Video To Claude

Sends a video/GIF to Gemini's video model, gets back a frame-accurate JSON build spec.

Works with setup

Test report

Verdict
Works with setup
Score
8.8/10
Tested
Jul 16, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · 2447178

Couldn't run it live (no GEMINI_API_KEY, google-genai not installed) but the repo ships real prior outputs (gallery-specs/*.json) from its own --micro pipeline — e.g. a credit-card reveal button spec with exact hex colors, a 600ms cubic-bezier(0.34,1.56,0.64,1) flip animation, and the non-obvious 'swap text at the 90-degree mark so the user never sees it change' detail — the kind of frame-level accuracy a baseline text-only pass simply cannot invent.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 4/5

What Video To Claude does

Uploads a YouTube URL, local video, GIF, or tweet video to Gemini's multimodal API with a prompt tuned to extract implementable specs (exact hex colors, pixel dimensions, animation timing in ms, cubic-bezier easing, state transitions), then hands the structured JSON to Claude to build. Triggers when a user shares a video/GIF and asks to clone a UI, reverse engineer a product demo, or extract tutorial build steps; a --micro flag adds a 'delight details' checklist for subtle micro-interaction effects (ring draws, shimmer, overshoot easing).

How to install Video To Claude

git clone https://github.com/rohunvora/video-to-claude ~/.claude/skills/video-to-claude
pip install google-genai
# then set GEMINI_API_KEY in environment (free tier available)

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Video To Claude

  • /video-to-claude Sends a video/GIF to Gemini's video model, gets back a frame-accurate JSON build spec.

It also activates on plain-language prompts like these:

  • Here's a GIF of a button animation, extract the exact hex colors and timing
  • Clone this micro-interaction from the tweet video I just linked
  • Reverse engineer this product demo video into implementable build specs

Frequently asked questions

Is the Video To Claude skill free?
Yes. The skill itself is free from rohunvora/video-to-claude. SkillProof publishes the install command and an independent test verdict at no cost.
Does Video To Claude work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Works with setup. Couldn't run it live (no GEMINI_API_KEY, google-genai not installed) but the repo ships real prior outputs (gallery-specs/*.json) from its own --micro pipeline — e.g. a credit-card reveal button spec with exact hex colors, a 600ms cubic-bezier(0.34,1.56,0.64,1) flip animation, and the non-obvious 'swap text at the 90-degree mark so the user never sees it change' detail — the kind of frame-level accuracy a baseline text-only pass simply cannot invent.
What is the Video To Claude SkillProof Score?
8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Video To Claude?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Video To Claude with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.