Skip to content

T8mars/minimax-h3-prompt-skill-T8 / skills/reveal-environment-through-performance-pullback

reveal-environment-through-performance-pullback

Verified

Create original short videos using the 表演让位于环境|近脸到全景的连续退镜 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 md2.6 KB
agents/openai.yamlconfig492 B
references/summary.mdmarkdown1.2 KB
references/template.mdmarkdown4.1 KB

references/template.md

View on GitHub
# 表演让位于环境|近脸到全景的连续退镜 Template

## Mechanism

Begin in an identity-close performance frame, keep the performance continuous while one unbroken pullback gradually transfers visual dominance from face to body and then to a responsive environment, and end with the performer still readable inside the now-dominant wide setting.

## Invariants

### inv-01

- Rule: Open close enough to establish one stable performer identity.
- Purpose: Gives the later scale transfer a human anchor.
- Failure if removed: Opening wide makes the performer secondary too early.

### inv-02

- Rule: Keep one continuous performance thread through the camera retreat.
- Purpose: Prevents the pullback from becoming scenery montage.
- Failure if removed: Stopping performance breaks the causal link.

### inv-03

- Rule: Reveal the first environmental response before the frame becomes wide.
- Purpose: Connects performer and setting gradually.
- Failure if removed: A sudden final background replacement feels unrelated.

### inv-04

- Rule: Transfer visual dominance through camera distance rather than a subject transformation.
- Purpose: Makes the scale shift legible and reusable.
- Failure if removed: Changing the performer instead of the frame changes the mechanism.

### inv-05

- Rule: End wide with both performer and responsive environment readable.
- Purpose: Completes the relationship without losing identity.
- Failure if removed: A landscape-only ending discards the opening anchor.


## Variable Slots

| Slot | Constraint |
|---|---|
| lead_subject | An original stable subject or pair whose role is clear without source identity. |
| setting | A materially new setting with fixed spatial anchors and no source-specific location. |
| causal_carrier | One object, route, mark or device that visibly carries the causal chain. |
| state_change | Five ordered states with observable handoffs, not a decorative montage. |
| camera_grammar | A new proof-oriented information order that does not copy source shot boundaries. |
| payoff | A held final consequence that resolves or recontextualizes the setup. |
| sound_family | An original hierarchy of story-world cues supporting each visible change. |

## Required Human-Facing Anchors

- Open close enough to establish one stable performer identity.
- Keep one continuous performance thread through the camera retreat.
- Transfer visual dominance through camera distance rather than a subject transformation.
- End wide with both performer and responsive environment readable.

## Anti-Copy Boundary

- source female singer
- source shoreline and aurora
- source translucent dress and face lighting
- the exact vocal-performance pullback

## Transfer Tests

1. A glass-bowl artisan begins in a close face-and-hands frame; one continuous retreat reveals resonating bowls, then a bioluminescent greenhouse canopy responding in expanding rings while the artisan keeps circling one mallet.
   - Preserved: inv-01, inv-02, inv-03, inv-04, inv-05
   - Changed: lead_subject, setting, causal_carrier, state_change, camera_grammar, payoff, sound_family
2. A weather engineer begins close while turning one tuning dial; the camera retreats through a tower chamber as suspended fabric vanes respond one by one, ending with the engineer small beneath the full wind lattice.
   - Preserved: inv-01, inv-02, inv-03, inv-04, inv-05
   - Changed: lead_subject, setting, causal_carrier, state_change, 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: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated 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: 194kUpdated Claude CodeCodexVerifiedInstall