What is the v5 Hybrid format for Claude Code skills?

It is a highly structured skill definition format that incorporates Markov Decision Process (MDP) components, such as state-action spaces, policies, and modal logic constraints, to make agent behavior more predictable and verifiable.

How do the four parallel agents collaborate?

Each agent focuses on a specific logical domain (e.g., state transitions or constraint verification). They append findings to a shared 'blackboard' markdown file, which is then synthesized into the final skill.

Can I use this to upgrade existing custom skills?

Absolutely. You can point the Skill Upgrader to any existing SKILL.md file, and it will re-architect the content into the formalized v5 structure while preserving the original intent.

Does this skill require external tools or databases?

Yes, it requires Ragie RAG with indexed partitions containing specific academic texts on planning algorithms, reinforcement learning, and modal logic to provide authoritative guidance.

Skill Upgrader v5

Name: Skill Upgrader v5
Author: scooter-lacroix

byscooter-lacroix

Developer Tools

Upgrades Claude Code skills to the v5 Hybrid format using decision theory frameworks and modal logic verification.

About

Skill Upgrader is a sophisticated meta-skill designed to evolve standard SKILL.md files into high-fidelity v5 Hybrid versions. By employing four parallel sub-agents powered by Ragie-backed RAG (referencing foundational texts on planning algorithms, reinforcement learning, and modal logic), it formalizes agent behaviors into Markov Decision Processes (MDP). This process ensures that skills are not just simple instructions, but mathematically sound policies with clearly defined state-action spaces, reward structures, and rigorous safety verifications for mission-critical automation.

Key Features

Logical constraint verification including temporal and epistemic properties
0 GitHub stars
Deep RAG integration with authoritative texts on RL and logic
Automated conversion to Decision Theory v5 Hybrid format
Formal state-action space modeling and MDP structure generation
Multi-agent orchestration using four specialized logical roles

Use Cases

Refining simple prompt-based skills into robust, structured logical agents
Adding formal safety and liveness constraints to developer workflows
Standardizing custom skill libraries to a unified, high-performance architecture

About

Key Features

Logical constraint verification including temporal and epistemic properties
0 GitHub stars
Deep RAG integration with authoritative texts on RL and logic
Automated conversion to Decision Theory v5 Hybrid format
Formal state-action space modeling and MDP structure generation
Multi-agent orchestration using four specialized logical roles

Use Cases

Refining simple prompt-based skills into robust, structured logical agents
Adding formal safety and liveness constraints to developer workflows
Standardizing custom skill libraries to a unified, high-performance architecture