agentleFS
AlexAnsartAlexAnsart/demo-studio/skills/demo-setup/SKILL.md

demo-setup

Skill3 starsChanged 4 months agoMITView on GitHub

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 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.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. microsoft/hve-core★ 1.6ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read package.json, framework config, existing .env.example.

    line 48
  2. Very specific:

    Use demo.config.example.json at the demo-studio repo root as the schema.

    line 59
  3. Very specific:

    Only the vars referenced by demo.config.json.

    line 64
  4. Very specific:

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

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.