Overview
What it does
Builds a ranked, buildable hook × CTA × shot × format matrix for a proven concept, with source clip IDs for editors.
When to use it
You've found a proven concept and want the full modular combination matrix — which hook × which CTA × which product shot × which format — ranked by predicted lift, ready for editors. Where the Ad Variant Writer tests copy variations on one ad, this composes across your tagged library.
Pairs with MCP
Uplifted holds scene-level performance for every modular component, so combinations can be ranked by the components' own track records rather than guessed.
Best for
Creative producers, video editors, performance marketers.
Install
Drop this entire block into a SKILL.md file inside your Claude project’s .claude/skills/variant-spec-sheet/ folder. Claude auto-invokes it when you want a production matrix for a proven concept.
---
name: variant-spec-sheet
description: Use this skill when the user has a proven concept and wants a modular combination matrix (hook x CTA x product shot x format) ranked by predicted lift, ready to hand to editors. Composes across the Uplifted library using scene-level component performance.
---
# Variant Spec Sheet
You build the multivariate production matrix for a proven concept, grounded in component-level performance.
## Data you need
- The proven base concept and its winning components from Uplifted
- The candidate component pools: hooks (with hook_rate / hold_rate), CTAs (with click data), product shots, formats — each with scene-level performance and tags
- Spend/conversion thresholds for confidence
## How to analyze
1. Identify the base concept's structure (hook slot, body/demo slot, proof slot, CTA slot).
2. For each slot, list the top components by their own scene-level performance.
3. Score candidate combinations with a simple predicted-lift heuristic: sum of component z-scores, penalized for untested pairings and for combinations that repeat a known fatigued element.
4. Cap output at the ~8–12 highest-potential combinations — enough to test, not so many editors revolt.
## Output format
VARIANT MATRIX — [Concept]
Ranked table: Variant | Hook | Body/Demo | Proof | CTA | Format | Predicted lift | Rationale (which components carry it)
PRODUCTION NOTES — for each variant, the source clip IDs to assemble from (raw-to-final links)
TEST PLAN — recommended split, min sample per cell, primary metric
DON'T BOTHER — combinations that look tempting but repeat a fatigued or low-hold component
## Guidelines
- Predicted lift is directional, not a promise — label it as a ranking aid.
- Never propose a combination using a component flagged as fatiguing.
- Always attach source clip IDs so the matrix is buildable, not theoretical.Prompt
Builds a ranked, buildable hook x CTA x shot x format matrix for a proven concept, complete with source clip IDs for the editor. Use it to turn a single winner into a full, production-ready test slate.
Build the modular variant matrix for my proven concept, ranked by predicted lift.
Concept: {{name / asset ID}}. From Uplifted, the candidate component pools with scene-level performance: hooks (hook_rate / hold_rate), CTAs (click data), product shots, formats. {{paste or confirm MCP}}
1. Identify the concept's slots (hook / body-demo / proof / CTA).
2. Per slot, list top components by scene-level performance.
3. Score combinations (sum of component z-scores; penalize untested pairings + fatigued elements).
4. Return the top 8–12 combinations.
Output: a ranked matrix (Variant | Hook | Body | Proof | CTA | Format | Predicted lift | Rationale), production notes with source clip IDs per variant, a test plan, and a "don't bother" list.
Predicted lift is directional. Never use a fatiguing component. Always attach clip IDs.
EXPECTED OUTPUT:
- A ranked, buildable variant matrix for the concept
- Source clip IDs per variant so editors can assemble immediately
- A test plan and a short "don't bother" list