Skill Upgrader

Takes any skill file and upgrades it to Decision Theory v5 Hybrid format by spawning four parallel agents that hit Ragie partitions loaded with planning and logic textbooks. Agent 1 extracts MDP structure from LaValle, Agent 2 designs policies using Sutton & Barto, Agent 3 formalizes constraints with Blackburn's modal logic, and Agent 4 verifies safety properties from Huth & Ryan. They collaborate on a shared blackboard, then you synthesize the final skill with proper state spaces, policies, and formal constraints. It's meta-tooling for formalizing your other skills, assuming you've already got those CS textbooks indexed in Ragie. The parallel agent design is clever, though you're betting hard on having that RAG infrastructure ready.

skills.sh installs: 491
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill skill-upgrader --agent claude-code

Installs into .claude/skills of the current project.

Files

Skill Upgrader

Meta-skill that upgrades any SKILL.md to Decision Theory v5 Hybrid format using 4 parallel Ragie-backed agents.

When to Use

"Upgrade this skill to v5"
"Formalize this skill with decision theory"
"Add MDP structure to this skill"
"Apply the skill-upgrader to X"

Prerequisites

Ragie RAG with indexed books:

decision-theory partition: LaValle Planning Algorithms, Sutton & Barto RL
modal-logic partition: Blackburn Modal Logic, Huth & Ryan Logic in CS

Workflow

Step 1: Setup Session

SESSION=$(date +%Y%m%d-%H%M%S)-upgrade-{skill_name}
mkdir -p thoughts/skill-builds/${SESSION}

Step 2: Initialize Blackboard

Create thoughts/skill-builds/{session}/00-blackboard.md:

# Skill Upgrade: {skill_name}
Started: {timestamp}

## Input Skill
{path_to_skill}

## Target Format
Decision Theory v5 Hybrid

## Agent Findings
(Agents append below)

---