Video Sourcing Skill

Use this skill when the user asks to find, compare, or analyze social videos (YouTube, TikTok, Instagram, Twitter/X), or explicitly invokes /video_sourcing.

This workflow expects host runtime execution (sandbox mode off). The runner auto-bootstraps a pinned runtime from Memories-ai-labs/[email protected] when VIDEO_SOURCING_AGENT_ROOT is not set.

Triggering

Run this workflow when either condition is true:

1. Message starts with /video_sourcing.
2. The user asks for video sourcing/trend/creator/brand analysis and wants concrete video links.

If /video_sourcing is used with no query body, ask for the missing query.

Execution contract

1. Resolve query text:
2. /video_sourcing ... => strip /video_sourcing and use remaining text.
3. Free-form => use user message as query.
4. Default to compact mode:
5. --event-detail compact
6. If user asks for debugging/raw payloads:
7. Switch to --event-detail verbose

/video_sourcing deterministic path

1. Build command with required args:
2. <skill_dir>/scripts/run_video_query.sh --query "<query>" --event-detail <compact|verbose> --ux-mode three_message --progress-gate-seconds 5
3. Start with exec using background: true and explicit timeout:
4. timeout: 420
5. Poll with process using action: "poll" every 2-4 seconds until process exits.
6. Parse NDJSON output and render only these events, using your persona voice for all user-facing text:
7. started => send a brief message conveying that video sourcing has begun, written in your persona voice
8. ux_progress => read the summary field as structured status data and compose a concise, natural progress update in your persona voice (do not echo summary verbatim) Send each ux_progress as a separate assistant message in Telegram.
9. terminal event (complete, clarification_needed, error) => send final message as-is
10. Do not forward raw progress, tool_call, or tool_result events for /video_sourcing.
11. Preserve the user's existing OpenClaw personality behavior across all messages — progress and final alike.
12. Never launch a second run while a prior run session is still active.
13. If retrying, call process with action: "kill" for the prior sessionId first.
14. If process exits without a terminal event, send a concise fallback message that:
15. states run ended before completion,
16. includes one actionable next step,
17. does not start another run automatically.

Behavior target for /video_sourcing:

1. Fast run (<5s): 2 messages (started, terminal).
2. Longer run (>=5s): recurring throttled ux_progress updates, then terminal.

Free-form path (non-strict)

1. Keep existing flexible behavior.
2. Build command without forcing three_message mode:
3. <skill_dir>/scripts/run_video_query.sh --query "<query>" --event-detail <compact|verbose>
4. Stream useful progress updates and final response naturally.

Final response format

When terminal event is complete:

1. One short paragraph conclusion.
2. Top 3 video references only by default:
3. title
4. url
5. one-line relevance note
6. Tools used: ... with a compact status summary.

If fewer than 3 videos exist, show all available references.

When terminal event is clarification_needed:

1. Ask the clarification question directly.
2. Treat this as the final response for the current run.

When terminal event is error:

1. Send concise failure reason.
2. Include one actionable next step.

Safety and fallback

1. If script fails due to missing env/tooling, explain exact missing piece (for example VIDEO_SOURCING_AGENT_ROOT, uv, or API key env var).
2. If VIDEO_SOURCING_AGENT_ROOT is unset, the runner uses managed path:
3. ~/.openclaw/data/video-sourcing-agent/v0.2.5
4. VIDEO_SOURCING_AGENT_ROOT remains an advanced override for local development.
5. Keep response concise and action-oriented.
6. Never fabricate video URLs or metrics.