By tommaone
Vernon — Socratic requirement enforcer. Intercepts vague tasks and asks targeted questions until requirements are specific enough to hand to Splinter.
"The simplest solution that actually works is almost always the right one."
A Claude Code skill marketplace implementing the Turtleman development style — a siege-specialist approach to software engineering using a squad of TMNT-inspired AI agents.
| Skill | Role | Invoke |
|---|---|---|
🐢 turtleman | Full Turtleman mode — activates the squad | /turtleman:turtleman <task> |
🐀 splinter | Ratman orchestrator — dispatches the right turtle | /splinter:splinter <task> |
🐸 vernon | Socratic requirement enforcer — clarifies before anyone builds | /vernon:vernon <task> |
🔵 leonardo | Plans and coordinates — design before code | /leonardo:leonardo <task> |
🟣 donatello | Automation, tooling, infra | /donatello:donatello <task> |
🔴 raphael | Fast delivery — fixes things quietly | /raphael:raphael <task> |
🟠 michelangelo | Creative lateral thinker — finds the meme solution | /michelangelo:michelangelo <task> |
⚔️ shredder | Devil's advocate — tears apart the plan before it ships | /shredder:shredder <plan> |
Siege specialist mindset: methodical, precise, no interest in glory — just getting through the wall.
The room isn't on fire. It's already been fixed. Just hasn't been mentioned yet. 🐢
Add to your ~/.claude/settings.json:
{
"extraKnownMarketplaces": {
"turtleman-skills": {
"source": {
"source": "git",
"url": "https://github.com/tommaone/claude-skills.git",
"ref": "main"
}
}
},
"enabledPlugins": {
"turtleman@turtleman-skills": true,
"splinter@turtleman-skills": true,
"vernon@turtleman-skills": true,
"leonardo@turtleman-skills": true,
"donatello@turtleman-skills": true,
"raphael@turtleman-skills": true,
"michelangelo@turtleman-skills": true,
"shredder@turtleman-skills": true
}
}
Restart Claude Code. Done.
The squad is generic by design. To make it yours:
plugins/turtleman/commands/turtleman.md — add your repos and active project contextshared/turtle-dojo.md — replace MCP placeholders with your own MCP server namesturtle-evolution/README.md to ~/.claude/turtle-evolution/ and create one .md per turtle (start empty)Each turtle has a personal lesson log at ~/.claude/turtle-evolution/<turtle>.md. These files live on your machine, never in this repo — they're yours.
Turtles read their evolution file on activation and apply any rules listed there. Splinter writes new lessons after tasks. Shredder challenges wrong lessons. You decide what sticks.
See turtle-evolution/README.md for the format and setup.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub tommaone/claude-skills --plugin vernonRaphael — aggressive reviewer, finds the hard problems.
Turtleman development mode — calm, direct, siege-specialist precision, TMNT squad deployed via Splinter.
Shredder — adversarial gate keeper, stress-tests plans and catches mistakes.
Splinter — master orchestrator, decomposes tasks and dispatches turtles.
Leonardo — disciplined architect and planner of the squad.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research