{"skill":{"slug":"openclaw-vln-planner","displayName":"OpenClaw VLN Planner","summary":"Plan the next high-level navigation step for a robot from a user navigation instruction, one current image, and a sequence of historical images. Use when the...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":123,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1774442245231,"updatedAt":1774442811505},"latestVersion":{"version":"1.0.0","createdAt":1774442245231,"changelog":"Initial release of OpenClaw VLN Planner.\n\n- Introduces a high-level vision-language navigation planner for robots based on visual observations and natural-language user instructions.\n- Outputs a single, validated mid-level navigation action as pure JSON (MOVE_FORWARD, TURN_LEFT, TURN_RIGHT, STOP) for each input.\n- Integrates with any OpenAI-compatible multimodal gateway for action prediction using current and historical frames.\n- Includes strict safety fallback rules—defaults to STOP on uncertainty, parse failure, or safety concerns.\n- Provides clear input requirements, output contract, and runtime configuration via external YAML.\n- Bundles schema reference, config template, and a bridge script for execution.","license":"MIT-0"},"metadata":null,"owner":{"handle":"tiktokdad","userId":"s179dsecf2d5pvr84n2smnqkyn83g2z0","displayName":"TIKTOKDAD","image":"https://avatars.githubusercontent.com/u/91710456?v=4"},"moderation":null}