Agent skill
video-use
Edit a supplied video through a source-preserving transcript, timeline and visual review workflow using available rendering tools.
From timscheuerai/gtm-architecture-template · 51 skill entries · 13 · pushed 2026-09-17
What it does when it runs
Edit a supplied video through a source-preserving transcript, timeline and visual review workflow using available rendering tools.
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/video-use" mkdir -p ~/.claude/skills/video-use cp -R "/tmp/gtm-architecture-template/.agents/skills/video-use/." ~/.claude/skills/video-use/
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/video-use/SKILL.md, which is licensed MIT (repository). 177 words, 1 heading.
Edit the supplied video
Inspect the footage and read the user's intent before choosing a treatment. Preserve originals and existing project edits. The brief determines whether this is an interview, montage, tutorial or talking head; do not force all material through one preset.
Record a project note with source files, intended message, chosen output, edits and unresolved decisions. Use a timestamped transcript where speech drives the cut, and inspect visuals at decisions. Transcription/generation services are optional external dependencies with their own costs.
Build an EDL with source ranges and derive the output timeline. Keep exact word context around cuts and maintain mappings for captions, overlays and later revisions. Use shorts-cut, shorts-audio and shorts-motion where relevant.
Use installed tooling with verified command/API grammar; no universal render.py or transcription service is bundled. Generate only the requested assets. Keep intermediate and final renders separate from sources.
Render, inspect and iterate against the brief. Use shorts-qa for applicable final checks. Deliver the export and editable project/EDL with known limitations. Publication and uploads remain separate actions within the user's actual request.
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.
- 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
- video-ad-analysis by OpenClaudia · 714
- hyperframes-product-launch-video by Varnan-Tech · 674
- suede-video by JasonColapietro · 127
Need help setting it up?
This page tells you what video-use 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.