video-skills
CLAUDE.md6 starsChanged 4 days agoMITView on GitHub
This repository is Video Skills: a reel-editing skill plus three talking-head templates and a local Python/FFmpeg renderer. The skill is at .claude/skills/reel-edit/SKILL.md (identical to .agents/skills/reel-edit/SKILL.md, which Codex reads). Read README.md for setup and docs/project-format.md for the executable project format. When the user pastes prompts/first-edit.md or asks to edit a clip, follow the skill. When they share a reference reel and ask for their version of it, follow .claude/skills/reference-script/SKILL.md and write only from their voice/ facts file. Use the repository virtual…
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- pale-yellow-reelSkill
- pink-broll-reelSkill
- reel-editSkill
- reference-scriptSkill
- pale-yellow-reelSkill
- pink-broll-reelSkill
- reel-editSkill
- reference-scriptSkill
The file
Files
Claude Code entry point
This repository is Video Skills: a reel-editing skill plus three talking-head templates and a local Python/FFmpeg renderer. The skill is at .claude/skills/reel-edit/SKILL.md (identical to .agents/skills/reel-edit/SKILL.md, which Codex reads). Read README.md for setup and docs/project-format.md for the executable project format.
When the user pastes prompts/first-edit.md or asks to edit a clip, follow the skill. When they share a reference reel and ask for their version of it, follow .claude/skills/reference-script/SKILL.md and write only from their voice/ facts file. Use the repository virtual environment (.venv/bin/python or .venv\Scripts\python.exe); run python3 bootstrap.py --check first if it does not exist. When the user has review notes (a .review.json beside a draft), follow the "Work through my review notes" prompt in prompts/revisions.md. Keep raw footage unchanged, keep working files in .local/, and never publish footage or renders anywhere without being told to.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

