alexansart/demo-studio

demo-setup

One-time setup that analyzes the current project and configures it to use the film-demo / narrate / sync-narration / produce-video skills — detects the dev server and framework, asks only when necessary, generates demo.config.json and .env entries, vendors…

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/alexansart/demo-studio --skill demo-setup

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

Demo setup

Turns a generic install of film-demo / narrate / sync-narration / produce-video into a working pipeline for this specific project. Run once per project (re-run when URL, auth, or narration settings change).

Read on demand (do not paste all into chat):

FileWhen
references/when-to-ask.mdBefore asking the user anything
references/script-format.mdScaffolding script.md
references/beat-plan.mdNarrated videos — sizing holds
references/narrated-compose.mdCompose flags after record
references/agent-integration.mdUser asks how Cursor / Claude Code invoke skills
examples/create-item/script.mdSimple form + list payoff
examples/search-flow/script.mdNav → query → scroll results
examples/assistant-panel/script.mdSide panel + tool wait bracket
templates/run.mjsStarting point for demos/<slug>/run.mjs

What this produces

<project root>/
├── demo.config.json
├── .env                          # gitignored — API key + demo login only
└── demos/
    ├── _engine/                   # vendored copy of film-demo/scripts/*.mjs
    ├── _lib/                      # paths.mjs, auth.mjs (from templates/)
    └── <first-demo-slug>/
        ├── script.md
        └── run.mjs

_engine/ = recording/zoom/guardrails library (same code as film-demo/scripts/). _lib/ = thin project helpers (render dirs, off-camera login) — patterns reused across every demo in this repo.

Steps

1. Detect the stack

Read package.json, framework config, existing .env.example. Infer baseUrl and devCommand. See references/when-to-ask.md — do not ask if inference is confident.

2. Ask only when necessary

Login selectors, ambiguous ports, narration voice — only when detection fails or the user explicitly wants narration without a key. Default narration to "none".

3. Write demo.config.json

Use demo.config.example.json at the demo-studio repo root as the schema. Omit auth when loginRequired: false. Never put secrets in this file.

4. Write / update .env

Only the vars referenced by demo.config.json. Confirm .env is gitignored.

5. Vendor the recording engine

Copy the installed film-demo skill's entire scripts/ folder → <project>/demos/_engine/. If not installed: npx skills add AlexAnsart/demo-studio --skill film-demo --copy

6. Copy project helpers

Copy from this skill's templates/ → <project>/demos/_lib/:

  • paths.mjs — nextRenderDir, logRun
  • auth.mjs — login + buildDemoSession from demo.config.json + env

Skip auth.mjs usage in scaffolded run.mjs when loginRequired: false.

7. Scaffold the first demo

Pick the closest examples/*/script.md pattern to what the user described (create-item, search-flow, assistant-panel). Copy/adapt it to demos/<slug>/script.md.

Copy templates/run.mjs → demos/<slug>/run.mjs. Replace TODO selectors, navigation paths, and beat plan comment. Match the Show section exactly.

If the user did not describe a flow yet, scaffold create-item as the default.

8. Verify

bash
node <demo-setup-skill-dir>/scripts/check-setup.mjs
node demos/_engine/test-engine.mjs

Both must pass. If ffmpeg/ffprobe missing, stop — nothing downstream works.

Deliverable

Report: inferred baseUrl, login on/off, narration provider, preset, scaffold path, and which example pattern was used. Point the user to references/agent-integration.md for how to invoke produce-video in Cursor or Claude Code. Remind them to fill .env before narrated or login-gated runs.

from this repository

More skills

All skills
alexansart
Community

film-demo

Records a polished, silent screen-capture demo video of any web app from a plain-English beat script — Playwright capture with a real cursor, human-speed typing, explicit zone-based zooms (focus/wide) with guaranteed containment, deterministic guardrails (cursor offscreen, zoom too long, inactivity), annotated frame inspection, post-record speed-ups, styled frame, and a verify/iterate loop. Use when the user asks to record, film, or generate a demo/tutorial/product video of a web app.

1h installs
1
GitHub stars
5
Updated
Jul 26
alexansart
Community

narrate

Generates a narration voiceover .mp3 for a demo video script using the ElevenLabs API — configurable voice/model/stability, deterministic output filename. Use when the user asks to add a voiceover, narration, or spoken audio to a demo/tutorial video, or names ElevenLabs explicitly.

1h installs
1
GitHub stars
5
Updated
Jul 26
alexansart
Community

produce-video

End-to-end production of a narrated, captioned demo video for any web app — chains narration generation (narrate), silent Playwright recording (film-demo, smart zooms + guardrails), and narration sync with burned captions (sync-narration) into one final .mp4. Use when the user asks to produce, make, or film a demo/product/tutorial video end to end, "with voice and subtitles", or "from A to Z".

1h installs
1
GitHub stars
5
Updated
Jul 26
alexansart
Community

sync-narration

Syncs a separately-recorded narration track onto a silent screen recording — pads audio with calculated pauses to match on-screen pacing (no voice during cursor movement), then burns styled captions. Use when the user provides a silent screen-recorded video plus a narration .mp3 and asks to sync/combine/caption them.

1h installs
1
GitHub stars
5
Updated
Jul 26