Skip to content

T8mars/minimax-h3-prompt-skill-T8 / skills/stage-two-turn-pause-reaction

stage-two-turn-pause-reaction

Verified

Create original short videos using the 对话喜剧|双轮停顿无声反应 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 md2.5 KB
agents/openai.yamlconfig438 B
references/summary.mdmarkdown1.2 KB
references/template.mdmarkdown4.2 KB

references/template.md

View on GitHub
# 对话喜剧|双轮停顿无声反应 Template

## Mechanism

Use a neutral two-shot to establish equal conversational footing, show one visible speaking turn, hold a clearly readable pause, show a second speaking turn, and end on the first speaker's silent reaction. The source supports only this visual turn-taking and reaction grammar; any question, answer meaning or comic mismatch is an explicitly original instantiation slot, never a source-derived fact.

## Invariants

### inv-01

- Rule: Begin with a neutral two-shot and stable eye lines.
- Purpose: Makes later singles spatially and socially legible.
- Failure if removed: Opening on isolated faces hides the relationship.

### inv-02

- Rule: Use one compact first speaking turn, with its meaning supplied only by the new original instance.
- Purpose: Creates a clean expectation without inventing source semantics.
- Failure if removed: Multiple setup turns blur ownership and weaken the pause.

### inv-03

- Rule: Hold one clearly readable pause between the two visible speaking turns.
- Purpose: Builds a timing interval without inventing source semantics.
- Failure if removed: An immediate second turn removes the visible timing contrast.

### inv-04

- Rule: Use one compact second speaking turn with minimal gesture; its meaning is an original instance variable.
- Purpose: Preserves the visible turn-taking structure while allowing new content.
- Failure if removed: A large performance or extra line turns the held exchange into a sketch montage.

### inv-05

- Rule: End on the first character's silent reaction with no additional speaking turn.
- Purpose: Lets the final visible reaction complete the timing pattern.
- Failure if removed: Additional speaking turns weaken the final hold.


## 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

- 开场双人中景建立稳定眼线
- 只保留一轮第一人说话
- 两轮之间有一次清楚停顿
- 第二人只说一轮且动作克制
- 结尾第一人无声反应且不再增加说话轮次

## Anti-Copy Boundary

- Friends
- Joey Tribbiani
- Chandler Bing
- Central Perk
- source dialogue and wardrobe

## Transfer Tests

1. Two original night guards sit in a museum break room. One asks whether the marble statue blinked; after a pause the other says, 'Only when you look away,' and the first guard silently turns toward the dark gallery.
   - 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. Two lighthouse keepers share tea. One asks whether the foghorn ever gets lonely; after a pause the other answers, 'It calls everyone,' and the first keeper stops stirring.
   - 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