# Send Video Proof to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "video-proof",
    "name": "Video Proof",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/rikisann/video-proof",
    "canonicalUrl": "https://clawhub.ai/rikisann/video-proof",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/video-proof",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-proof",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "references/proof-spec.md",
      "scripts/api-proof.js",
      "scripts/package-lock.json",
      "scripts/package.json",
      "scripts/record-proof.js"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "video-proof",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T14:37:08.253Z",
      "expiresAt": "2026-05-08T14:37:08.253Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-proof",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-proof",
        "contentDisposition": "attachment; filename=\"video-proof-1.0.2.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "video-proof"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/video-proof"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/video-proof",
    "downloadUrl": "https://openagent3.xyz/downloads/video-proof",
    "agentUrl": "https://openagent3.xyz/skills/video-proof/agent",
    "manifestUrl": "https://openagent3.xyz/skills/video-proof/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/video-proof/agent.md"
  }
}
```
## Documentation

### Video Proof

Record video demos of implemented features using Playwright's built-in screen recording. After a coding task completes, this skill starts your app, runs a scripted walkthrough, and captures video + screenshots + console logs as proof artifacts.

Works with any stack — Next.js, Vite, Django, Rails, Go, Docker, static files, or an already-running server. You provide the start command; the skill handles the rest.

### Prerequisites

Run once per machine:

bash scripts/setup.sh

Installs Playwright (Chromium), ffmpeg, and the yaml npm package.

### Option A: YAML Proof Spec (recommended)

Create a proof-spec.yaml:

proof:
  start_command: "npm run dev"       # any shell command that starts your app
  start_port: 3000                   # port to poll before recording begins
  base_url: "http://localhost:3000"
  steps:
    - goto: "/dashboard"
    - wait: 2000
    - screenshot: "dashboard-loaded"
    - click: "text=Create New"
    - wait: 1000
    - assert_visible: "text=New Item"
    - screenshot: "item-created"

Run it:

node scripts/record-proof.js --spec proof-spec.yaml --output ./proof-artifacts

### Option B: Inline CLI (simple cases)

node scripts/record-proof.js \\
  --start "python3 -m http.server 8080" \\
  --port 8080 \\
  --url http://localhost:8080 \\
  --goto "/" \\
  --screenshot "home" \\
  --output ./proof-artifacts

### Option C: Already-running server (no start_command)

Omit start_command — the script skips server startup and goes straight to recording:

proof:
  base_url: "https://staging.myapp.com"
  steps:
    - goto: "/login"
    - screenshot: "login-page"

### Artifacts Produced

proof-artifacts/
├── video.webm            # Full screen recording
├── video.mp4             # Chat-friendly version (auto-converted via ffmpeg)
├── screenshots/          # Named screenshots from steps
│   ├── dashboard-loaded.png
│   └── item-created.png
├── console.log           # Browser console output (errors, warnings, logs)
└── proof-summary.md      # Markdown report with pass/fail status per step

Exit code: 0 if all steps pass, 1 if any step fails. On failure, a FAILURE.png full-page screenshot is captured automatically.

### Start Command Examples

The start_command field accepts any shell command. Examples:

Stackstart_commandstart_portNext.jsnpm run dev3000Vite / Reactnpm run dev5173Djangopython manage.py runserver 0.0.0.0:80008000Flaskflask run --port 50005000Railsbin/rails server -p 30003000Gogo run . -addr :80808080Rust (Actix/Axum)cargo run8080Docker Composedocker compose up3000Static filespython3 -m http.server 80808080Already running(omit field)—

### Step Actions

ActionValueDescriptiongoto"/path" or full URLNavigate to a pageclickPlaywright selectorClick an element (text=Submit, #btn, .class)fill{selector, value}Clear and fill an input fieldtype{selector, text}Type into an element keystroke by keystrokewaitmillisecondsPause (let animations/data load)screenshot"name"Save screenshots/<name>.pngscroll"down" or "up"Scroll 500px in directionassert_visiblePlaywright selectorFail the proof if element isn't visibleassert_urlstringFail if current URL doesn't contain string

### API-Only Proof (No Browser)

For backend/API changes with no UI, use api-proof.js:

node scripts/api-proof.js --spec api-spec.yaml --output ./proof-artifacts

proof:
  start_command: "npm start"
  start_port: 3000
  base_url: "http://localhost:3000"
  requests:
    - method: GET
      path: /api/health
      assert_status: 200
      assert_body_contains: "ok"
    - method: POST
      path: /api/users
      headers:
        Content-Type: application/json
      body: '{"name": "test"}'
      assert_status: 201

Produces api-proof.md and api-results.json instead of video.

### Integration with Coding Agents

Append to any coding task prompt:

After completing the implementation, create a proof-spec.yaml that:
1. Starts the app with the appropriate command for this project
2. Navigates to the relevant pages
3. Demonstrates the feature with clicks/fills as needed
4. Asserts the expected outcome is visible
5. Takes before/after screenshots

Then run:
  node <skill-path>/scripts/record-proof.js --spec proof-spec.yaml --output ./proof-artifacts

Commit proof-artifacts/ with your changes.

The agent writes the proof spec based on what it built, runs it, and the video becomes part of the deliverable.

### Spec Reference

See references/proof-spec.md for the full YAML schema, API proof schema, and a copy-paste PRD template.

### Tips

Use assert_visible to make proofs fail when the feature doesn't work — video of a broken page isn't useful proof
Keep specs focused on the specific feature, not the whole app
wait steps between actions let data load and animations settle — 1-2s is usually enough
The video captures real load times — doubles as a basic performance check
If ffmpeg isn't available, the script still produces .webm (just skips mp4 conversion)
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: rikisann
- Version: 1.0.2
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-01T14:37:08.253Z
- Expires at: 2026-05-08T14:37:08.253Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/video-proof)
- [Send to Agent page](https://openagent3.xyz/skills/video-proof/agent)
- [JSON manifest](https://openagent3.xyz/skills/video-proof/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/video-proof/agent.md)
- [Download page](https://openagent3.xyz/downloads/video-proof)