MCP App StoreMCP App Store
from relax324
Tools and procedures to develop the Relax project and validate changes by submitting and monitoring remote Ray training jobs (non-blocking, debug-friendly).
This skill provides a focused development and debugging workflow for the Relax reinforcement-learning codebase. It explains how to make minimal, targeted code changes, submit training jobs to remote Ray clusters using the provided entrypoint scripts, and monitor logs to validate or iterate on fixes. The skill emphasises non-blocking job submission (RAY_NO_WAIT=1) and sensible log filtering so debugging is efficient and safe.
Use this skill when you need to: adjust training parameters or scripts, validate code changes on a real Ray cluster, run remote experiments for reproduction, or triage training failures (import errors, CUDA OOMs, runtime mismatches). Do not run remote debug flows without explicit cluster address (RAY_ADDRESS) from the user.
This skill is best used by code-aware assistants that can run shell commands and interpret logs (Copilot/Codex/Claude Code/GitHub Codespaces style agents). It assumes the agent can read repo files and invoke CLI tooling (ray, bash).
A well-documented development and debugging skill for the Relax reinforcement learning project on Ray clusters. No bundled scripts — purely instructional, guiding the agent through code changes, remote training job submission, and log monitoring. Clear prerequisites, environment variable tables, and error recovery steps. Niche usefulness as it targets a specific project's workflow.
Clean skill with no security concerns. No scripts to execute. Purely instructional with good structure and error handling guidance. Limited to a specific project's debugging workflow.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Agent Browser — Core
Core usage guide for agent-browser: snapshot-and-ref browser automation to navigate pages, interact with elements, extract data, take screenshots, manage sessio
Datadog Live Debugger (dd-debugger)
Place live log probes on running services to capture runtime arguments and variables without redeploying (Datadog Live Debugger).
Arcana (Technical Mechanism Analysis)
Explain how systems, protocols, or architectures actually work under the hood and surface non-obvious implications and failure modes.
Synalinks Framework
Keras-inspired framework for building structured, neuro-symbolic LLM programs with DataModel schemas, modular Programs, and training/optimization tools.
Offload Test Runner
Run and debug large test suites in parallel using Offload; includes invocation patterns, log filtering, flaky-test handling, and config guidance.
Replit — Advanced Troubleshooting
Step-by-step diagnostics and debugging techniques for deep Replit issues: Nix build failures, container crash loops, memory leaks, and platform vs app isolation
Avenir-Web
Run and improve Avenir-Web autonomous web tasks: choose run mode, validate and refine instructions, execute single or batch runs, and analyze outputs to propose