Skip to content

T8mars/minimax-h3-prompt-skill-T8 / skills/stage-progressive-character-reveal

stage-progressive-character-reveal

Verified

Create original short videos using the 角色登场|细节到全身揭晓 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 md2.4 KB
agents/openai.yamlconfig338 B
references/summary.mdmarkdown911 B
references/template.mdmarkdown4.1 KB

references/template.md

View on GitHub
# 角色登场|细节到全身揭晓 Template

## Mechanism

Reveal one stable character through a controlled information ladder: signature detail, partial or rear silhouette, face, one restrained personality action and complete hero view. Each stage must answer one identity question while preserving exact defining features and calm secondary motion. Character, medium, environment, reveal detail, gesture, camera axis and mood are variable.

## Invariants

### inv-01

- Rule: Begin on one signature detail rather than the full design.
- Purpose: Creates an identity question and gives small features value.
- Failure if removed: A full-body opening removes progressive revelation.

### inv-02

- Rule: Use a partial or rear silhouette before showing the face.
- Purpose: Establishes body language and delays recognition.
- Failure if removed: Jumping directly to a portrait flattens the reveal ladder.

### inv-03

- Rule: Preserve defining identity, materials and silhouette through every stage.
- Purpose: Makes separate shots read as one character.
- Failure if removed: Redesign drift breaks trust and comparison.

### inv-04

- Rule: Allow only one restrained signature action after the face reveal.
- Purpose: Adds personality without replacing presentation with action.
- Failure if removed: Multiple gestures or combat beats dilute the introduction.

### inv-05

- Rule: End on a clean complete hero view and hold it.
- Purpose: Provides the promised design proof.
- Failure if removed: Cropping or immediate exit denies completion.


## Variable Slots

| Slot | Constraint |
|---|---|
| lead_subject | An original subject whose identity and silhouette remain stable. |
| setting | A new setting with fixed spatial anchors and no source-specific location. |
| escalation_variable | One readable variable that changes monotonically or in countable stages. |
| performance_rule | One restrained performance rule that makes the mechanism legible. |
| camera_grammar | A coherent information order that does not copy the source shot boundaries. |
| payoff | One clean physical or graphic consequence that closes the causal chain. |
| sound_family | A new hierarchy of diegetic cues supporting each state change. |

## Required Human-Facing Anchors

- 从可识别细节开始
- 揭晓尺度逐步扩大
- 角色只做一次代表动作
- 以全身定格完成身份确认

## Anti-Copy Boundary

- source black-haired female design with cream oversized sleeves and red ties
- repeated character-sheet strip beneath every shot
- source sunlit stone courtyard and exact orbit
- source hand-to-eye gesture, boots and final low-angle pose

## Transfer Tests

1. A retro-futurist train conductor is revealed through a gloved ticket-punch detail, a side silhouette behind frosted carriage glass, a face reveal as the door opens, one waist-level ticket punch and a high-angle full-body platform hold.
   - 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. A moss-armored forest courier appears through a shoulder clasp, a side silhouette behind hanging roots, a profile reveal, one waist-level map fold and a complete eye-level stance beneath a canopy.
   - 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