---
name: egbe-os-product-demo-video
description: Record a real product walkthrough and produce a video and poster.
metadata:
  egbe-when: "Offer when a homepage or pitch would benefit from showing the product in action."
  egbe-visible: "true"
  egbe-title: "Product demo video"
  egbe-description: "Show your product in action with a clear walkthrough video and a preview image."
  egbe-category: "Product & design"
---

<!-- egbe-catalog-updates:v1 -->
For work in a workspace with an installed, executable Egbe catalog, run
`python3 "<skills-directory>/egbe-os-quickstart/scripts/sync-catalog.py" --check` using the
actual installation path before starting work with this skill. `<skills-directory>` is the
project folder that contains this skill's directory, such as `.agents/skills`; find it with
file tools or `ls`, not inline interpreter code. Follow its result
with `<skills-directory>/egbe-os-quickstart/references/skill-updates.md`, then reread this
skill if updated. The check is read-only; the reference covers applying updates.
For public guidance without an installed catalog or command execution, skip
this local check and read the current published instructions directly. Reading
does not require a project or installation. For project execution that needs
connection or setup, use `GET /quickstart` on `OS_URL` to choose the appropriate
workspace or no-installation path before setup. The quickstart handles its own check.

Scheduled and other unattended runs have no one to approve inline code, so
`python -c`, `node -e`, heredoc scripts and code-execution tools may be blocked
there. Run bundled scripts as `python3 <script> ...` or `node <script> ...`, and
read files with file tools or plain shell commands.

<!-- egbe-connection-identity:v1 -->
Public instruction and playbook reads do not require credentials or connection
identity. The following applies to authenticated project requests, not reading
or applying public guidance without a connection.

For a BYOA workspace, retain its connection identity on **every authenticated
Egbe request**, including the examples and referenced workflows below. Load
`OS_URL` and `OS_API_KEY` from the project's Git-ignored `.env.local`. Set
`OS_AGENT_NAME` to your actual human-readable agent name, for example
`Claude Code` or `Codex`, not a slug such as `claude-code` or `CLAUDE_CODE`.
This is the name the owner sees in Dashboard. Never infer it from curl or reuse
another agent's identity. If your name is unknown, leave it unset. Quickstart saves the per-agent UUID in
`OS_CONNECTION_ID_<AGENT_SLUG>` (uppercase name with separators changed to
underscores, e.g. `CLAUDE_CODE`) and the optional owner-provided nickname in
`OS_WORKSPACE_NAME` in that file.

Many agent runtimes, including Claude Code, start a fresh shell for every
command, so shell functions and exported variables from an earlier command are
gone. Make each command that calls Egbe self-contained: load `OS_URL` and
`OS_API_KEY` in that same command, and run each authenticated curl example
through the project-local helper with your agent name set inline:

```bash
OS_AGENT_NAME="<your agent name>" python3 "<skills-directory>/egbe-os-quickstart/scripts/egbe-curl.py" --egbe-request /me/limits -s
```

`--egbe-request` loads the saved URL and API key from `.env.local` without
executing it, constructs the full URL, and adds the bearer token before calling
curl. Replace `/me/limits` with the API path from an example and keep its other
curl options; omit the example's URL and Authorization header. This mode rejects
additional destinations and redirects. Without this mode, the helper takes the
same arguments as `curl` and you must load credentials before shell expansion.
Do not edit global shell
configuration. Only in a shell that persists between your commands may you
instead export `OS_AGENT_NAME` once and define
`curl() { python3 "<skills-directory>/egbe-os-quickstart/scripts/egbe-curl.py" "$@"; }`.
Likewise prefix `OS_AGENT_NAME="<your agent name>"` on each command that runs a
bundled Python or JavaScript client.

The helper adds the saved identity headers only for the configured Egbe URL;
other destinations receive no extra headers. For an Egbe request it exits 22 on
an HTTP status of 400 or above and writes a status and request ID line to stderr
after every response; `<skills-directory>/egbe-os-quickstart/references/connection.md`
describes both. It rejects mixed destinations and redirects when attaching
identity. If the helper or this agent's UUID is missing, follow `GET /quickstart`
first. Before catalog installation, download and inspect
`GET /skills/quickstart/resources/scripts/egbe-curl.py` into the workspace's temporary
setup directory and use that path. After installation, switch to the installed helper.
For other Python, JavaScript or MCP clients, explicitly configure the same
`X-Egbe-Connection-Id`, `X-Egbe-Agent-Name`, and optional `X-Egbe-Workspace-Name`
headers on Egbe requests. A client that cannot attach identity headers remains
usable as an unidentified connection; do not claim its later activity is identified.
Deployed-product requests use their separate product credentials and no agent identity.


# Record a product demo

Keep the recording context, source captures, final media and checks together in
`egbe-docs/marketing/packs/<video-id>/`; version source captures in `work/` and use
the existing plan or asset notes rather than creating a separate document per step.
Keep credential-bearing captures out of Git and public exports.

Show the real path from customer intent to a useful result. Deliver a playable
video and poster; embedding or publishing them is a separate action unless
included in the request.

## Prepare the walkthrough

Read the requested or already agreed audience, destination and behavior, then
inspect the actual product. Resolve consequential gaps without reopening accepted
choices. Capture the shortest coherent journey that demonstrates the requested
result. Use a local or staging app when appropriate; for an existing
deployment, confirm its serving revision through `egbe-os-deploy` rather than guessing
a hostname.

Use synthetic, non-sensitive content and a test identity only if the journey
needs authentication. Reuse an authorized identity when possible. A public
tool needs neither signup nor a mailbox. Do not generate paid transactions,
send outreach or alter real customer records just to make a demo. Prepare any
necessary test state within the approved task scope.

## Capture real behavior

Use the harness's available browser/recording tools. If they cannot record,
follow [Recording options](references/recording.md). Identify the precise
missing dependency or permission if recording remains unavailable; screenshots
or AI-generated footage are not a completed recording.

Start from a ready page, perform meaningful actions and wait for visible
outcomes instead of relying only on fixed sleeps. Keep text legible at the
target size and let viewers see the result. If the app fails, record the defect
as a blocker; do not conceal it with a mock success screen. Cut idle/setup time,
not steps essential to understanding what the product really does.

## Verify and deliver

Inspect playback from start to finish and the poster at the intended display
size: content is readable, the promised result is visible, no private data is
exposed, and no black/error frames or accidental dialogs remain. Confirm file
duration, codec and dimensions, not just existence. Keep source revision/URL
and walkthrough steps with the project's existing asset records so another
session can reproduce the capture.

Store the video and poster in the requested destination; for embedding, use
the product's existing public asset convention. Check the actual browser
player, fallback poster and mobile layout. Provide controls or a pause option
for looping content; respect reduced motion and add captions when speech
carries meaning. Report local file paths, verified outcome and any limitations.
Publish only when authorized, using `egbe-os-git` and `egbe-os-deploy` for an Egbe-hosted app.