T8mars/minimax-h3-prompt-skill-T8 / skills/contract-scale-into-evidence
contract-scale-into-evidence
VerifiedCreate original short videos using the 景别收紧|从世界到眼神 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 | 2.4 KB |
| agents/openai.yaml | config | 362 B |
| references/summary.md | markdown | 1011 B |
| references/template.md | markdown | 4.5 KB |
references/template.md
View on GitHub# 景别收紧|从世界到眼神 Template
## Mechanism
Begin with monumental environment scale and a tiny stable subject pair. Contract framing in discrete evidence steps—paired medium, full-body investigation, object inspection, subject-owned mechanism insert and eye-level reaction—so every scale change answers one question and raises a more personal one. Preserve route, axis and identity, keep performance restrained, and stop at the facial endpoint instead of adding another action branch.
## Invariants
### inv-01
- Rule: Establish world scale, route and the stable subject group in an extreme or very wide opening.
- Purpose: Gives later close evidence a measurable spatial and emotional baseline.
- Failure if removed: Opening close removes the scale contrast and makes later inserts feel arbitrary.
### inv-02
- Rule: Contract framing through ordered information layers rather than random beauty shots.
- Purpose: Turns camera scale into an evidence funnel.
- Failure if removed: Repeated similar coverage reveals no new question and produces a flat montage.
### inv-03
- Rule: Move the evidence from the shared environment to a local object and then to a mechanism owned by the lead subject.
- Purpose: Raises personal stakes without requiring a copied threat or effect.
- Failure if removed: Unrelated props do not create an inward causal progression.
### inv-04
- Rule: Preserve the same route axis, subject identities and wardrobe or material markers across every scale change.
- Purpose: Lets the audience read all shots as one continuous investigation.
- Failure if removed: Continuity drift makes the scale ladder look like disconnected footage.
### inv-05
- Rule: End on one restrained face or sensor response immediately after the closest mechanism proof.
- Purpose: Converts physical evidence into a readable human or system endpoint.
- Failure if removed: A new action after the reaction restarts the sequence and weakens the funnel closure.
## Variable Slots
| Slot | Constraint |
|---|---|
| lead_subject_group | One stable person, pair or machine group whose identity remains continuous. |
| monumental_setting | A setting with a readable route and strong wide-scale geography. |
| local_discovery | One small external object or state that justifies stopping. |
| owned_mechanism | One tool, garment mechanism or device physically associated with the lead subject. |
| scale_ladder | A deliberate wide-to-close information order in which each scale reveals new evidence. |
| performance_rule | Restrained testing and recognition rather than exaggerated reaction. |
| final_response | One face, lens or status response that closes the sequence. |
## Required Human-Facing Anchors
- 景别持续收紧
- 人物空间关系稳定
- 证据从环境转到局部再到装置
- 最后用近景反应闭合
## Anti-Copy Boundary
- two wuxia women in white and green robes
- misty Chinese immortal valley settlement
- silver sword, pebble test and the source Mandarin dialogue
- the unverified four-step audio-before-action rule and exact source shot boundaries
## Transfer Tests
1. Two orbital engineers cross a vast repair bay, stop at a washer pulled toward a sealed bulkhead, inspect a wrist seal tester carrying the same pulse and end on one engineer listening toward the door.
- Preserved: inv-01, inv-02, inv-03, inv-04, inv-05
- Changed: lead_subject_group, monumental_setting, local_discovery, owned_mechanism, scale_ladder, performance_rule, final_response
2. A ranger pair crosses a giant wind farm, kneels at a frost-covered feather, checks the same crystalline growth on a handheld vane and ends on a controlled gaze toward one silent turbine.
- Preserved: inv-01, inv-02, inv-03, inv-04, inv-05
- Changed: lead_subject_group, monumental_setting, local_discovery, owned_mechanism, scale_ladder, performance_rule, final_response
## 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: 194k | 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: 194k | 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: 194k | Updated | Claude CodeCodex | Verified | Install |