demo-recorder — Claude Code skill: what it does, how to install
demo-recorder drives headless Chromium to record scripted 3K 60fps web app demos, generate narration via Cloney, and dub the final cut.
Apache-2.0 ★ 173 updated 2026-10-24
npx skills add sammcj/agentic-coding --skill demo-recorder -a claude-codeWhat demo-recorder does
The skill runs headless Chromium through scripted test steps written in demos/<demo>.mjs. It outputs a silent 3K 60fps video file named demo.mp4 into ~/Downloads/demo-recorder/<demo>/. When provided with a scene-by-scene script in demos/<demo>.md, it synthesises narration audio using Cloney and mixes it with the footage.
Under the hood, workflow logic lives in a Makefile, Playwright drivers, and Bash helper scripts. The initial execution of record fetches Playwright directly into the skill directory, so working internet access is mandatory. Mouse movement relies on an injected cursor overlay that only reacts to synthetic events, which means scripts require deliberate h.moveTo and h.wait calls to pace the action.
Chromium depends on its internal sandbox while Cloney requires Apple Metal acceleration, causing both record and narrate tasks to fail inside an agent sandbox. You must execute those targets unsandboxed. If Cloney is missing from the system, speech generation steps are skipped, yet the silent capture still compiles successfully.
What it helps with
- record headless browser product demos in 3K 60fps from scripted files
- align visual scene timings with written voice-over scripts
- generate narration audio clips with Cloney and dub them onto video
- inspect still frames after recording to catch missed clicks or leaks
Example prompts for the agent
- Record a walkthrough using demos/login-flow.mjs and export stills
- Synthesise voice clips from demos/login-flow.md and dub the output video
- Build the silent demo cut without running Cloney narration
How to install demo-recorder
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill demo-recorder -a claude-code2Manually: put the files in place
~/.claude/skills/demo-recorder/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/demo-recorder/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill demo-recorder -a codex2Manually: put the files in place
.agents/skills/demo-recorder/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill demo-recorder -a cursor2Manually: put the files in place
.cursor/skills/demo-recorder/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sammcj/agentic-coding Skills/demo-recorder/SKILL.md2Manually: put the files in place
.github/skills/demo-recorder/SKILL.md1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill demo-recorder -a gemini-cli2Platform CLI
gemini skills install https://github.com/sammcj/agentic-coding --path Skills/demo-recorderManually: put the files in place
.devin/skills/demo-recorder/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 demo-recorder
How to install demo-recorder in Claude Code?
Run npx skills add sammcj/agentic-coding --skill demo-recorder -a claude-code. The skill config will be placed in ~/.claude/skills/demo-recorder/SKILL.md.
What does demo-recorder do?
It drives headless Chromium through a JavaScript scenario, records a 3K 60fps video, and optionally narrates and dubs the footage using Cloney text-to-speech.
Why must record and narrate targets run outside the agent sandbox?
Headless Chromium manages its own process sandboxing, and Cloney relies on Metal GPU acceleration. Both components fail inside the restricted sandbox environment of the agent.
Source text
SKILL.md · Apache-2.0
---
name: demo-recorder
description: Use when the user wants a scripted screen-recording demo video of a web app, a narration script or text-to-speech voice-over for one, or a dubbed cut.
metadata:
version: 2026-10-12
---
Drives headless Chromium through a scripted walkthrough, encodes a silent 3K 60fps `demo.mp4`, then optionally voices the narration with Cloney and dubs it on. Below, `$M` means `make -f <this-skill-dir>/Makefile`; run it from the directory holding `demos/`; output goes to `~/Downloads/demo-recorder/<demo>/` unless `OUT=` says otherwise. `$M help` lists the targets; each script in `scripts/` takes `--help`.
## Workflow
1. Create a task per step below, phrased with its completion criterion, then work them to completion.
2. Write `demos/<demo>.mjs` exporting `options`, `setup()`, `run(h, ctx)` and `teardown(ctx)`, modelled on `assets/examples/openspeccer.mjs`; the `h` helpers are in `scripts/lib/recorder.mjs`.
3. In `setup()`, record against a throwaway copy of the target so on-camera edits leave the user's repo untouched.
4. Call `h.scene("<name>")` at the start of each narrated section.
5. Write `demos/<demo>.md`: one `## N. Title` section per scene in recording order, an `_On screen: ..._` note, then the spoken text at about 2.2 words per second of scene (example: `assets/examples/openspeccer.md`).
6. Run `$M record encode DEMO=demos/<demo>.mjs`. Done when `~/Downloads/demo-recorder/<demo>/timings.tsv` lists every scene and you have viewed every image in `~/Downloads/demo-recorder/<demo>/stills/`.
7. Fix what the stills show (missed click, wrong tab, personal paths via `options.hide`), then repeat step 6.
8. Ask which Cloney character and engine to use (offer `$M voices`; defaults are in `scripts/narrate.sh --help`), unless the user records clips themselves as `N.wav` in `~/Downloads/demo-recorder/<demo>/audio/`. If a `cloney` skill is available, activate it first; otherwise `cloney --help` covers the CLI.
9. Run `$M narrate DEMO=demos/<demo>.mjs VOICE=<character> ENGINE=<engine>`. Done when no row says FAILED or "runs past scene". Re-run for a take that said the wrong words (a fresh seed usually fixes it); trim the text of a clip that runs past its scene.
10. Run `$M dub DEMO=demos/<demo>.mjs`. Done when its table has no `(no clip)` row; then report `~/Downloads/demo-recorder/<demo>/demo-dubbed.mp4`.
## Gotchas
- Chromium needs its own sandbox and Cloney needs Metal; both fail inside the agent sandbox, so run `record` and `narrate` unsandboxed.
- `record` installs Playwright into the skill directory on first run; that needs network access.
- Check clips with `ffprobe` and `ffmpeg -af volumedetect`; never play audio, leave listening to the user.
- Breeze takes 35-75 s per clip. `narrate.sh` caches renders and re-renders only sections whose text or voice changed, so edit and re-run freely. Delete `~/Downloads/demo-recorder/<demo>/audio/.narrate/N.*` to re-render one clip; `FORCE=1` re-renders all.
- Pass `VOICE`/`ENGINE` on every `narrate` for a non-default voice; omitting them re-renders every clip in the default voice.
- `narrate` transcribes every take and rejects one that says the wrong words; `TAKES=3` keeps the shortest that passes. `VERIFY=0` skips the check.
- Without Cloney, `narrate` and `dub` skip with a message; `$M demo` still produces the silent cut.
- `dub.sh` pairs clip `N.wav` with the Nth scene in `timings.tsv`; keep section numbers in scene order.
- The cursor is an injected overlay that only moves on mouse events; `h.moveTo` onto whatever the narration names, and `h.wait` before the next `h.scene` so the narration has room.
- Keep spaces out of the `DEMO` path; make splits it and mangles the output folder name.
- `~/Downloads/demo-recorder/<demo>/frames/` runs to about 800 MB per 90 s; offer to delete it once the cut is final.
© sammcj · Apache-2.0 · sammcj/agentic-coding