Skip to content

T8mars/minimax-h3-prompt-skill-T8 / skills/live-subject-print-collage-ad-relay

live-subject-print-collage-ad-relay

Verified

Create original short videos using the 实拍印刷层接力|人物、商品细节与字卡共同推进 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.

FileKindSize
SKILL.mdskill md2.8 KB
agents/openai.yamlconfig729 B
references/summary.mdmarkdown2.1 KB
references/template.mdmarkdown5.9 KB

references/template.md

View on GitHub
# 实拍印刷层接力|人物、商品细节与字卡共同推进 Template

## Mechanism

Establish one original clearly adult campaign subject with at least three stable identity and wardrobe anchors in a live-action frame. Introduce a coherent print-material system—paper grain, torn masks, ink fields and concise original text—and require every new layer to be handed off by a visible subject action, garment detail or registered spatial edge. Alternate full-body proof, at least two material-detail macros, one environment-based performance and at least two substantially different poster layouts while preserving the same subject and garment family. Keep text short, readable and causally tied to the evidence beside it. End by gathering the previously proven subject, details and message hierarchy into one held campaign sheet. The reusable mechanism is live-subject-to-print registration, evidence-linked typography, material-detail relay, layout variation and consolidated poster closure—not the source adult, face, hair, garments, motorcycle, roadside setting, national imagery, decades, slogans, brands, palette, layouts, creator identity or timing.

## Invariants

### inv-01

- Rule: Establish one clearly adult original subject with at least three stable identity and wardrobe anchors before the first print conversion.
- Purpose: Gives every later cutout, portrait and lineup a verifiable human and garment baseline.
- Failure if removed: Without a stable opening identity, poster variations can conceal character and wardrobe drift.

### inv-02

- Rule: Use one coherent print-material system and let each new layer enter through a visible action, detail or registered spatial edge.
- Purpose: Turns collage transitions into causal handoffs rather than decorative overlays.
- Failure if removed: Arbitrary paper wipes can cover discontinuity without advancing the campaign.

### inv-03

- Rule: Alternate full-body proof with at least two distinct garment or object detail macros.
- Purpose: Connects campaign attitude to concrete material evidence.
- Failure if removed: A sequence of portraits and slogans alone does not prove the advertised design.

### inv-04

- Rule: Use at least two substantially different poster layouts while preserving subject, wardrobe and message hierarchy.
- Purpose: Demonstrates that the identity system survives editorial variation.
- Failure if removed: Repeating one composition with new words does not test reusable layout behavior.

### inv-05

- Rule: Gather previously proven subject, details and concise messages into one final held campaign sheet.
- Purpose: Creates a readable terminal state instead of ending mid-transition.
- Failure if removed: A final unrelated portrait leaves the evidence and message modules unresolved.


## Variable Slots

| Slot | Constraint |
|---|---|
| lead_subject | An original stable subject or pair with a readable role. |
| setting | A new setting with fixed spatial anchors and no source-specific surface. |
| escalation_variable | One causal variable that changes through visible stages. |
| performance_rule | A restrained acting or motion rule that keeps the mechanism legible. |
| camera_grammar | An information order that proves each state without copying source shot boundaries. |
| payoff | A clean final physical, informational or social consequence. |
| sound_family | An original hierarchy of diegetic cues; no unsupported source-audio claim. |

## Required Human-Facing Anchors

- Establish one clearly adult original subject with at least three stable identity and wardrobe anchors before the first print conversion.
- Use one coherent print-material system and let each new layer enter through a visible action, detail or registered spatial edge.
- Use at least two substantially different poster layouts while preserving subject, wardrobe and message hierarchy.
- Gather previously proven subject, details and concise messages into one final held campaign sheet.

## Anti-Copy Boundary

- the source adult male fashion subject, face, hair, body, sunglasses and exact performance
- the source denim, leather, boots, belt, motorcycle, workwear details and branded styling
- the source American flag, roadside service station, route symbols, national and decade references
- the source slogans, visible brand-like marks, red-cream-black palette, torn-paper shapes and exact poster layouts
- the source camera order, typography timing, creator identity and 15-second fashion-commercial wording

## Transfer Tests

1. An adult coastal field engineer in a slate utility jacket moves between live harbor footage, cyan technical-paper cutouts, zipper and fabric macros, two evidence-linked short statements and a final field-equipment campaign sheet.
   - Preserved: inv-01, inv-02, inv-03, inv-04, inv-05
   - Changed: lead_subject, setting, escalation_variable, performance_rule, camera_grammar, payoff, sound_family
2. An adult ceramic artist in a moss apron moves between studio footage, fiber-paper masks, clay and stitching macros, two changing editorial grids and a final workshop exhibition poster.
   - Preserved: inv-01, inv-02, inv-03, inv-04, inv-05
   - Changed: lead_subject, setting, escalation_variable, performance_rule, camera_grammar, payoff, sound_family

## Model Skeletons

### MiniMax H3

    integrated_multimodal_description: [new subject, environment, ordered actions, camera, light and final state preserving every anchor]
    overall_soundscape: [diegetic ambience, action cues and causal payoff]
    non_diegetic_music: [original music arc or N/A]

### Seedance 2.0

    任务:[原创实例意图]
    总时长约[4–15]秒。
    主体定义:[稳定人物、物体与空间关系]
    事件或镜头:[按因果顺序实现全部锚点]
    整体风格与画质:[原创媒介、光影、色彩与声音]
    约束:[连续性、物理逻辑、反复制与结尾状态]

Adapt shot count to the user's concept. Preserve the causal mechanism, not a fixed storyboard.
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 196kUpdated Claude CodeCodexVerifiedInstall