Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By dbinky
Multi-persona PR review pipeline, ralph loop planning, and code review skills.
npx claudepluginhub dbinky/dbinky-skill-set --plugin spec-to-designYou are a pragmatic senior engineer who ships working software. You respect
You are a senior technical writer and architect reviewing a body of documentation
You are a specialist code reviewer focused entirely on finding complexity that is greater
You are a specialist reviewer focused exclusively on inconsistency across a codebase. You
You are the Curation Orchestrator. You coordinate a parallel codebase analysis pipeline
Automatically generate ralph review files (RALPH.md, focus-areas.md, gaps-identified.md) from spec and design docs without interactive Q&A
Non-interactive submission to ralph-o-matic with sensible defaults — pre-flight checks, auto-commit, auto-push, and Teams notification
Analyze a codebase for vibe-coding cruft — dead code, excessive complexity, duplication, and inconsistent patterns — then selectively fix issues to produce clean, senior-engineer-quality code.
End-to-end feature automation — interactive brainstorm for spec and design, then automated alignment, planning, implementation, ralph refinement, and PR review
Generate ralph-o-matic review files via interactive Q&A or automatic derivation (--auto) from spec and design docs
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Review pull requests with structured analysis and approve with confidence
Multi-lens code review pipeline: deep review (Claude or Codex), automated fix loop, interactive walkthrough, manual promote, external-finding injection.
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Claude Code skills for ralph-o-matic iterative AI coding refinement loops
A Claude Code plugin that orchestrates multi-persona PR reviews with language and framework-specific rules.
Architect (R1) → 10x Engineer (R1) → Architect (R2) → 10x Engineer (R2) → Security → Manager → [You Choose Fixes] → Senior Engineer
Six specialized reviewers examine your PR sequentially, each building on previous feedback. The Architect and 10x Engineer debate twice before Security and Manager weigh in. You then choose which fix categories to apply, and the Senior Engineer implements them.
# Add the marketplace
/plugin marketplace add dbinky/dbinky-skill-set
# Install the plugin
/plugin install pr-review@dbinky-skill-set
/pr-review # Auto-detect PR from current branch
/pr-review 87 # Review specific PR number
| Persona | Focus | Rounds |
|---|---|---|
| Ivory Tower Architect | SOLID, DRY, naming, patterns, testability | 2 |
| 10x GSD Engineer | Pragmatism, shipping, over-engineering pushback | 2 |
| Security Expert | OWASP, injection, auth, secrets, crypto | 1 |
| Engineering Manager | Final call — Must Fix / Should Fix / Consider / Defer | 1 |
| Senior Engineer | Implements the fixes you select | 1 |
Comment limits scale with PR size so small PRs aren't over-reviewed and large PRs get thorough coverage. Limits apply to new findings only — responses between Architect and 10x during the debate are always unlimited.
| PR Size | Files | Architect | 10x | Security |
|---|---|---|---|---|
| Small | 1–3 | 3–5 | 2–3 | Unlimited |
| Medium | 4–10 | 5–10 | 3–6 | Unlimited |
| Large | 11–25 | 8–16 | 5–10 | Unlimited |
| XL | 26+ | 12–20 | 8–14 | Unlimited |
After the Manager categorizes all findings, you choose a tier:
Rules are auto-detected from the PR diff. Each language/framework has two rule files: general patterns and security-specific patterns.
Languages: Go, Python, TypeScript, JavaScript, C#, Rust, Java, Dart
Frameworks: Orleans, Spring Boot, React, Angular, Flutter
Multi-language PRs load all applicable rule sets.
gh) — the plugin will check for it and guide installation if missingMIT