Agent skill
voiceover-video
YouTube video editor (/video-youtube-editor; this folder keeps its first name, voiceover-video): a complete edit of a horizontal YouTube video (16:9, often long), three ways, the same skill.
Filed under LinkedIn and social.
From ihsaneGTM/gtm-skills · 8 skill entries · 0 · pushed 2026-10-26
What it does when it runs
YouTube video editor (/video-youtube-editor; this folder keeps its first name, voiceover-video): a complete edit of a horizontal YouTube video (16:9, often long), three ways, the same skill. FACECAM: the user filmed the whole video talking to the camera; their real voice runs all along, cut tight (retakes, fillers and dead air cut out), illustrated in motion design with their dressed face shots in between. AI VOICE: no filming; the whole video in motion design, said by their voice clone, an ElevenLabs voice or Ihsane's once shared, from a script, an idea or an article. HYBRID: they film only the intro (and a few cutbacks), their cloned voice says the rest. The style « Document » settled over twelve reviews on 2026-10-12/13 (real homepages at the full viewport and real logos, LinkedIn-style cards of fictional people, editorial lines with a yellow marker, numbers that count, charts one per metric under their app icon, the yellow V chapter pages, the method list), real stock shots in a frame on the paper and GIFs as pinned prints; face shots dressed (graded, at their speed, cut out, lockups behind the head, punches); junctions on the same frame, no dead air; ONE music; -14 LUFS; a 1080p draft and a 720p preview, the 4K only when the user asks. Trigger on: edit my YouTube video, YouTube video editor, horizontal video, long video, facecam, no facecam, AI voice video, I only filmed the intro, use my voice for the rest, cloned voice video, voiceover video, monte ma vidéo YouTube, vidéo horizontale, sans facecam, j'ai filmé que l'intro, fais la suite avec ma voix clonée.
Automated analysis of the skill and the 68 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
- ELEVENLABS_API_KEY
- GEMINI_API_KEY
- GIPHY_API_KEY
- NANO_BANANA_API_KEY
- PEXELS_API_KEY
- Hosts it reaches
- api.elevenlabs.io
- api.giphy.com
- api.pexels.com
- assets.mixkit.co
- commons.wikimedia.org
- giphy.com
- gsap.com
- media.giphy.com
- mixkit.co
- www.pexels.com
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It does act, so it runs under whatever permissions your session already grants. - Actions present in the files
- shellwrites filesnetwork
Ask about voiceover-video
Opens your assistant with this page's recorded context. Check the linked sources before relying on it.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/ihsaneGTM/gtm-skills.git /tmp/gtm-skills git -C /tmp/gtm-skills sparse-checkout set "plugins/video/skills/voiceover-video" mkdir -p ~/.claude/skills/voiceover-video cp -R "/tmp/gtm-skills/plugins/video/skills/voiceover-video/." ~/.claude/skills/voiceover-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.
Before you install: this skill will not complete its job on a bare agent. It needs ELEVENLABS_API_KEY, GEMINI_API_KEY, GIPHY_API_KEY, NANO_BANANA_API_KEY, PEXELS_API_KEY, which you have to obtain separately.
The skill
Source on GitHub ↗The source carries no licence at all, so no permission to redistribute it exists. Everything else on this page is our own reading of the file and is published here; the text of the skill is not, and stays where its author put it.
Files bundled with it
These load only when the skill asks for them, so they cost nothing until it runs.
- kit.js
- CustomBounce.min.js
- CustomEase.min.js
- CustomWiggle.min.js
- DrawSVGPlugin.min.js
- EasePack.min.js
- MorphSVGPlugin.min.js
- MotionPathPlugin.min.js
- Physics2DPlugin.min.js
- ScrambleTextPlugin.min.js
- SplitText.min.js
- TextPlugin.min.js
- gsap.min.js
- package.json
- prereqs.json
- decisions.md
- engine.md
- example-cutback-story.js
- example-intro-story.js
- example-story-part1.js
- example-story-part2.js
- look.md
- media.md
- motion-scenes.md
- elevator-a.html
- floor-a.html
- type-a.html
- assemble.mjs
- capture.mjs
- chapters.mjs
- clone.mjs
- colours.mjs
- cut.mjs
- facecam.mjs
- grade.mjs
- hdr-lut.mjs
- hear.mjs
- intro.mjs
- media.mjs
- motionscene.mjs
- new.mjs
- people.mjs
- png.mjs
- prep.mjs
- render.mjs
- sound.mjs
- sweep.mjs
- take.mjs
- tracker.mjs
- verify.mjs
- styles.json
- techniques.json
- blocs.js
- clip.html
- docs.js
- engine.js
- framed.js
- fx.js
- pen.png
- intro-story.js
- motionpage.js
- part.html
- photos.js
- story.js
- sweep.html
- theme.css
- tracker.html
- voices.json
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 · 57,918
- Agentic video understanding by ericosiu · 3,766
- show-and-tell-video-slate by ericosiu · 3,766
- video-analysis by ericosiu · 3,766
- video-content-engine by ericosiu · 3,766
- video-ad-analysis by OpenClaudia · 724
- hyperframes-product-launch-video by Varnan-Tech · 688
- video-outreach by chadboyda · 85
Need help setting it up?
This page tells you what voiceover-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.