Agent skill
launch-video
Create a product launch video from a truthful beat script, available assets and a reproducible motion project.
Filed under Positioning and messaging.
From timscheuerai/gtm-architecture-template · 51 skill entries · 13 · pushed 2026-09-17
What it does when it runs
Create a product launch video from a truthful beat script, available assets and a reproducible motion project.
Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/timscheuerai/gtm-architecture-template.git /tmp/gtm-architecture-template git -C /tmp/gtm-architecture-template sparse-checkout set ".agents/skills/launch-video" mkdir -p ~/.claude/skills/launch-video cp -R "/tmp/gtm-architecture-template/.agents/skills/launch-video/." ~/.claude/skills/launch-video/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from timscheuerai/gtm-architecture-template/blob/2c312c9398064ad3730c786647293458cb89632c/.agents/skills/launch-video/SKILL.md, which is licensed MIT (repository). 197 words, 1 heading.
Build a launch video
Read the product brief, real feature behavior and brand context. Establish audience, runtime, aspect ratio, key message and output. This skill provides a production procedure; a motion renderer, audio provider and paid generation are separate prerequisites.
Create a beat sheet with spoken line, visual action, evidence/asset and target duration. Every screen must represent a real feature or be labeled concept/demo. Keep an editable script beside the render project.
Use the available renderer and inspect its current APIs before implementation. Align visuals to measured narration/word cues. Keep narration text and beat timing in one source so revisions do not leave scenes out of sync.
Choose the user's intended voice and licensed music. Paid generation needs the requested scope and budget; do not silently select a recurring service or imitate a real person's voice without the appropriate basis.
Render a short representative segment, inspect typography, timing and audio, then render the whole artifact. Keep output files separate from source assets. Use shorts-qa for applicable checks and verify the final codec/playback requirements.
Deliver video, editable project, script, asset credits and validation notes. No prebuilt Remotion scene library or automatic uploader is implied by this skill.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- hyperframes-product-launch-video by Varnan-Tech · 674
- launch by coreyhaines31 · 54,316
- video by coreyhaines31 · 54,316
- Agentic video understanding by ericosiu · 3,627
- show-and-tell-video-slate by ericosiu · 3,627
- video-analysis by ericosiu · 3,627
- video-content-engine by ericosiu · 3,627
- launch-strategy by OpenClaudia · 714
Need help setting it up?
This page tells you what launch-video does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.