T8mars/minimax-h3-prompt-skill-T8 / skills/build-viewpoint-scale-spectacle-ladder
build-viewpoint-scale-spectacle-ladder
VerifiedCreate original short videos using the 尺度奇观阶梯|每镜重置参照再逼近 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.5 KB |
| agents/openai.yaml | config | 459 B |
| references/summary.md | markdown | 1.1 KB |
| references/template.md | markdown | 4.0 KB |
references/template.md
View on GitHub# 尺度奇观阶梯|每镜重置参照再逼近 Template
## Mechanism
Reset a familiar viewpoint and scale anchor in each vignette, introduce one impossible airborne form that preserves readable silhouette, vary observer distance and occlusion, then escalate proximity until the final viewpoint encounter feels immediate rather than merely larger.
## Invariants
### inv-01
- Rule: Give each vignette an immediately familiar scale anchor.
- Purpose: Makes the impossible size measurable.
- Failure if removed: A blank sky provides no scale proof.
### inv-02
- Rule: Use one dominant impossible silhouette per vignette.
- Purpose: Keeps the spectacle readable.
- Failure if removed: Several equal forms create visual noise.
### inv-03
- Rule: Change observer carrier or occlusion between vignettes.
- Purpose: Prevents a repetitive size montage.
- Failure if removed: Identical viewpoints flatten the ladder.
### inv-04
- Rule: Increase proximity, not just nominal size.
- Purpose: Creates a real escalation toward encounter.
- Failure if removed: Distant forms remain postcards.
### inv-05
- Rule: End with a viewpoint-level encounter that preserves spatial legibility.
- Purpose: Converts spectacle into immediate stakes.
- Failure if removed: An abstract final close-up loses the observer relationship.
## 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
- Give each vignette an immediately familiar scale anchor.
- Use one dominant impossible silhouette per vignette.
- Increase proximity, not just nominal size.
- End with a viewpoint-level encounter that preserves spatial legibility.
## Anti-Copy Boundary
- source giant whale, manta, nautilus, jellyfish and shark
- Shanghai skyline, airplane window, highway and car POV
- the exact animal order and city landmarks
- source blue atmospheric spectacle palette
## Transfer Tests
1. Five original airborne seed structures appear over a coastal wind farm, train window, quarry road, public greenhouse and maintenance rover; each new anchor shortens distance until a translucent seed sail crosses directly over the rover canopy.
- 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. Five enormous folded-paper weather instruments drift through an archive city, observatory window, tram corridor, plaza and bicycle POV, with increasing occlusion and a final near overhead pass.
- 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.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| 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: 196k | Updated | Claude CodeCodex | Verified | Install |