🎯

ralph-wiggum-v2

🎯Skill

from adaptationio/skrillz

VibeIndex|
What it does

ralph-wiggum-v2 skill from adaptationio/skrillz

ralph-wiggum-v2

Installation

Add MarketplaceAdd marketplace to Claude Code
/plugin marketplace add adaptationio/Skrillz
Install PluginInstall plugin from marketplace
/plugin install skrillz@adaptationio-Skrillz
Claude CodeAdd plugin in Claude Code
/plugin enable skrillz@adaptationio-Skrillz
Add MarketplaceAdd marketplace to Claude Code
/plugin marketplace add /path/to/skrillz
Install PluginInstall plugin from marketplace
/plugin install skrillz@local

+ 4 more commands

πŸ“– Extracted from docs: adaptationio/skrillz
1
-
Last UpdatedJan 16, 2026

Skill Details

SKILL.md

Autonomous TDD development loop with parallel agent swarm, category evolution, and convergence detection. Use when running autonomous game development, quality improvement loops, or comprehensive codebase reviews.

Overview

# Ralph Wiggum v2 - Autonomous TDD Development Loop

Quick Start

```

/ralph-wiggum-v2:ralph-loop --project "diablo-starcraft" --completion-promise "DIABLO_STARCRAFT_COMPLETE"

```

Overview

Autonomous TDD development loop that uses parallel agent swarms to review code, discover issues, and fix them with test-first methodology until convergence criteria are met.

Workflow

Phase 1: Discovery & Initialization

  1. Locate or create state file: {project}/.ralph/state.json
  2. Locate or create categories file: {project}/.ralph/categories.json
  3. Bootstrap categories from codebase structure if empty

Phase 2: Parallel Agent Review Swarm

Spawn 3-5 parallel agents with:

  • Random category (weighted toward lowest scores)
  • Random subcategory within that category
  • Random review style (never same as last 3 used)
  • Unique focus area (no overlap between agents)

Phase 3: TDD Implementation Cycle

For each finding:

  1. Write failing test first
  2. Implement minimal fix
  3. Verify test passes
  4. Update state

Phase 4: Category Evolution

After each iteration:

  1. Merge new discoveries
  2. Recalculate scores
  3. Meta-review (every 5 iterations)

Phase 5: Convergence Detection

Complete when:

  • 10 consecutive clean iterations
  • All category scores >= 95/100
  • All tests passing
  • Game runs without crashes

---

State Schema

```json

{

"project": "diablo-starcraft",

"iteration": 0,

"consecutiveCleanIterations": 0,

"requiredCleanIterations": 10,

"completionPromise": "DIABLO_STARCRAFT_COMPLETE",

"categories": {},

"discoveryLog": [],

"lastReviewStyles": [],

"agentHistory": [],

"startedAt": "",

"lastUpdated": ""

}

```

Categories Schema

```json

{

"categories": {

"": {

"score": 50,

"maxScore": 100,

"subcategories": {

"": {

"score": 50,

"issues": [],

"lastReviewed": null,

"reviewCount": 0

}

},

"discoveredAt": 0,

"lastUpdated": ""

}

}

}

```

---

Review Styles

Code Quality

| Style | Focus |

|-------|-------|

| NITPICKER | Formatting, naming, tiny inconsistencies |

| REFACTORER | Duplication, abstraction opportunities |

| DRY_ENFORCER | Copy-paste code, repeated patterns |

| TYPE_ZEALOT | Type safety, any usage, casting |

| SOLID_ADHERENT | SOLID principle violations |

| API_PURIST | Interface design, contracts, signatures |

Reliability

| Style | Focus |

|-------|-------|

| DEBUGGER | Logic errors, off-by-one, wrong operators |

| EDGE_CASE_HUNTER | Boundary conditions, null/undefined |

| ERROR_HANDLER | Missing try/catch, unhandled promises |

| STATE_MACHINE_ANALYST | Invalid state transitions |

| CONCURRENCY_EXPERT | Race conditions, async bugs |

| MEMORY_LEAK_HUNTER | Listeners not removed, growing arrays |

Performance

| Style | Focus |

|-------|-------|

| PERFORMANCE_HAWK | O(nΒ²), unnecessary renders, hot paths |

| ALLOCATION_AUDITOR | Object churn, GC pressure |

| RENDER_OPTIMIZER | DOM thrashing, layout thrashing |

Security

| Style | Focus |

|-------|-------|

| SECURITY_AUDITOR | XSS, injection, unsafe operations |

| INPUT_VALIDATOR | Unsanitized user input |

Architecture

| Style | Focus |

|-------|-------|

| ARCHITECT | Coupling, cohesion, separation of concerns |

| DEPENDENCY_AUDITOR | Circular deps, tight coupling |

| LAYER_GUARDIAN | Layer violations, wrong abstractions |

Testing

| Style | Focus |

|-------|-------|

| TEST_SKEPTIC | Coverage gaps, weak assertions |

| MUTATION_TESTER | Tests that always pass |

| INTEGRATION_ANALYST | Unit vs integration gaps |

Game-Specific

| Style | Focus |

|-------|-------|

| DIABLO_VETERAN | ARPG conventions, loot, skills, combat feel |

| STARCRAFT_FAN | Faction identity, unit feel, SC universe |

| GAME_FEEL_EXPERT | Juice, polish, responsiveness |

| BALANCE_DESIGNER | Numbers, progression, fairness |

| PLAYER_PSYCHOLOGY | Motivation, reward loops |

| SPEEDRUNNER | Exploits, sequence breaks |

| COMPLETIONIST | Missing edge cases in content |

| FIRST_TIME_USER | Onboarding, confusion points |

Meta

| Style | Focus |

|-------|-------|

| FRESH_EYES | What would confuse a new developer? |

| DOCUMENTATION_STICKLER | Missing/wrong comments |

| FUTURE_MAINTAINER | Technical debt accumulation |

---

Agent Output Format

```json

{

"agentId": "",

"category": "",

"subcategory": "",

"reviewStyle": "