Menu
Use inferred direction deltas to search toward unvisited safe positions after simple action probes identify a controlled object.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Detect regular rectangular board cells and click untried non-HUD cells while avoiding prior no-op, HUD-only, or death outcomes.
Prefer safe untried simple actions from the current state when no higher-confidence solver has a plan.
When coordinate clicks are available but no board model is confident, probe visible compact non-HUD objects before raw fallback actions.
Play ARC-AGI-3 interactive grid games via the arc MCP tools — explore mechanics from observation, then exploit them to win levels.
Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.
Use this skill when the user wants Ouroboros to browse or automate websites in a real Chrome-compatible browser. Prefer it for navigating pages, taking browser snapshots, clicking or filling visible controls, scraping page state, testing web flows, and using CDP auto-connect without asking the user to install npm packages.
| name | movement-bfs-frontier |
| description | Use inferred direction deltas to search toward unvisited safe positions after simple action probes identify a controlled object. |
| license | Apache-2.0 |
| executor | movement_bfs |
| triggers | ["movement_deltas_known","simple_actions_available"] |
| priority | 90 |
| metadata | {"author":"ouroboros-rsi","version":"1.0"} |
Use this skill when simple action probes show that actions 1-4 move a stable foreground object. Treat the moved object as the controlled object only after the transition model has observed consistent deltas.
Plan by building a local movement graph from the current inferred position,
learned action deltas, blocked edges, death edges, and visited positions. Prefer
short paths to unvisited safe cells. Never choose an edge already observed to
cause GAME_OVER or no visible change from the same state.
This skill is intentionally generic. It must not store exact game ids, frame hashes, solved-level walkthroughs, or fixed coordinates from public games.
