Reference Decode
- 688 installs
- 19 repo stars
- Updated July 27, 2026
- postplusai/postplus-skills
reference-decode is a PostPlus routing-contracts skill that decodes benchmark videos, contact sheets, frames, or rough ideas into structured hook and visual-grammar objects before storyboard or video-generation prompts a
About
reference-decode is a PostPlus routing and contracts family skill that decodes benchmark videos, contact sheets, frame sets, or rough creative notes into reusable prompt structure before storyboard or video generation work begins. The skill extracts hook essence, the viewer question, must-copy visual grammar, and forbidden drift constraints so downstream prompts stay faithful to the reference without vague creative briefs. Developers and creative technologists reach for reference-decode when a benchmark clip or mood board must become explicit generation instructions rather than subjective descriptions. The workflow supports both reference-backed briefs and no-reference cases that still need disciplined prompt scaffolding. reference-decode outputs structured objects consumed by storyboard writers and video model prompt authors in PostPlus pipelines. The skill does not render video, run generation jobs, or replace final copywriting; it front-loads decode artifacts that keep hooks and visual rules consistent across generative steps.
- Extracts four required objects: hookEssence, viewerQuestion, mustCopyVisualGrammar, forbiddenDrift
- Uses the smallest sufficient source set (hook-first clip, 0–5s opening, contact sheet, or style board)
- Separates visual structure from identity—no copying faces, wardrobe, creator, location, or exact overlays
- Supports no-reference briefs via proxy structure before prompt work
- PostPlus family: Routing & Contracts (familyId routing-contracts)—not final storyboard or provider payload
Reference Decode by the numbers
- 688 all-time installs (skills.sh)
- +43 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #348 of 1,335 Generative Media skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/postplusai/postplus-skills --skill reference-decodeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 688 |
|---|---|
| repo stars | ★ 19 |
| Security audit | 2 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | postplusai/postplus-skills ↗ |
How do you decode video references into prompt structure?
Turn benchmark clips, contact sheets, or rough creative notes into structured hook and visual-grammar objects before you write storyboards or video generation prompts.
Who is it for?
Developers building generative video pipelines who have benchmark clips or contact sheets and need explicit prompt contracts before storyboard writing.
Skip if: Teams that only need final rendered video output without reference decoding, or static blog content with no visual benchmark inputs.
When should I use this skill?
A developer has benchmark videos, contact sheets, frames, or rough creative notes that must become structured hook and visual-grammar prompt objects.
What you get
Structured hook essence, viewer question, visual-grammar rules, and forbidden-drift constraints ready for storyboard and generation prompts.
- Hook essence object
- Visual grammar and forbidden-drift contract
Files
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 provider payload 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:
hookEssenceviewerQuestionmustCopyVisualGrammarforbiddenDrift
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.
- If an owned CLI or script command fails, report the exact error and stop. Do
not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools.
Handoff
- Grid, beat sheet, or full render request ->
video-request-architect. - Explicit learn/do-not-copy boundary ->
reference-contract-builder. - Prompt already drafted ->
prompt-preflight-qa.
Public Command Boundary
- Choose the smallest matching command or workflow from the user input and run
it directly.
- If an owned CLI or script command fails, report the exact error and stop. Do
not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools.
- This public skill is instruction-driven. Produce the artifact described by the workflow directly from the available evidence.
- Do not call private provider/runtime paths or unpublished local tools.
- If the CLI returns a quote-confirmation challenge, run
postplus quote confirm --json --challenge-file <challenge.json>and retry with the returned token.
Related skills
Remotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.451k4.2k
Ai Video GenerationGenerate videos using 40+ AI models including Veo, Seedance, and others via inference.sh442k665Ai Image GenerationGenerate images using 50+ AI models including FLUX, Gemini, and Replicate via inference.sh441k665Ai Avatar VideoGenerate videos featuring AI avatars for product demos, tutorials, marketing, or explainers441k665Remotion RenderRender videos programmatically using React components and Remotion framework441k665
Remotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k665How it compares
Use reference-decode to structure visual references before prompting; use audience-voice skills when the input is social comments rather than benchmark media.
FAQ
What inputs does reference-decode accept?
reference-decode accepts benchmark videos, contact sheets, frame sets, or rough creative ideas that need promptable structure. The skill runs before storyboard or video generation prompt writing in PostPlus routing-contracts workflows.
What does reference-decode output?
reference-decode outputs structured objects for hook essence, viewer question, must-copy visual grammar, and forbidden drift. Those artifacts guide storyboard authors and video generation prompts so references stay explicit and testable.
Is Reference Decode safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.