record-demo
Produces professional 30-60s narrated browser demo videos from a storyboard.
Install
mkdir -p .claude/skills/record-demo && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18156" && unzip -o skill.zip -d .claude/skills/record-demo && rm skill.zipInstalls to .claude/skills/record-demo
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Produce a short (30-60s) narrated, captioned product demo video with the aidemo engine, via the aidemo MCP server. Use when the user says "record a demo of X", "make a demo video", "demo this feature", or points at a flow (e.g. a shopping flow inside a ChatGPT app) and wants a shareable MP4 with voiceover + captions. The skill authors a storyboard.json (script + per-scene voice/music plan + browser action-spec) and renders it with the engine. Do NOT use for: live screen-sharing, editing an already-rendered MP4, or demos of native/mobile apps (browser only).Key capabilities
- →Generate a storyboard.json for product demos
- →Render MP4s with voiceover and captions
- →Simulate browser actions for demos
- →Utilize the `aidemo` engine via MCP server or CLI
- →Validate storyboard edits before rendering
- →File engine bugs or surprises via `feedback` tool
How it works
The skill acts as a demo director, authoring a `storyboard.json` (script, voice/music plan, browser action-spec) and rendering it into an MP4 video using the `aidemo` engine. It can use either an MCP server or CLI.
Inputs & outputs
When to use record-demo
- →Record feature demos
- →Generate marketing videos
- →Create walkthroughs
About this skill
record-demo
You are the demo director. Turn a feature + loose directions into a polished
browser demo video using the aidemo engine.
This file is a thin adapter. The authoring knowledge lives in the engine — fetch it first, then follow it:
- Preferred — the
aidemoMCP server (registered byaidemo repo-init, or bundled automatically if you installed the Claude Code plugin): call theget_authoring_guidetool and follow the guide. Pipeline operations (probe,render,voice,captions,compose,gif) are jobs: they return ajobIdimmediately — polljob_statusfor progress, results, and failure artifacts. Validate storyboard edits withvalidate_storyboardbefore rendering. Pass absolute demo directories. - Fallback — no MCP server registered: run
aidemo guideand follow the same document using the CLI commands it maps out. - After verifying the final video (per the guide's "Verify before
declaring done"): if you hit any engine bug, surprise, or workaround this
session, file it now — the MCP
feedbacktool (title+body; environment/log context is auto-attached) oraidemo feedback <dir>on the CLI (falls back to a localdocs/feedback-*.mdoffline). If nothing came up, skip this step.
Invoking the engine (aidemo)
aidemo <cmd> means whichever of these applies:
- In the aidemo repo itself (a full checkout):
node bin/aidemo.mjs <cmd>. - In a product repo where this skill was installed via
aidemo repo-init(the engine is not vendored here):npx -y github:tandryukha/aidemo#stable <cmd>.
If unsure, run aidemo doctor (or the MCP doctor tool) — it prints the
engine version and checks prereqs (ffmpeg, Chrome, OPENAI_API_KEY — or
OPENAI_BASE_URL pointing at a local OpenAI-compatible server, or
AIDEMO_TTS_PROVIDER=local for in-process TTS + offline captions; in both
cases no key is needed and doctor reports what's in effect).
Distribution & updates
This skill is a versioned copy of the source in the
aidemo repo. In a product repo
it arrived via aidemo repo-init, which also added a SessionStart hook that
runs aidemo skill check and prints a notice when a newer version is out.
(The authoring guide itself never goes stale — it is served by the engine at
render time.)
- Update the skill (when notified, or any time):
aidemo skill update --dir .— rewrites this file and bumps.claude/skills/record-demo/installed.json. Installed as a Claude Code plugin instead? Update it with/plugin(the marketplace flow), notaidemo skill update. - Send feedback upstream: see step 3 above.
- Bootstrap a new repo:
npx -y github:tandryukha/aidemo#stable repo-init --dir .
When not to use it
- →When the user needs live screen-sharing
- →When the user needs to edit an already-rendered MP4
- →When creating demos for native or mobile apps (browser only)
Limitations
- →The skill does not support live screen-sharing
- →It cannot edit an already-rendered MP4
- →It is for browser-only demos, not native/mobile apps
How it compares
This skill automates the creation of polished, narrated product demo videos with browser action simulations, providing a structured approach to video generation rather than manual recording and editing.
Compared to similar skills
record-demo side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| record-demo (this skill) | 0 | 20d | No flags | Intermediate |
| narrator-ai-cli | 0 | 3mo | Review | Intermediate |
| video-report | 7 | 2mo | No flags | Beginner |
| video-ai-direction | 0 | 1mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
narrator-ai-cli
NarratorAI-Studio
>-
video-report
remotion-dev
Generate a report about a video
video-ai-direction
cardinalconseils
AI video generation direction for Kling API — prompt engineering, motion design, platform specs, text-to-video and image-to-video workflows for marketing content
video-creation
Sheldon-92
Professional video production judgment for AI coding agents — storytelling, motion design, audio, tools (HyperFrames/Remotion)
skills
OpenDemon
噼哩噼哩 Pilipili-AutoVideo 是一个全自动 AI 视频生成代理,可将自然语言主题转化为完整的短视频(含配音、字幕、转场),并自动生成剪映草稿文件。
ugc-video-prompts
palmier-io
Generate ultra-realistic UGC/influencer-style video clips inside Palmier Pro — talking selfies, product demos, candid lifestyle motion — using the proven still-then-animate pipeline instead of cold text-to-video. Drives Palmier Pro's generate_video, get_timeline, and get_media tools directly, with m