paper-explainer-video — Claude Code skill for research videos
The paper-explainer-video Claude Code skill turns a paper section or result into an animated explainer with plotted data. It activates on requests for a research-based animation or teaching video.
MIT ★ 88 updated 2026-11-14
npx skills add mkaremm80/My-Skills-on-Claude --skill paper-explainer-video -a claude-codeWhat paper-explainer-video does
The skill builds a 16:9 video with an animated scene, live plot panels, and captions that change as a parameter moves across its range. It reads the selected paper section, chooses one parameter to sweep, then recreates the model from the paper’s equations and values and checks key results before rendering.
It produces an MP4, a configurable Python script, and Markdown narration notes. The workflow renders preview frames for inspection before the full video, then extracts frames for a final check. Calculations use NumPy and SciPy; plotting uses Matplotlib’s FFMpegWriter, while ffmpeg extracts frames. Video encoding uses libx264.
What it helps with
- explain a paper result through animation
- show how a model changes across a parameter sweep
- compare computed curves with numerical results
- prepare captions and narration notes for a video
Example prompts for the agent
- Turn the main result in this paper into an animated explainer video.
- Sweep SNR in the model and make a narrated video showing the changes.
- Animate this theorem for a teaching video and verify the key values.
How to install paper-explainer-video
1Skills CLI (Vercel)
npx skills add mkaremm80/My-Skills-on-Claude --skill paper-explainer-video -a claude-code2Manually: put the files in place
~/.claude/skills/paper-explainer-video/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/paper-explainer-video/
1Skills CLI (Vercel)
npx skills add mkaremm80/My-Skills-on-Claude --skill paper-explainer-video -a codex2Manually: put the files in place
.agents/skills/paper-explainer-video/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add mkaremm80/My-Skills-on-Claude --skill paper-explainer-video -a cursor2Manually: put the files in place
.cursor/skills/paper-explainer-video/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mkaremm80/My-Skills-on-Claude skills/paper-explainer-video2Manually: put the files in place
.github/skills/paper-explainer-video/SKILL.md1Skills CLI (Vercel)
npx skills add mkaremm80/My-Skills-on-Claude --skill paper-explainer-video -a gemini-cli2Platform CLI
gemini skills install https://github.com/mkaremm80/My-Skills-on-Claude --path skills/paper-explainer-videoManually: put the files in place
.devin/skills/paper-explainer-video/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about paper-explainer-video
How do I install paper-explainer-video in Claude Code?
Run npx skills add mkaremm80/My-Skills-on-Claude --skill paper-explainer-video -a claude-code.
What does paper-explainer-video do?
It makes an animated explainer from a research paper section or result, with a parameter sweep, plots, and captions. The output also includes a Python script and narration notes.
What does paper-explainer-video need to run?
It uses NumPy and SciPy for calculations, Matplotlib with FFMpegWriter for rendering, and ffmpeg to extract frames. Video encoding uses libx264.
Source text
SKILL.md · MIT
---
name: "paper-explainer-video"
description: "Make a 16:9 animated dashboard explainer video (mp4 + Python script + narration) for a section or result of a research paper, with a parameter sweep and live plots."
---
# Paper explainer video (dashboard style)
Use this when the user asks for an explainer video, animation or "video like the FAS one" for a paper, a section (system model, a theorem, a result figure) or a concept for teaching.
## What the output looks like
One 16:9 frame (1920x1080, 30 fps, white background, colorful):
- Top: a small grey credit line, a bold title, and a one-line purple summary of the setup.
- Left (about 40% width): an animated physical scene (waves, antennas, nodes, users, circuits). It moves every frame, with markers that show the decisions or outcomes.
- Right: a 2x2 grid of live panels. Static curves are drawn once; a dotted vertical line and dots move along them. One panel may be fully redrawn each frame (for example a bar chart of one realization).
- Bottom: a yellow rounded caption box. It changes 4-6 times as the swept parameter crosses thresholds, then shows a summary with the key numbers during a final hold.
- An optional inset in the scene (for example a complex-plane arrow) for the key quantity.
## Procedure
1. Read the paper section. Pick ONE swept parameter that tells the story (horizon, SNR, speed, tilt, number of blocks, and so on). Write the one-sentence message the video must show.
2. Re-implement the model in numpy/scipy, using the paper's own equations and parameter values. Verify the key numbers (closed forms vs. numerical integration, table values, limits) before drawing anything. Tell the user if something does not match.
3. Precompute the expensive parts: Monte Carlo curves on a fine grid (around 21 points, about 20k draws), and cache them.
4. For realization panels, use ONE fixed random draw that varies smoothly with the parameter (for example a finite plane-wave sum with fixed paths, and noise drawn once). Scan seeds and choose one that tells the story clearly; say this in the narration notes.
5. Timeline: intro hold (about 2 s), an eased sweep (0.5 - 0.5 cos(pi x)), and a final hold (about 3 s). Default 17 s; for voice-over make it about 60 s (for example 8 / 42 / 10 s).
6. Write the script with argparse: `--out`, `--preview` (writes 3 PNG frames), `--dpi`. Put the parameters at the top (CREDIT, model values, SEED, timings). Render with matplotlib FFMpegWriter (libx264, yuv420p, bitrate 6000), using a grab_frame loop.
7. ALWAYS render the previews first and look at them. Fix overlaps, then render the full video. Afterwards, extract 4 frames with ffmpeg and check them.
8. Deliver the .mp4, the .py and a narration .md (time | caption | what to say in simple English | panel guide | settings | easy edits). Number versions v1, v2, ....
## Layout lessons (avoid these bugs)
- For the scene axes use `set_aspect('equal', adjustable='datalim')` and centre the xlim on the content, or the scene shrinks and gets clipped.
- Put long scene labels where nothing moves; check that inset axes do not cover labels.
- Legends: put them in empty regions (often `lower right` for outage-type curves). Use `ncol=2` for bar panels and leave headroom in ylim for markers.
- Keep the gridspec top at about 0.86, so the subtitle does not hit the panel titles, and the bottom at about 0.155, so a two-line caption does not hit the x-labels.
- Formula text goes inside the axes in an empty area, not over a curve.
- Full redraws (cla) are only for the scene and one realization panel; the others use set_data. About 4 minutes for 510 frames at 1080p is normal.
## Style constants
Blue #1c7ed6, orange #e8590c, green #2f9e44, red #e03131, teal #0c8599, purple #7048e8, gray #868e96, ink #212529, gold #f59f00. Bold titles at 11.5 pt, base font 10 pt, top/right spines off.
## Language
Captions and narration use simple English (B2 or below), with short sentences and numbered caption steps ("1 ·", "2 ·", ...).
© mkaremm80 · MIT · mkaremm80/My-Skills-on-Claude