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:

• Message starts with /video_sourcing.
• 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

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

/video_sourcing deterministic path

• Build command with required args:
• /scripts/run_video_query.sh --query "" --event-detail --ux-mode three_message --progress-gate-seconds 5
• Start with exec using background: true and explicit timeout:
• timeout: 420
• Poll with process using action: "poll" every 2-4 seconds until process exits.
• Parse NDJSON output and render only these events, using your persona voice for all user-facing text:
• started => send a brief message conveying that video sourcing has begun, written in your persona voice
• 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.

• terminal event (complete, clarification_needed, error) => send final message as-is
• Do not forward raw progress, tool_call, or tool_result events for /video_sourcing.
• Preserve the user's existing OpenClaw personality behavior across all messages — progress and final alike.
• Never launch a second run while a prior run session is still active.
• If retrying, call process with action: "kill" for the prior sessionId first.
• If process exits without a terminal event, send a concise fallback message that:
• states run ended before completion,
• includes one actionable next step,
• does not start another run automatically.

Behavior target for /video_sourcing:

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

Free-form path (non-strict)

• Keep existing flexible behavior.
• Build command without forcing three_message mode:
• /scripts/run_video_query.sh --query "" --event-detail
• Stream useful progress updates and final response naturally.

Final response format

When terminal event is complete:

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

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

When terminal event is clarification_needed:

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

When terminal event is error:

• Send concise failure reason.
• Include one actionable next step.

Safety and fallback

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