icons (7am, exercise, shower) 1.24.png → Deep work - person with headphones 1.36.png → Time blocks (color-coded) 1.48.png → Energy chart (high/low throughout day) 2.00.png → Batch processing illustration 2.12.png → Meeting room with 3 people 2.24.png → Notes on whiteboard 2.36.png → Break time - person stretching 2.48.png → Nutrition: plate of food 3.00.png → Sleep: person in bed, zzz 3.12.png → Weekly planning - 7-day grid 3.24.png → Recap checklist (5 habits listed) 3.36.png → Call to action text 3.48.png → Your logo + social handles (end card) DOWNLOAD: All 20 files auto-named by timestamp, ready for drag-and-drop into CapCut/Premiere. Timeline placement: each image holds for 12 seconds. STYLE LOCK REFERENCE: Consistent pen weight (2px), palette (3 colors), and layout spacing across all 20 images.
About this skill
name: timestamp-image-pack-generator description: Take a voice-over transcript with timestamps and generate one style-locked image per timestamp, auto-downloaded and named for easy timeline placement. Use when working on timestamped image pack generator.
Timestamped Image Pack Generator
End-to-end script-to-visuals skill for faceless YouTube. Ingests a transcript (with second-level timestamps from TurboScribe or equivalent), calls Higgsfield through Claude Code to render one image per timestamp in a locked visual style (default MS-Paint stick figures), then downloads each file named after its timestamp so editing is literally drag to next timestamp. Use when spinning up a faceless channel that needs 20+ visuals per video without a designer.
What you get
- Per-timestamp images
- Consistent style guide
- Timestamp-named files
- Batch downloader
- Timeline placement recipe
- Style-lock reference sheet
Customize your output
- Style: MS Paint, storybook, photoreal, watercolor, anime
- Niche prompts: Zen, space, animals, crime, motivation
- Image count cap: 20, 40, 60
- Resolution: 1920x1080, 2560x1440
- Aspect ratio: 16:9, 9:16, 1:1
- Editor target: CapCut, Premiere, DaVinci
Example output
'A 60-second script produces 20 images named 0.00.png through 0.55.png, ready to drop into CapCut or Premiere.'
Best for
Faceless YouTube creators, sleep and meditation channels, kids-story creators.
Note: Depends on Higgsfield credits. TurboScribe or equivalent for timestamped SRT. High confidence.
SKILL.md preview
---
name: timestamp-image-pack-generator
description: Use when spinning up a faceless video that needs one style-locked image generated per transcript timestamp, downloaded and named for direct timeline placement.
version: 1.0.0
category: YouTube/Video
author: AgentVolt
license: proprietary
tags:
- youtube
- video
- p4
---
# Timestamped Image Pack Generator
Takes a timestamped voice-over transcript and generates one style-locked image per timestamp, downloading and naming each file so it drops straight onto a video timeline.
## When to use
… (sign up to view the full skill)