Skip to content

T8mars/minimax-h3-prompt-skill-T8 / skills/handoff-ensemble-focus

handoff-ensemble-focus

Verified

Create original short videos using the 群演聚焦接力|全场到主位再回合奏 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.yamlconfig482 B
references/summary.mdmarkdown1.2 KB
references/template.mdmarkdown4.1 KB

references/template.md

View on GitHub
# 群演聚焦接力|全场到主位再回合奏 Template

## Mechanism

Establish a complete ensemble and its audience or work field, bring two central contributors into a shared action, isolate one lead long enough for a complete proof phrase while the ensemble remains spatially implied, then reintroduce the co-lead and finish on a wider synchronized group state.

## Invariants

### inv-01

- Rule: Establish the full ensemble and surrounding response field before isolating a lead.
- Purpose: Makes later focus changes legible.
- Failure if removed: Opening close hides the ensemble stakes.

### inv-02

- Rule: Bring two central contributors into one shared action before ownership narrows.
- Purpose: Defines the co-lead relationship.
- Failure if removed: An immediate solo gives no handoff.

### inv-03

- Rule: Give one lead enough uninterrupted screen ownership to complete a proof phrase.
- Purpose: Makes the focus transfer countable.
- Failure if removed: Rapid cutting never establishes ownership.

### inv-04

- Rule: Reintroduce the co-lead before the ending.
- Purpose: Returns focus from individual to partnership.
- Failure if removed: A solo-only ending abandons the opening pair.

### inv-05

- Rule: Finish wide enough to show the ensemble responding in one synchronized state.
- Purpose: Closes the nested focus levels.
- Failure if removed: Ending close loses the group payoff.


## 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

- Establish the full ensemble and surrounding response field before isolating a lead.
- Bring two central contributors into one shared action before ownership narrows.
- Reintroduce the co-lead before the ending.
- Finish wide enough to show the ensemble responding in one synchronized state.

## Anti-Copy Boundary

- source retro male singers and band
- Eddie & The Comet Tails sign
- source stage, microphones and audience
- the exact rock performance blocking and wardrobe

## Transfer Tests

1. In a kinetic sculpture workshop, two lead technicians begin before a full crew and moving test wall; the camera isolates the color-calibration lead for one complete adjustment, reintroduces the motion lead, and ends wide as every module synchronizes.
   - 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. At a botanical lantern launch, two coordinators begin among a full volunteer ring; one coordinator receives a complete close proof while setting the timing beacon, the second returns to trigger the release, and the final wide shows the whole ring lifting lantern pods together.
   - 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