UGC Campaign Pipeline

Complete UGC video campaign pipeline: product → hero image → variations → videos → edited final. ✅ USE WHEN: - User says "crear campaña UGC" or "pipeline completo" - Need end-to-end UGC video production - Starting from product image/URL → final edited video - Want the full Doritos-style workflow ❌ DON'T USE WHEN: - Just need one step (use individual skills) - Already have final videos, just editing → use Remotion - Only need images, no video → use Morpheus only OUTPUT: Edited MP4 video with multiple scenes + subtitles + logo

This skill's instructions expect local scripts, catalog files, and a COMFY_DEPLOY_API_KEY, but the published metadata doesn't declare any of those requirements. Before installing/using: 1) Don't paste or expose any API key until you confirm what COMFY_DEPLOY_API_KEY is (which service uses it and what privileges it grants). 2) Verify that the referenced scripts under ~/.clawdbot/skills/* and the model catalog file are from trusted sources and inspect their contents — the agent will run them. 3) Ensure required binaries (e.g., jq, the 'uv' runner, Python) are present and trusted. 4) Consider running this in an isolated VM or sandbox to avoid unintended access to your home directory. 5) Ask the skill author for an explicit dependency list and the exact purpose of COMFY_DEPLOY_API_KEY; if they can't provide that, treat the skill as high-risk and avoid supplying secrets.

Type: OpenClaw Skill Name: ugc-campaign-pipeline Version: 1.0.0 The skill bundle defines a workflow for creating UGC videos by orchestrating several other local OpenClaw skills. All commands in SKILL.md execute Python scripts located within the `~/.clawdbot/skills/` directory using `uv run`, and all file operations are confined to local paths within `~/clawd/`. There is no evidence of data exfiltration, unauthorized remote execution, persistence mechanisms, or prompt injection attempts to subvert the agent's intended behavior. The instructions are clear and directly support the stated purpose.