<< All versions

Skill v1.0.0

currentAutomated scan100/100
t8mars/minimax-h3-prompt-skill-t8/performer-anchor-semantic-lyric-escalation
──Details
PublishedOctober 8, 2026 at 12:23 AM
Content Hashsha256:d180913400765b72...
Git SHA5882fc3d72d7
──Files
Files (1 file, 2.7 KB)
SKILL.md2.7 KBactive
SKILL.md · 48 lines · 2.7 KB

version: "1.0.0" name: performer-anchor-semantic-lyric-escalation description: "Create original short videos using the 歌词表演|稳定主唱锚点与逐句语义升能 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."


歌词表演|稳定主唱锚点与逐句语义升能

Create a new execution from the reusable mechanism, not a surface reskin of any reference video.

Workflow

  1. Read references/summary.md for fit, input slots, and the concise starting example.
  2. Read references/template.md completely before drafting.
  3. Preserve the user's subject and objective, then fill every missing scene, trigger, event-chain, camera, sound, and payoff slot.
  4. Treat these anchors as mandatory:
  • Introduce one stable original performer, performance tool and first lyric in the same readable opening relation.
  • Give each lyric line exact readable copy and one distinct motion or spatial behavior derived from its meaning.
  • Use graphic elements to expand the performance space without covering the face, hands or primary action.
  • After the last lyric proof, reduce text density and end on a longer performer-led movement release.
  1. Change source-specific people, setting, props, palette, dialogue, shot boundaries, sound family, and payoff surfaces together.
  2. Compile MiniMax H3 and Seedance 2.0 independently; do not leak one model's field syntax into the other.
  3. Silently verify anchor coverage, continuity, timing, physical causality, and anti-copy distance before returning the final prompts.

MiniMax H3

  • Use the current official H3 task grammar and language profile.
  • Separate integrated visual action, overall soundscape, and non-diegetic music or explicit silence.
  • Use timestamps only to make event order executable; keep shots consecutive and duration-safe.

Seedance 2.0

  • Define stable subjects once and preserve event order, camera motivation, sound intent, and overall duration.
  • Use a simple paragraph for simple concepts or an ordered multi-shot structure for complex concepts.
  • State overall duration once; do not copy H3 field labels or per-shot timecode grammar.

Output

Return one concept sentence, the filled slots, an anchor-coverage check, one MiniMax H3 prompt, one Seedance 2.0 prompt, and a short anti-copy validation note.

Non-Negotiable

  • A subject-only request is underspecified. Preserve that subject and complete the mechanism instead of returning a generic portrait or showcase.
  • Do not omit, reorder, or weaken a required anchor.
  • Do not reuse source people, brands, dialogue, exact storyboard, signature props, exact timings, or recognizable effect surfaces.
All versions