Explainer video (start here)
This skill routes a video request to one of ten tool skills and holds the rules they all share. Each tool skill
runs the same eight-phase state machine (brief, script, voice, visuals, render, mix, QA, deliver) with gates that
refuse to deliver anything unchecked. $SKILL is this skill's folder.
Non-negotiables (and why)
- Deliver an MP4 with the voice baked in. Not an interactive page, not slides, not a silent render. A person
once asked three times for a video and kept getting click-through pages.
- Natural voice, always tried first. Kokoro-82M runs offline on any CPU (
python3 -m pip install kokoro-onnx soundfile, model files from github.com/thewh1teagle/kokoro-onnx releases, model-files-v1.0). Then edge-tts,
then Piper. Never call a voice, or anything else, impossible before trying the alternatives and naming them.
A person was once told TTS was impossible when it was not and read it as being treated as less deserving
because of where they are from. When a limit really comes from the environment, say so plainly, in one sentence.
- Voice first, picture follows. Synthesize every line, lay out the timeline from the real clip lengths, and
key every animation to those times.
- Hit the bar on the first attempt. The bar is the Claude-made animations people share publicly: one
persistent subject, every line changes something on screen, eased motion and camera moves, depth and light,
music ducked under the voice, sound effects on events.
references/quality-bar.md has the details.
- Look before you deliver. Render stills, open them, fix what is wrong, and write down what you saw.
- Coding problems use the five-part format (
references/dsa-five-part-format.md): decode the problem and
every example, brute force, intuition through timed questions, every approach with time and space, final
C++ with a dry run. Compile and run the code first.
Pick the tool
If the person named a tool, use it. Otherwise pick by the look they want and say which default you chose:
| Want |
Skill |
| Classic math / 3b1b look, "anim video" |
manim-video |
| Hand-drawn, paper-cut or chalkboard short; fastest render |
handdrawn-js-video |
| Polished motion graphics in React |
remotion-video |
| Vector motion and code animation in TypeScript generators |
motion-canvas-video or revideo-video (headless render API, faster here) |
| HTML compositions with a CLI renderer |
hyperframes-video |
| One HTML page of DOM/SVG motion design |
gsap-video |
| Short clip like Claude Motion: a Short or Reel (9:16), a data clip from a CSV, block-built shots you can edit |
motion-video |
| 3D diorama film |
threejs-video (slow on CPU; fine on a GPU laptop) |
| Keyframed 2.5D motion design you can tweak in a studio |
theatrejs-video |
No preference and a coding problem: handdrawn-js-video (character, speed) or manim-video (classic look).
Looks. A named palette ("Catppuccin Mocha", "Tokyo Night", "a light Nord one", "pastel") is one of 30 registry
themes that every kit can wear: keep the tool choice above, write the theme id into the brief's Style section and
record it with vstate.py set theme=<id> (references/themes.md lists the ids and how a kit applies one). A
drawing style (whiteboard, chalkboard, blueprint, paper-craft or risograph, watercolor) means handdrawn-js-video,
whose styles combine with any theme. No look named: keep the kit's own palette (original).
Find the pipeline
The tool skills carry the scripts (state machine, voice, music, mix, QA, capture). Use the first that exists:
- An installed skill:
~/.claude/skills/<tool>-video/ (or the project's .claude/skills/).
- This repository's copy:
$SKILL/../<tool>-video/ when this skill was installed with its siblings.
- A copy in the current project or a shared folder (search for
<tool>-video/SKILL.md).
- The repository:
npx skills add praxstack/claude-video-skills-for-people-who-feel-neglected-by-claude --skill <tool>-video,
or git clone https://github.com/praxstack/claude-video-skills-for-people-who-feel-neglected-by-claude then
./install.sh <tool>-video.
Then read that skill's SKILL.md and follow it from vstate.py status.
If none of the pipeline is reachable
Do not downgrade the deliverable. Build the same thing by hand, in this order:
- Write the script as lines with a shown caption and a spoken text (symbols spelled out in the spoken text).
- Voice each line with Kokoro (
Kokoro(onnx, voices).create(text, voice="af_heart", speed=1.0, lang="en-us")),
trim silence, and compute each line's start as the running sum of lead (0.25 s) + clip + pad (0.35 s) +
think pause.
- Animate against those start times in any tool, render frames to H.264 at the exact total length.
- Mix: voice on top, a quiet music bed ducked under it,
loudnorm=I=-16:TP=-1.5:LRA=11, AAC, -pix_fmt yuv420p.
- Check: ffprobe the result, extract a frame per chapter and look at each, listen-check by comparing a few line
start times against the plan (
ffmpeg -ss <t> -t 3 on the audio).
Reference files
references/quality-bar.md, dsa-five-part-format.md, script-format.md, voice-and-audio.md,
state-machine.md, themes.md, environment.md, lessons-learned.md.
1---2name: explainer-video3description: Make a finished, narrated explainer video (an MP4 with a natural voice, music and animation timed to the voice), for example a LeetCode or DSA problem walkthrough, a concept explainer or an anim video. Use this whenever someone asks for a video, an animated explainer, a 3Blue1Brown-style animation, or a film made with Manim, Motion Canvas, Remotion, Revideo, HyperFrames, GSAP, Three.js, Theatre.js or hand-drawn canvas, or a short Claude Motion-style clip (a Short, Reel or data clip), even if they only say "make a video of this problem". It picks the right tool skill, enforces the rules that stop the usual failures (an interactive page instead of a video, a robotic or missing voice, slide-like visuals), and runs the resumable eight-phase pipeline.4metadata:5 source: https://skillmd.com/skills/praxstack/explainer-video6---78# Explainer video (start here)910This skill routes a video request to one of ten tool skills and holds the rules they all share. Each tool skill11runs the same eight-phase state machine (brief, script, voice, visuals, render, mix, QA, deliver) with gates that12refuse to deliver anything unchecked. `$SKILL` is this skill's folder.1314## Non-negotiables (and why)15161. **Deliver an MP4 with the voice baked in.** Not an interactive page, not slides, not a silent render. A person17 once asked three times for a video and kept getting click-through pages.182. **Natural voice, always tried first.** Kokoro-82M runs offline on any CPU (`python3 -m pip install kokoro-onnx19 soundfile`, model files from github.com/thewh1teagle/kokoro-onnx releases, `model-files-v1.0`). Then edge-tts,20 then Piper. Never call a voice, or anything else, impossible before trying the alternatives and naming them.21 A person was once told TTS was impossible when it was not and read it as being treated as less deserving22 because of where they are from. When a limit really comes from the environment, say so plainly, in one sentence.233. **Voice first, picture follows.** Synthesize every line, lay out the timeline from the real clip lengths, and24 key every animation to those times.254. **Hit the bar on the first attempt.** The bar is the Claude-made animations people share publicly: one26 persistent subject, every line changes something on screen, eased motion and camera moves, depth and light,27 music ducked under the voice, sound effects on events. `references/quality-bar.md` has the details.285. **Look before you deliver.** Render stills, open them, fix what is wrong, and write down what you saw.296. **Coding problems use the five-part format** (`references/dsa-five-part-format.md`): decode the problem and30 every example, brute force, intuition through timed questions, every approach with time and space, final31 C++ with a dry run. Compile and run the code first.3233## Pick the tool3435If the person named a tool, use it. Otherwise pick by the look they want and say which default you chose:3637| Want | Skill |38|---|---|39| Classic math / 3b1b look, "anim video" | `manim-video` |40| Hand-drawn, paper-cut or chalkboard short; fastest render | `handdrawn-js-video` |41| Polished motion graphics in React | `remotion-video` |42| Vector motion and code animation in TypeScript generators | `motion-canvas-video` or `revideo-video` (headless render API, faster here) |43| HTML compositions with a CLI renderer | `hyperframes-video` |44| One HTML page of DOM/SVG motion design | `gsap-video` |45| Short clip like Claude Motion: a Short or Reel (9:16), a data clip from a CSV, block-built shots you can edit | `motion-video` |46| 3D diorama film | `threejs-video` (slow on CPU; fine on a GPU laptop) |47| Keyframed 2.5D motion design you can tweak in a studio | `theatrejs-video` |4849No preference and a coding problem: `handdrawn-js-video` (character, speed) or `manim-video` (classic look).5051**Looks.** A named palette ("Catppuccin Mocha", "Tokyo Night", "a light Nord one", "pastel") is one of 30 registry52themes that every kit can wear: keep the tool choice above, write the theme id into the brief's Style section and53record it with `vstate.py set theme=<id>` (`references/themes.md` lists the ids and how a kit applies one). A54drawing style (whiteboard, chalkboard, blueprint, paper-craft or risograph, watercolor) means `handdrawn-js-video`,55whose styles combine with any theme. No look named: keep the kit's own palette (`original`).5657## Find the pipeline5859The tool skills carry the scripts (state machine, voice, music, mix, QA, capture). Use the first that exists:60611. An installed skill: `~/.claude/skills/<tool>-video/` (or the project's `.claude/skills/`).622. This repository's copy: `$SKILL/../<tool>-video/` when this skill was installed with its siblings.633. A copy in the current project or a shared folder (search for `<tool>-video/SKILL.md`).644. The repository: `npx skills add praxstack/claude-video-skills-for-people-who-feel-neglected-by-claude --skill <tool>-video`,65 or `git clone https://github.com/praxstack/claude-video-skills-for-people-who-feel-neglected-by-claude` then66 `./install.sh <tool>-video`.6768Then read that skill's SKILL.md and follow it from `vstate.py status`.6970## If none of the pipeline is reachable7172Do not downgrade the deliverable. Build the same thing by hand, in this order:73741. Write the script as lines with a shown caption and a spoken text (symbols spelled out in the spoken text).752. Voice each line with Kokoro (`Kokoro(onnx, voices).create(text, voice="af_heart", speed=1.0, lang="en-us")`),76 trim silence, and compute each line's start as the running sum of lead (0.25 s) + clip + pad (0.35 s) +77 think pause.783. Animate against those start times in any tool, render frames to H.264 at the exact total length.794. Mix: voice on top, a quiet music bed ducked under it, `loudnorm=I=-16:TP=-1.5:LRA=11`, AAC, `-pix_fmt yuv420p`.805. Check: ffprobe the result, extract a frame per chapter and look at each, listen-check by comparing a few line81 start times against the plan (`ffmpeg -ss <t> -t 3` on the audio).8283## Reference files8485`references/quality-bar.md`, `dsa-five-part-format.md`, `script-format.md`, `voice-and-audio.md`,86`state-machine.md`, `themes.md`, `environment.md`, `lessons-learned.md`.