Kurzgesagt Style Explainer
Make a short flat-vector science explainer (about 60 s) in the measured visual style of Kurzgesagt – In a Nutshell, style only (no characters, logos or footage), with Remotion, an ElevenLabs voice-over synced by word timestamps, and a measurement loop that scores the finished render against the style. Use when asked for a Kurzgesagt-style or "flat vector space-y" animated explainer, or when you need to measure a video style in numbers and hit those numbers.
Install
npx skills add maxeffortyt/kurzgesagt-style-explainer --skill kurzgesagt-style-explainergit clone --depth 1 https://github.com/maxeffortyt/kurzgesagt-style-explainer.git /tmp/kurzgesagt-style-explainer
mkdir -p ~/.claude/skills
cp -r /tmp/kurzgesagt-style-explainer/. ~/.claude/skills/kurzgesagt-style-explainerPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Kurzgesagt-style explainer This skill turns one topic into a ~60-second animated explainer that matches a *measured* style, then checks the render against the same measurements. The numbers come from 8 one-minute clips of Kurzgesagt videos (analysed at 10 fps, 4,800 frames). Read `STYLE.md` before you design anything. **Hard rules** - Copy the style only. Never use the reference channel's characters, mascots (the birds), logo, footage or images. Every shape is your own SVG/React. - Keep the science accurate. Fact-check every number in the script before you generate the voice. - Do not download music or sound effects unless the user provides them. Synthesize sound effects yourself if the folder is empty. - Never print or commit API keys. Read them from the environment or a `.env` the user provides. ## Workflow ### 1. Style target - Default: use `STYLE.md` and `reference/ref_profile.json` as they are (numbers only, no frames). - To target another style: pick 5–10 one-minute clips you are allowed to analyse, then ```bash python3 tools/style_metrics.py clip.mp4 reports/clip.json --fps 10 # one report per clip python3 tools/similarity.py build reports/ my_profile.json # mean/std per metric + palette pool ``` and write your own `STYLE.md` with the same table. Analyse at 10 fps and say so; don't claim more than you measured. ### 2. Brief
Details
- Skill name
kurzgesagt-style-explainer- Repository
- maxeffortyt/kurzgesagt-style-explainer
- License
- MIT
- Repo updated
- 10 November 2026
FAQ
What does the Kurzgesagt Style Explainer skill do?
Make a short flat-vector science explainer (about 60 s) in the measured visual style of Kurzgesagt – In a Nutshell, style only (no characters, logos or footage), with Remotion, an ElevenLabs voice-over synced by word timestamps, and a measurement loop that scores the finished render against the style. Use when asked for a Kurzgesagt-style or "flat vector space-y" animated explainer, or when you need to measure a video style in numbers and hit those numbers.
How do I install the Kurzgesagt Style Explainer skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add maxeffortyt/kurzgesagt-style-explainer --skill kurzgesagt-style-explainer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Kurzgesagt Style Explainer popular?
It lives in maxeffortyt/kurzgesagt-style-explainer, which has 5 GitHub stars and 2 forks.
Related skills
Launch Video
6serenakeyitan/launch-video-skill
Generate a polished product launch / demo video with Remotion. Use when the user wants a marketing or launch video for a product (CLI tool, web app, mobile app, library, agent, etc.). Produces a rendered MP4 from a reusable scene library, with synced typing/click SFX.
Image to Code
5catch-the-wave/fullstack-ios-claude-skills
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.
Video Recording
9TwillAI/skills
Record high-quality browser verification videos using WebReel. Two-phase workflow: test with agent-browser to collect CSS selectors, then record with WebReel for polished output.
Clarity Mapping
9duvoai/skills
Map how a process works with Duvo Clarity. Use when the user asks to map, document or understand how their team does a piece of work, to interview people about a process, or to analyze what those interviews found. Sets up a Duvo workspace if the user has none, creates the process, invites people to short voice interviews within the plan's allowance, tracks who has done theirs, and analyzes the process map.
Webreel
9TwillAI/skills
WebReel CLI reference — config format, step types, human-like recording patterns, and troubleshooting. webreel is pre-installed globally in the sandbox.
Podcast Synthesis
6qingliu1617-art/xiaoyuzhou-synthesis-skill
Synthesize multiple podcast/interview transcripts from the same industry into a structured, multi-perspective analysis report. Accepts two input types: (A) 小宇宙 episode URLs (the skill will transcribe audio first, then synthesize), or (B) pre-existing transcript files (.txt, .docx, .md). Trigger when the user provides 2 or more 小宇宙 links, transcript files, or a mix — and asks for analysis, synthesis, a report, or even just "help me understand this industry". Also trigger when the user mentions 小宇宙, podcast transcripts, interview transcripts, or says things like "I have a few podcast conversatio
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.