AlexAnsart/demo-studio / skills/demo-setup
demo-setup
VerifiedOne-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 the recording engine and project helpers, and scaffolds a first demo from reference patterns. Use when the user asks to set up, configure, or install demo-studio / video-recording skills for this project, or before running produce-video for the first time in a new codebase.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.2 KB |
| examples/assistant-panel/script.md | markdown | 1.3 KB |
| examples/create-item/script.md | markdown | 729 B |
| examples/search-flow/script.md | markdown | 1.2 KB |
| references/agent-integration.md | markdown | 2.2 KB |
| references/beat-plan.md | markdown | 1.4 KB |
| references/narrated-compose.md | markdown | 1.2 KB |
| references/script-format.md | markdown | 1.4 KB |
| references/when-to-ask.md | markdown | 2.0 KB |
| scripts/check-setup.mjs | script | 1.5 KB |
| templates/auth.mjs | script | 2.0 KB |
| templates/paths.mjs | script | 882 B |
| templates/run.mjs | script | 4.6 KB |
references/agent-integration.md
View on GitHub# Cursor, Claude Code, and other agents
## What a "skill" is here
Each skill is a folder with:
- `SKILL.md` — instructions the agent reads when triggered
- `scripts/` — deterministic tools the agent **runs** (Node, Python, ffmpeg)
There is no background daemon. The agent is the orchestrator.
## How users invoke it
| Environment | Typical invocation |
|-------------|-------------------|
| **Cursor** | `@produce-video` in chat, or describe the task ("produce a demo video of…") — Cursor loads matching skills from `.cursor/skills/` |
| **Claude Code** | Same pattern under `.claude/skills/` — mention the skill or ask for an end-to-end demo video |
| **Any agent with skills support** | `npx skills add AlexAnsart/demo-studio --all --agent <name>` |
Install once per machine/project:
```bash
npx skills add AlexAnsart/demo-studio --all --agent cursor --copy
```
Then run `demo-setup` in the **target app repo** (not inside the demo-studio repo
unless you're dogfooding the hello example).
## What the user should NOT run manually
For a normal production run, the user asks in natural language. The agent:
1. Writes `demos/<slug>/script.md` and `run.mjs`
2. Runs `node demos/<slug>/run.mjs` (record)
3. Runs `node demos/_engine/compose.mjs …` (zoom + frame + speed-up)
4. Runs guardrails / inspect / verify
5. (Narrated) runs narrate → align → sync-narration
6. Delivers the `.mp4` path
Commands like `compose.mjs` are **pipeline internals** — documented so agents
(and debuggers) know the exact flags, not because end users run them daily.
## Repo-only commands (`hello-demo`)
The root README's `npm run example:hello` and manual `compose.mjs` on
`examples/hello-demo/renders/001` are for **validating the demo-studio checkout**
(GIF generation, CI). They are not the user workflow after `npx skills add`.
## First-time project flow
```
User: "Set up demo-studio for this project"
→ demo-setup skill (config + vendor engine + scaffold)
User: "Produce a narrated demo of creating a task"
→ produce-video skill (chains narrate + film-demo + sync-narration)
```
Silent clip only:
```
User: "Record a silent demo of the signup flow"
→ film-demo skill
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |