Skip to content

T8mars/minimax-h3-prompt-skill-T8 / skills/build-earned-arrival-journey

build-earned-arrival-journey

Verified

Create original short videos using the 人物旅程|从困境走向目标 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.yamlconfig344 B
references/summary.mdmarkdown930 B
references/template.mdmarkdown6.1 KB

references/template.md

View on GitHub
# 人物旅程|从困境走向目标 Template

## Mechanism

A recognizable person remains the emotional coordinate while an externally observed journey moves from constrained work pressure into an expanded goal space. Context is revealed through material interactions and camera parallax rather than direct exposition; scale and light increase toward the transition, and a final task-completing interaction—not a gesture to the lens—turns anticipation into earned arrival. Shot count, camera carrier and reveal order are variable.

## Invariants

### inv-01

- Rule: Keep one recognizable person emotionally legible across changing spaces, using face, posture or task behavior as the recurring anchor rather than requiring a selfie.
- Purpose: Preserves human stakes and orientation while allowing external, profile, wide or body-mounted camera implementations.
- Failure if removed: Without a recurring human coordinate, the route becomes anonymous location coverage; requiring a close selfie would make the template surface-specific.

### inv-02

- Rule: Make every contextual reveal originate from a physical interaction—moving a cart, opening geometry, passing an obstacle or handing off an object—and let the camera discover it through parallax, reframing or occlusion.
- Purpose: Makes camera change causal and informative without prescribing wrist turns or a return-to-face pattern.
- Failure if removed: Unmotivated coverage feels decorative; copying the same turn-and-recover move makes new instances mechanically identical.

### inv-03

- Rule: Create one legible transition from compressed effort to expanded possibility using at least two of scale, light, depth, sound or traffic flow; the transition may occur through a door, lift, ramp, curtain, bend or temporal match.
- Purpose: Gives the physical route a visible emotional direction.
- Failure if removed: If every space has equal brightness and scale, arrival has no visual payoff.

### inv-04

- Rule: Choose a capture grammar appropriate to each new world and keep its rules consistent; controlled documentary texture may come from parallax, shallow focus, operator lag or environmental occlusion, not a fixed bundle of DV defects.
- Purpose: Protects immediacy while allowing polished 35mm, shoulder documentary, fixed observational or body-mounted variants.
- Failure if removed: A copied artifact bundle reveals the source; random defects or identity drift destroy route comprehension.

### inv-05

- Rule: Resolve arrival through one task-completing physical interaction between the person and the goal environment, while their emotional state remains readable without addressing the lens.
- Purpose: Closes spatial and emotional questions through consequence rather than a copied reaction gesture.
- Failure if removed: A generic smile or hand sign does not prove arrival; a destination-only cut loses the human cost that made it meaningful.


## Variable Slots

| Slot | Constraint |
|---|---|
| traveler | One original adult subject with stable identity and a clear reason to move. |
| prep_space | A compressed, imperfectly lit working area with readable practical obstacles. |
| context_reveals | One to three physically motivated discoveries whose order and camera implementation change with the instance. |
| material_handoff | An object, obstacle or collaborator changes the route or objective; avoid mirror-based self-checks. |
| goal_threshold | A brighter, wider destination visibly different from the prep space. |
| capture_texture | Select an instance-specific external, fixed, body-mounted or handheld grammar; do not reuse a bundled source artifact signature. |
| resolution_action | A material action that proves the person has entered or completed the goal, with no direct-to-camera hand sign. |
| shot_structure | Choose three to six events with an order justified by the new task; do not map source beats one-to-one. |

## Required Human-Facing Anchors

- 起点困境明确
- 目标空间提前可见或可理解
- 至少三个连续物理过渡
- 抵达后完成目标动作

## Anti-Copy Boundary

- source face, ethnicity cues, hair, earrings and stage wardrobe
- concert backstage corridor, dressing mirror, curtain and exact stage-light composition
- exact dialogue, countdown, finger-heart gesture and performer premise
- creator-specific DV artifact bundle, wrist-turn/return pattern, mirror readiness check or shot timing copied beat for beat

## Transfer Tests

1. An original ceramic artist is filmed by an external stabilized 35mm camera while pushing a padded kiln cart through a cramped workshop. Shelves create parallax, assistants open a canvas loading bay, and the route expands into a dawn street market where she unwraps one still-warm bowl for the first waiting buyer.
   - Preserved: inv-01, inv-02, inv-03, inv-04, inv-05
   - Changed: traveler, prep_space, context_reveals, material_handoff, goal_threshold, resolution_action, shot_structure
2. A telescope technician crosses a narrow daytime maintenance gantry in three long lateral shots, passing a suspended mirror segment and a safety-team handoff before the observatory dome opens to a star-filled night created by a time-match; she seats the final instrument and watches the first signal arrive.
   - Preserved: inv-01, inv-02, inv-03, inv-04, inv-05
   - Changed: traveler, prep_space, context_reveals, material_handoff, goal_threshold, capture_texture, resolution_action, shot_structure

## 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