← Back to Skills Marketplace
cohnen

Shellbot Product Video

by cohnen · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
327
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install shellbot-product-video
Description
Create conversion-focused product marketing videos with Remotion + React using the AIDA framework (Attention, Interest, Desire, Action). Use when building la...
README (SKILL.md)

Shellbot Product Video

Overview

Build one thing well: product marketing videos that convert. Keep Remotion as the source of truth for pacing, layout, animation, and render output. Use external generation tools only to enrich scenes. Built by the ShellBot Team.

Non-Negotiable Story Structure (AIDA)

Follow this structure in order:

  1. Establish the problem being solved.
  2. Introduce the solution.
  3. Show use cases, not feature lists.
  4. End with a CTA that includes an incentive.

Reject drafts that skip any step.

Workflow

1) Bootstrap the Remotion Base Project

List bundled templates:

./scripts/bootstrap_template.sh --list

Bootstrap the chosen template:

./scripts/bootstrap_template.sh --template cinematic-product-16x9 ./my-product-video
cd ./my-product-video
npm install

To also copy official Remotion rule asset snippets into the project:

./scripts/bootstrap_template.sh --template cinematic-product-16x9 --include-rule-assets ./my-product-video

Template bundle:

  • assets/remotion-product-template (aida-classic-16x9)
  • assets/templates/cinematic-product-16x9
  • assets/templates/saas-metrics-16x9
  • assets/templates/mobile-ugc-9x16
  • references/remotion-rules/assets (official-style reusable snippet assets)

Then adapt scene content/components and composition metadata in src/Root.tsx for the brief.

2) Capture Brief Inputs

Collect these fields before writing scenes:

  • Product name
  • Audience
  • Core pain/problem
  • Value proposition (one sentence)
  • 2 to 4 use cases
  • CTA
  • Incentive for CTA (discount, trial extension, bonus, etc.)
  • Visual style direction

If use cases are missing and only features are present, ask for use-case phrasing.

3) Build AIDA Narrative and Timing

Use this duration allocation as a starting point:

  • Attention: 0% to 20%
  • Interest: 20% to 45%
  • Desire: 45% to 80%
  • Action: 80% to 100%

Generate a structured plan with:

python3 scripts/brief_to_aida_plan.py --in brief.json --out plan.json --duration-sec 45 --fps 30

4) Map Story to Remotion Scenes

Implement scenes as React components and sequence them using Sequence. Keep transitions purposeful and short (usually 8-18 frames).

Load references/remotion-product-video-playbook.md when writing or reviewing Remotion code. Load references/remotion-rules-index.md and then only the specific files needed from references/remotion-rules/.

5) Add Ancillary Assets (Optional but Useful)

Use Freepik-generated assets only to support scenes:

  • Nano Banana 2 or Freepik image models for hero stills/background art.
  • Kling for short inserts or transition clips.
  • ElevenLabs voiceover and music endpoints for narration and soundtrack.

Do not let generated clips replace the whole narrative structure.

Load references/freepik-ancillary-assets.md when planning asset generation.

6) Assemble, QA, and Render

Run this QA gate before rendering:

  • Problem is clear in first 3-5 seconds.
  • Solution is introduced before midpoint.
  • Use cases are concrete scenarios, not feature bullets.
  • CTA includes an explicit incentive.
  • Audio levels keep voiceover intelligible over music.

Then render via Remotion CLI or renderer API.

Creative Rules

  • Prefer visual metaphors and outcomes over UI tours.
  • Keep one message per scene.
  • Use motion to direct attention, not decorate.
  • Show benefits in context: who uses the product, when, and what changes.
  • Keep CTA simple and singular.

Deliverables

Produce these outputs for each request:

  1. AIDA script draft.
  2. Scene plan JSON (plan.json).
  3. Remotion project from the selected bundled template customized for the brief.
  4. Asset manifest listing generated inputs and their intended scene usage.
  5. Final render command(s).

References

Use this skill for product marketing videos only. For other video categories, use a different skill.

Usage Guidance
This skill is coherent for producing Remotion AIDA videos. Before using: 1) Review the included shell/python scripts (bootstrap_template.sh, package_skill.sh, publish_clawhub.sh, brief_to_aida_plan.py) to confirm they do only what you expect. 2) When you run npm install in the generated project, it will fetch common packages (react, remotion) — run in a sandbox or build environment if you prefer. 3) If you want to use Freepik/ElevenLabs/Kling asset generation, you'll need to supply those API keys separately and confirm the endpoints/credentials are handled securely; the skill does not declare or store them. 4) If you plan to publish with the provided publish script, check it for network calls and verify it requires the ClawHub CLI and login credentials you control.
Capability Analysis
Type: OpenClaw Skill Name: shellbot-product-video Version: 1.0.0 The skill bundle is a legitimate toolset for generating product marketing videos using the Remotion framework. All scripts (bootstrap_template.sh, package_skill.sh, and brief_to_aida_plan.py) perform standard file operations and data processing consistent with the stated purpose, and the SKILL.md instructions focus strictly on the AIDA marketing framework without any evidence of prompt injection or malicious intent.
Capability Assessment
Purpose & Capability
The name/description align with the provided files: Remotion/React templates, example plans, and playbooks for building AIDA product videos. No unrelated credentials, binaries, or install steps are requested.
Instruction Scope
SKILL.md instructs running bundled scripts (bootstrap_template.sh, brief_to_aida_plan.py, npm install, remotion render) and using external asset generators (Freepik/Kling/ElevenLabs) for ancillary assets. This is within the stated scope, but running included shell/python scripts has side effects — inspect them before executing.
Install Mechanism
There is no automated install spec; the skill is instruction-first and bundles project templates and scripts. The workflow expects running npm install in the bootstrapped project (normal for JS templates). No remote archive downloads or obscure URLs are used by the skill itself.
Credentials
requires.env lists nothing and primary credential is none. The SKILL.md references external services (Freepik, ElevenLabs) but does not request or attempt to capture credentials — using those services would require you to supply API keys separately.
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges or modify other skills. Autonomous invocation is allowed (platform default) but not a special privilege here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install shellbot-product-video
  3. After installation, invoke the skill by name or use /shellbot-product-video
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Slug shellbot-product-video
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Shellbot Product Video?

Create conversion-focused product marketing videos with Remotion + React using the AIDA framework (Attention, Interest, Desire, Action). Use when building la... It is an AI Agent Skill for Claude Code / OpenClaw, with 327 downloads so far.

How do I install Shellbot Product Video?

Run "/install shellbot-product-video" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Shellbot Product Video free?

Yes, Shellbot Product Video is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Shellbot Product Video support?

Shellbot Product Video is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Shellbot Product Video?

It is built and maintained by cohnen (@cohnen); the current version is v1.0.0.

💬 Comments