MCP App StoreMCP App Store
Développez et déboguez le projet d'apprentissage par renforcement Relax sur des clusters Ray distants.
Cette compétence fournit un flux de travail complet pour itérer sur le projet d'apprentissage par renforcement Relax, depuis la modification locale du code jusqu'à la validation distante sur des clusters Ray.
scripts/entrypoint/ray-job.sh.ray job logs avec des filtres de bruit obligatoires pour économiser des tokens et faire remonter les erreurs critiques (CUDA OOM, tracebacks).Cette compétence n'a pas encore été examinée par notre pipeline d'audit automatisé.
Synalinks Framework
Keras-inspired framework for building structured, neuro-symbolic LLM programs with DataModel schemas, modular Programs, and training/optimization tools.
Runtime Communication (research_mvp)
Rules and workflows for messaging, delegation, and task coordination in the research_mvp local multi-agent runtime (leader, researcher, trainer).
Deliberate Practice
Guided framework for accelerating skill acquisition using focused practice, immediate feedback, and progressive challenge—useful for learning technical skills,
Relax: Development & Remote Training Debugging
Tools and procedures to develop the Relax project and validate changes by submitting and monitoring remote Ray training jobs (non-blocking, debug-friendly).
CKB Standalone Debugger
Repository-specific skill for offline CKB contract debugging: run mock transactions, GDB sessions, flamegraph/coverage analysis, and WASM-compatible runs for co
KnowBe4 (Membrane)
Integrate with KnowBe4 via the Membrane CLI to manage users, phishing and training campaigns, groups, reports, and account settings.
Raymon — Ray-style log store & MCP server
Lightweight searchable Ray-compatible log server (Raymon) exposing an MCP interface for agents to search, list, and fetch full log entries for debugging and tri
Learning Opportunities
Adds short interactive learning exercises during AI-assisted coding to help developers understand design decisions and new code before merging.