theredbluepill

Manage the Trinity AGI auth service and RBAC system -- database schema, role hierarchy, permission management, JWT flow, audit logging, and API endpoints.

Sync files between the host machine and the running Trinity Docker containers — config, agent files, skills, and extensions.

Develop the Trinity AGI Flutter Web Shell -- understand the architecture, A2UI renderer, WebSocket models, dual-client pattern, design tokens, and build workflow.

Operate the Trinity AGI Kubernetes infrastructure -- Helm charts, multi-tenant per-user OpenClaw pods, Vault Agent Injector secrets, minikube dev, and production deployment.

Operate the OpenClaw Gateway that powers Trinity AGI — configure providers, manage sessions, use the CLI, and understand the WebSocket protocol.

Manage the Trinity AGI Docker Compose stack — start, stop, logs, rebuild frontend, and full deploy.

Convert and extract text from PDFs, DOCX, images (OCR), and other document formats using the gateway's built-in document processing stack.

Track tech and AI earnings season automatically — weekly calendar previews, per-company scheduled alerts, and detailed post-earnings summaries delivered to your messaging channel.

Comprehensive guide to using the ARC-AGI Toolkit Python scripts for running remote game attempts, managing scorecards, and exploring games

Use when a remote ARC-AGI-3 run has finished and you need to diagnose what happened from scorecards, reasoning logs, and replay evidence

Use when studying an ARC-AGI-3 game, planning the next remote attempt, or deciding how to learn the most from limited actions

Use when designing or restructuring this repo's ARC-AGI-3 remote attempt runner so experiments stay comparable, observable, and action-efficient

Checks mechanical per-level solvability (a winning trajectory exists under the real game rules). Use when authoring or reviewing stems, after logic changes, or when debugging “impossible” puzzles. Complements discoverability review.

Judges whether an ARC game is discoverable by play (goals/rules learned in the env); co-requires fair shared observation/actions for humans and AIs. Use when reviewing stems for discovery-through-play or remediation.