reference-decode

v2026.09.24

Turn reference videos, frames, or contact sheets into reusable hook and visual rules for new creative prompts, with clear imitation boundaries.

GitHub
安装命令
npx skhub add postplusai/reference-decode
Markdown
SKILL.md

Reference Decode

Use When

  • A benchmark video, contact sheet, frame set, rough idea, or source material needs to become promptable structure.
  • You need the hook essence, viewer question, visual grammar, and forbidden drift before storyboard or request writing.
  • A no-reference brief still needs a proxy structure before prompt work.

Do Not Use When

  • Do not create the final storyboard grid or execution request here.
  • Do not copy faces, exact wardrobe, creator identity, exact location, or exact overlays from benchmark material.

Core Rule

Do not summarize references as "good vibe", "nice pacing", or "strong chemistry". Extract four objects:

  • hookEssence
  • viewerQuestion
  • mustCopyVisualGrammar
  • forbiddenDrift

Default Workflow

  1. Use the smallest sufficient source set: hook-first clip, first 0-5 seconds, hook-first contact sheet, supporting note, or full style board only if needed.
  2. Decode the opening mechanism: first clear promise, viewer question, and the exact visual structure that makes the promise legible.
  3. Separate structure from identity. Keep camera grammar, shot order, object logic, timing, and relationship logic; do not keep exact identity details.
  4. Create a compact decode artifact when it is useful.
  5. Print or return the decode block before storyboard or request writing.

No-Reference Mode

When no usable reference exists, operate in proxy mode:

  • start from the chosen segment pattern
  • infer the likely viewer question
  • express must-copy grammar as scene anchors, not imitation notes
  • express forbidden drift as anti-generic safeguards
  • state that the output is brief-derived, not observed from footage

Output Shape

The artifact contains hookEssence, viewerQuestion, mustCopyVisualGrammar, and forbiddenDrift.

Stop Conditions

  • Stop when required user intent, source evidence, or owned input artifacts are missing and guessing would change the result.

Handoff

  • For a grid or panel plan, preserve the decoded evidence in the requested layout before image generation.
  • Image generation -> image-batch-runner.
  • Video generation -> video-batch-runner; pass the useful decoded grammar as context, not as a second contract file.

Public Command Boundary

  • Choose the smallest matching command or workflow from the user input and run it directly.

  • This public skill is instruction-driven. Produce the artifact described by the workflow directly from the available evidence.

  • Do not use unpublished execution paths or local tools.

  • If the CLI returns a quote-confirmation challenge, obtain user approval for its scope and cost before running postplus quote confirm --json --challenge-file <challenge.json> and retry with the returned token.

发现
标签

此技能尚未发布标签。

版本
最新版本元数据

版本

v2026.09.24

发布时间

2026年9月24日

分类

未分类

许可证

NOASSERTION

源路径

skills/10-routing/reference-decode

默认分支

main

最新提交

51a1c76

Tree SHA

ee441c2