Multi Variant Scripting

v1.0.0

Produce 2-4 genuinely distinct video script variants from a single brief — technical/cinematic (A), general/walkthrough (B), developer/explainer (C). Uses in...

0· 109·0 current·0 all-time
byNissan Dookeran@nissan

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for nissan/multi-variant-scripting.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Multi Variant Scripting" (nissan/multi-variant-scripting) from ClawHub.
Skill page: https://clawhub.ai/nissan/multi-variant-scripting
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install multi-variant-scripting

ClawHub CLI

Package manager switcher

npx clawhub@latest install multi-variant-scripting
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name and description (produce multiple distinct script variants) match the SKILL.md content: guidance, templates, and checklist for writing A/B/C variants. There are no unrelated requirements (no binaries, env vars, or installs) that would be inconsistent with a writing tool.
Instruction Scope
SKILL.md contains only writing methodology, templates, checks, and handoff format. It does not instruct the agent to read local files, access environment variables, call external endpoints, or collect unrelated system data. Mentions of external actors ('Finn', 'Nissan') are workflow labels in the doc and are not accompanied by network or upload instructions.
Install Mechanism
No install specification or code files are present. This is lowest-risk (instruction-only) — nothing is written to disk or fetched at install time.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. That aligns with a pure writing/templating skill. There are no secret names or unrelated credential requests.
Persistence & Privilege
The skill is not always:true and does not request persistent or elevated privileges. It does not modify other skills' configs or system settings in the instructions.
Assessment
This skill is an instruction-only template for writing multiple script variants and appears internally consistent and low-risk. Before installing/use: (1) verify that your production tooling (e.g., any system named 'Finn') does not automatically accept or publish handed-off scripts—this SKILL.md does not define any automatic uploads but your environment might; (2) avoid pasting secrets or private data into briefs you hand to the skill, since the skill's instructions assume local operation but your agent's environment may be configured to sync outputs externally; (3) if you expect integration with a build/production pipeline, confirm that separate connectors (not part of this skill) handle that and have appropriate access controls; (4) if you want stronger guarantees about no network egress, validate agent/runtime network policies—SKILL.md states outbound:false, but enforcement depends on the runtime. Overall, the skill appears coherent and safe to use as a writing-helper.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🎬 Clawdis
latestvk979z8eayp9116vfy10gt486v983rkp7
109downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

Skill: Multi-Variant Scripting

Owner: Sara
Version: 1.0
First used: 2026-03-24 (Reddi Agent Protocol — 3-variant pipeline)


What This Does

Produces 2–4 distinct script variants for the same product from a single brief. Each variant serves a different audience or communication style. Variants must be genuinely distinct — not the same script with synonyms swapped.

When to use this skill: Any time the demo-video playbook calls for 2+ variants. Read this before writing the first word of any script.


The Variant Differentiation Test

Before writing a single scene, define these three things for each variant:

  1. What does this audience already know? (Don't explain what they know — assume it)
  2. What's the ONE thing this variant needs them to feel or understand? (Not a list — one thing)
  3. What's the register? (cinematic / conversational / technical)

If two variants have the same answers to all three → they are not distinct → collapse them into one.

Running this test upfront prevents the most common failure: writing three scripts that tell the same story three different ways, rather than three genuinely different stories about the same product.


Variant Labelling Convention

Use these labels consistently across all projects so Finn knows the production approach without reading the script:

LabelAudienceStyleVO Density
ATechnical or sophisticatedCinematic — minimal VO, UI carries storySparse
BGeneral / accessibleWalkthrough — guided, second personMedium
CDeveloper / architectExplainer — structured, covers architectureDense

Word Count Targets

Check these before calling any script done:

Target LengthNarration Word Count
60s110–130 words
90s160–195 words
2min220–260 words
3min330–390 words

At natural TTS pace: ~130 words/min. Count words in the clean narration section only (no stage directions).


Interleaved Writing Technique

The wrong way: Write A fully → Write B fully → Write C fully

By the time you write C, it has unconsciously borrowed A's metaphors and B's sentence structure. C ends up sounding like a compressed remix of the first two.

The right way (interleaved): Write Scene 1 for A, B, C → Write Scene 2 for A, B, C → continue scene by scene

This forces explicit differentiation at each narrative beat. When you write Scene 2 for C, you've just written Scene 2 for A and B — so you're actively thinking "how is C different here?" rather than just continuing a flow.


Common Failure Modes

Drift

What it is: Writing C after A and B causes C to unconsciously borrow A's metaphors and B's structural patterns.
Fix: Use interleaved writing. Never fully complete one variant before starting the others.

Jargon Bleed

What it is: Technical terms written for C leak into B because they were written in the same session.
Fix: Before writing, define a jargon whitelist per variant. Terms on C's whitelist should not appear in B. Terms on B's whitelist should not appear in A unless they're genuinely plain-language.

Example:

  • A whitelist: (none — no jargon, let the UI speak)
  • B whitelist: "agent", "automates", "dashboard"
  • C whitelist: "MCP protocol", "orchestrator", "tool-call", "mesh routing"

Length Creep

What it is: All variants drift toward the same word count because the writer fills to a comfortable length.
Fix: Count words in the clean narration section after writing each scene. Stop when you hit the ceiling. Tighten, don't pad.


Output Checklist — Before Handoff to Finn

Run this check on all variants together, not one at a time:

  • Each variant has a clean narration section (narration only — no stage directions, no scene headers)
  • Word counts checked against length targets (count them, don't estimate by feel)
  • No variant shares an opening line with another (first sentence must be unique per variant)
  • Jargon that appears in C does not appear in B
  • Jargon that appears in B does not appear in A
  • Screenshot/recording requirements section is complete and specific
  • "Notes for Finn" section includes timing gotchas, transition notes, any unusual assembly requirements
  • Differentiation test re-run on final drafts — confirm answers to all three questions are still distinct

Handoff Format

Each script file must follow the standard format:

# Video Script [A/B/C] — [Title]
**Version:** 1.0
**Target length:** X seconds
**Audience:** [who]
**Style:** [description]

## Scene-by-scene
### Scene N — [Title] (M:SS–M:SS)
**Screen:** [page/state]
**Action:** [interaction if any]
**Narration:** "[exact spoken words]"
**Music/mood:** [description]

## Full narration (clean read)
[narration only — this is the direct TTS input]

## Screenshot/recording requirements
[specific assets needed, with reuse notes]

## Notes for Finn
[timing, transitions, assembly gotchas]

All three script files are handed to Finn together. Finn does not start production until Nissan has approved all scripts.

Comments

Loading comments...