The `/ring:review` command is renamed to `/ring:codereview` to more accurately reflect its function. The name "review" was too generic and could be misinterpreted. "codereview" is explicit, clarifying that the command triggers a parallel code review by specialized agents. This enhances command discoverability and reduces ambiguity. All documentation, skill files, and examples across the repository are updated to reflect this new command name. The command's definition is also expanded to provide a more comprehensive guide on the parallel review workflow, detailing the process and expected output format. Finally, a new `AGENTS.md` symlink is added for easier navigation.
20 KiB
💍 The Ring - Skills Library for AI Agents
Proven engineering practices, enforced through skills.
Ring is a comprehensive skills library and workflow system for AI agents that transforms how AI assistants approach software development. Currently implemented as a Claude Code plugin marketplace with 7 active plugins (see .claude-plugin/marketplace.json for current versions), the skills themselves are agent-agnostic and can be used with any AI agent system. Ring provides battle-tested patterns, mandatory workflows, and systematic approaches to common development tasks.
✨ Why Ring?
Without Ring, AI assistants often:
- Skip tests and jump straight to implementation
- Make changes without understanding root causes
- Claim tasks are complete without verification
- Forget to check for existing solutions
- Repeat known mistakes
Ring solves this by:
- Enforcing proven workflows - Test-driven development, systematic debugging, proper planning
- Providing 46 specialized skills - From brainstorming to production deployment (20 core + 2 dev-team + 9 product planning + 6 FinOps + 1 ralph-wiggum + 7 technical writing + 1 beads)
- 20 specialized agents - 5 review/planning agents + 10 developer role agents + 2 FinOps agents + 3 technical writing agents
- Automating skill discovery - Skills load automatically at session start
- Preventing common failures - Built-in anti-patterns and mandatory checklists
🤖 Specialized Agents
Review & Planning Agents (default plugin):
ring-default:code-reviewer- Foundation review (architecture, code quality, design patterns)ring-default:business-logic-reviewer- Correctness review (domain logic, requirements, edge cases)ring-default:security-reviewer- Safety review (vulnerabilities, OWASP, authentication)ring-default:write-plan- Implementation planning agentring-default:codebase-explorer- Deep architecture analysis (Opus-powered, complements built-in Explore)- Use
/ring-default:codereviewcommand to orchestrate parallel review workflow
Developer Agents (dev-team plugin):
ring-dev-team:backend-engineer- Language-agnostic backend specialist (adapts to Go/TypeScript/Python/etc)ring-dev-team:backend-engineer-golang- Go backend specialist for financial systemsring-dev-team:backend-engineer-typescript- TypeScript/Node.js backend specialist (Express, NestJS, Fastify)ring-dev-team:backend-engineer-python- Python backend specialist (FastAPI, Django, Flask)ring-dev-team:devops-engineer- DevOps infrastructure specialistring-dev-team:frontend-engineer- React/Next.js specialist (JavaScript-first)ring-dev-team:frontend-engineer-typescript- TypeScript-first React/Next.js specialistring-dev-team:frontend-designer- Visual design specialistring-dev-team:qa-analyst- Quality assurance specialistring-dev-team:sre- Site reliability engineer
FinOps Agents (ring-finops-team plugin):
ring-finops-team:finops-analyzer- Financial operations analysisring-finops-team:finops-automation- FinOps template creation and automation
Technical Writing Agents (ring-tw-team plugin):
ring-tw-team:functional-writer- Functional documentation (guides, tutorials, conceptual docs)ring-tw-team:api-writer- API reference documentation (endpoints, schemas, examples)ring-tw-team:docs-reviewer- Documentation quality review (voice, tone, structure, completeness)
Plugin versions are managed in .claude-plugin/marketplace.json
🚀 Quick Start
Installation as Claude Code Plugin
-
Quick Install Script (Easiest)
Linux/macOS/Git Bash:
curl -fsSL https://raw.githubusercontent.com/lerianstudio/ring/main/install-ring.sh | bashWindows PowerShell:
irm https://raw.githubusercontent.com/lerianstudio/ring/main/install-ring.ps1 | iex -
Install from the Claude Code Plugin Marketplace (Recommended)
- Open Claude Code
- Go to Settings → Plugins
- Search for "ring"
- Click Install
-
Manual Installation
# Clone the marketplace repository git clone https://github.com/lerianstudio/ring.git ~/ring # Install Python dependencies (optional, but recommended) cd ~/ring pip install -r requirements.txtNote: Python dependencies are optional. The hooks will use fallback parsers if PyYAML is unavailable.
First Session
When you start a new Claude Code session with Ring installed, you'll see:
## Available Skills:
- using-ring (Check for skills BEFORE any task)
- test-driven-development (RED-GREEN-REFACTOR cycle)
- systematic-debugging (4-phase root cause analysis)
- verification-before-completion (Evidence before claims)
... and 30 more skills
🎯 Core Skills
The Big Four (Use These First!)
1. using-ring - Mandatory Skill Discovery
Before ANY action → Check skills
Before ANY tool → Check skills
Before ANY code → Check skills
2. test-driven-development - Test First, Always
RED → Write failing test → Watch it fail
GREEN → Minimal code → Watch it pass
REFACTOR → Clean up → Stay green
3. systematic-debugging - Find Root Cause
Phase 1: Investigate (gather ALL evidence)
Phase 2: Analyze patterns
Phase 3: Test hypothesis (one at a time)
Phase 4: Implement fix (with test)
4. verification-before-completion - Prove It Works
Run command → Paste output → Then claim
No "should work" → Only "does work" with proof
📚 All 46 Skills (Across 7 Plugins)
Core Skills (ring-default plugin - 20 skills)
Testing & Debugging (6):
test-driven-development- Write test first, watch fail, minimal codesystematic-debugging- 4-phase root cause investigationverification-before-completion- Evidence before claimstesting-anti-patterns- Common test pitfalls to avoidcondition-based-waiting- Replace timeouts with conditionsdefense-in-depth- Multi-layer validation
Collaboration & Planning (10):
brainstorming- Structured design refinementwriting-plans- Zero-context implementation plansexecuting-plans- Batch execution with checkpointsrequesting-code-review- Parallel 3-reviewer dispatch with severity-based handlingreceiving-code-review- Responding to feedbackdispatching-parallel-agents- Concurrent workflowssubagent-driven-development- Fast iteration with parallel reviewsusing-git-worktrees- Isolated developmentfinishing-a-development-branch- Merge/PR decisionsroot-cause-tracing- Backward bug tracking
Meta Skills (4):
using-ring- Mandatory skill discoverywriting-skills- TDD for documentationtesting-skills-with-subagents- Skill validationtesting-agents-with-subagents- Subagent-specific testing
Developer Skills (ring-dev-team plugin - 2 skills)
Code Development:
using-dev-team- Introduction to developer specialist agentswriting-code- Best practices for code implementation
Product Planning Skills (ring-pm-team plugin - 9 skills)
Pre-Development Workflow (9 gates, includes using-pm-team):
using-pm-team- Introduction to product planning workflow
pre-dev-prd-creation- Business requirements (WHAT/WHY)pre-dev-feature-map- Feature relationshipspre-dev-trd-creation- Technical architecture (HOW)pre-dev-api-design- Component contractspre-dev-data-model- Entity relationshipspre-dev-dependency-map- Technology selectionpre-dev-task-breakdown- Work incrementspre-dev-subtask-creation- Atomic units
FinOps & Regulatory Skills (ring-finops-team plugin - 6 skills)
Regulatory Templates (6):
using-finops-team- Introduction to FinOps team workflowregulatory-templates- Brazilian regulatory orchestration (BACEN, RFB)regulatory-templates-setup- Template selection initializationregulatory-templates-gate1- Compliance analysis and field mappingregulatory-templates-gate2- Field mapping validationregulatory-templates-gate3- Template file generation
Ralph Wiggum (ralph-wiggum plugin - 1 skill)
Iterative Development:
using-ralph-wiggum- Ralph Wiggum iterative loop technique guide
Technical Writing Skills (ring-tw-team plugin - 7 skills)
Documentation Creation:
using-tw-team- Introduction to technical writing specialistswriting-functional-docs- Patterns for guides, tutorials, conceptual docswriting-api-docs- API reference documentation patternsdocumentation-structure- Document hierarchy and organizationvoice-and-tone- Voice and tone guidelines (assertive, encouraging, human)documentation-review- Quality checklist and review processapi-field-descriptions- Field description patterns by type
Beads Integration (beads plugin - 1 skill)
Issue Tracking:
using-beads- Beads (bd) integration for dependency-aware issue tracking
🎮 Interactive Commands
Ring provides slash commands for common workflows:
/ring:brainstorm- Interactive design refinement using Socratic method/ring:write-plan- Create detailed implementation plan with bite-sized tasks/ring:execute-plan- Execute plan in batches with review checkpoints
Ralph Wiggum (Iterative AI Loops)
/ralph-wiggum:ralph-loop "PROMPT" --max-iterations N --completion-promise "TEXT"- Start autonomous iterative loop/ralph-wiggum:cancel-ralph- Cancel active Ralph loop/ralph-wiggum:help- Explain Ralph technique and examples
Technical Writing (Documentation)
/ring-tw-team:write-guide [topic]- Start writing a functional guide with voice/tone guidance/ring-tw-team:write-api [endpoint]- Start writing API reference documentation/ring-tw-team:review-docs [file]- Review existing documentation for quality
💡 Usage Examples
Building a Feature
User: "Add user authentication to the app"
Claude: I'm using the brainstorming skill to design this feature...
[Structured exploration of requirements]
Claude: I'm using test-driven-development to implement...
[RED-GREEN-REFACTOR cycle for each component]
Claude: I'm using verification-before-completion to confirm...
[Runs tests, shows actual output]
Fixing a Bug
User: "The app crashes when clicking submit"
Claude: I'm using systematic-debugging to investigate...
Phase 1: [Gathering evidence]
Phase 2: [Pattern analysis]
Phase 3: [Hypothesis testing]
Phase 4: [Implementing fix with test]
Planning a Project
User: "Plan an e-commerce platform"
Claude: I'll use the pre-dev workflow to plan this systematically...
Gate 1: PRD Creation [Business requirements]
Gate 2: Feature Map [Domain groupings]
Gate 3: TRD Creation [Architecture patterns]
... [Through all 8 gates]
Code Review (Parallel, 3x Faster!)
User: "Review my authentication implementation"
Claude: Dispatching all 3 reviewers in parallel...
[Launches code-reviewer, business-logic-reviewer, security-reviewer simultaneously]
Code reviewer: PASS. Clean architecture, good tests.
Business reviewer: FAIL. Missing password reset flow (HIGH severity).
Security reviewer: FAIL. JWT secret hardcoded (CRITICAL severity).
Aggregating issues by severity:
- CRITICAL: JWT secret hardcoded in auth.ts:42
- HIGH: Password reset flow missing from requirements
Dispatching fix subagent to address Critical/High issues...
[Fixes applied]
Re-running all 3 reviewers in parallel...
All reviewers: PASS. Ready for production.
Key benefits:
- 3x faster - All reviewers run simultaneously (not sequential)
- Comprehensive - Get all feedback at once, easier to prioritize
- Tech debt tracking - Low/Cosmetic issues tracked with TODO/FIXME comments in code
- Model-specific - All reviewers run on Opus for deep analysis
🏗️ Architecture
Monorepo Marketplace - Multiple specialized plugin collections:
ring/ # Monorepo root
├── .claude-plugin/
│ └── marketplace.json # Multi-plugin marketplace config (5 active plugins)
├── default/ # Core Ring plugin (ring-default)
│ ├── skills/ # 20 core skills
│ │ ├── skill-name/
│ │ │ └── SKILL.md # Skill definition with frontmatter
│ │ └── shared-patterns/ # Universal patterns (5 patterns)
│ ├── commands/ # 8 slash command definitions
│ ├── hooks/ # Session initialization
│ │ ├── hooks.json # Hook configuration
│ │ ├── session-start.sh # Loads skills at startup
│ │ └── generate-skills-ref.py # Auto-generates quick reference
│ ├── agents/ # 5 specialized agents
│ │ ├── code-reviewer.md # Foundation review (parallel)
│ │ ├── business-logic-reviewer.md # Correctness review (parallel)
│ │ ├── security-reviewer.md # Safety review (parallel)
│ │ ├── write-plan.md # Implementation planning
│ │ └── codebase-explorer.md # Deep architecture analysis (Opus)
│ ├── lib/ # Infrastructure utilities (9 scripts)
│ └── docs/ # Documentation
├── dev-team/ # Developer Agents plugin (ring-dev-team)
│ └── agents/ # 10 specialized developer agents
│ ├── backend-engineer.md # Language-agnostic backend specialist
│ ├── backend-engineer-golang.md # Go backend specialist
│ ├── backend-engineer-typescript.md # TypeScript/Node.js backend specialist
│ ├── backend-engineer-python.md # Python backend specialist
│ ├── devops-engineer.md # DevOps infrastructure
│ ├── frontend-engineer.md # React/Next.js specialist (JavaScript-first)
│ ├── frontend-engineer-typescript.md # TypeScript-first React/Next.js specialist
│ ├── frontend-designer.md # Visual design specialist
│ ├── qa-analyst.md # Quality assurance
│ └── sre.md # Site reliability engineer
├── finops-team/ # FinOps plugin (ring-finops-team)
│ ├── skills/ # 6 regulatory compliance skills
│ │ └── regulatory-templates*/ # Brazilian regulatory compliance
│ ├── agents/ # 2 FinOps agents
│ │ ├── finops-analyzer.md # FinOps analysis
│ │ └── finops-automation.md # FinOps automation
│ └── docs/
│ └── regulatory/ # Brazilian regulatory documentation
├── pm-team/ # Product Planning plugin (ring-pm-team)
│ └── skills/ # 8 pre-dev workflow skills
│ └── pre-dev-*/ # PRD, TRD, API, Data, Tasks
├── ralph-wiggum/ # Iterative AI loops plugin (ralph-wiggum)
│ ├── commands/ # 3 slash commands (ralph-loop, cancel-ralph, help)
│ ├── hooks/ # SessionStart and Stop hooks
│ ├── scripts/ # Setup utilities
│ └── skills/ # using-ralph-wiggum skill
├── tw-team/ # Technical Writing plugin (ring-tw-team)
│ ├── skills/ # 7 documentation skills
│ ├── agents/ # 3 technical writing agents
│ ├── commands/ # 3 slash commands
│ └── hooks/ # SessionStart hook
├── beads/ # Beads integration plugin (beads)
│ ├── skills/ # using-beads skill
│ └── hooks/ # SessionStart and Stop hooks
├── ops-team/ # Team-specific skills (reserved)
└── pmm-team/ # Team-specific skills (reserved)
🤝 Contributing
Adding a New Skill
For core Ring skills:
-
Create the skill directory
mkdir default/skills/your-skill-name -
Write SKILL.md with frontmatter
--- name: your-skill-name description: | Brief description of WHAT this skill does (the method/technique). 1-2 sentences maximum. trigger: | - Specific condition that mandates using this skill - Another trigger condition - Use quantifiable criteria when possible skip_when: | - When NOT to use this skill → alternative - Another exclusion condition sequence: after: [prerequisite-skill] # Skills that should come before before: [following-skill] # Skills that typically follow related: similar: [skill-that-seems-similar] # Differentiate from these complementary: [skill-that-pairs-well] # Use together with these --- # Skill content here...Schema fields explained:
name: Skill identifier (matches directory name)description: WHAT the skill does (method/technique)trigger: WHEN to use - specific, quantifiable conditionsskip_when: WHEN NOT to use - differentiates from similar skillssequence: Workflow ordering (optional)related: Similar/complementary skills for disambiguation (optional)
-
Update documentation
- Skills auto-load via
default/hooks/generate-skills-ref.py - Test with session start hook
- Skills auto-load via
-
Submit PR
git checkout -b feat/your-skill-name git add default/skills/your-skill-name git commit -m "feat(skills): add your-skill-name for X" gh pr create
For product/team-specific skills:
-
Create plugin structure
mkdir -p product-xyz/{skills,agents,commands,hooks,lib} -
Register in marketplace Edit
.claude-plugin/marketplace.json:{ "name": "ring-product-xyz", "description": "Product XYZ specific skills", "version": "0.1.0", "source": "./product-xyz", "homepage": "https://github.com/lerianstudio/ring/tree/product-xyz" } -
Follow core plugin structure
- Use same layout as
default/ - Create
product-xyz/hooks/hooks.jsonfor initialization - Add skills to
product-xyz/skills/
- Use same layout as
Skill Quality Standards
- Mandatory sections: When to use, How to use, Anti-patterns
- Include checklists: TodoWrite-compatible task lists
- Evidence-based: Require verification before claims
- Battle-tested: Based on real-world experience
- Clear triggers: Unambiguous "when to use" conditions
📖 Documentation
- Skills Quick Reference - Auto-generated at session start from skill frontmatter
- CLAUDE.md - Repository guide for Claude Code
- Design Documents - Implementation plans and architecture decisions
🎯 Philosophy
Ring embodies these principles:
- Skills are mandatory, not optional - If a skill applies, it MUST be used
- Evidence over assumptions - Prove it works, don't assume
- Process prevents problems - Following workflows prevents known failures
- Small steps, verified often - Incremental progress with continuous validation
- Learn from failure - Anti-patterns document what doesn't work
📊 Success Metrics
Teams using Ring report:
- 90% reduction in "works on my machine" issues
- 75% fewer bugs reaching production
- 60% faster debugging cycles
- 100% of code covered by tests (enforced by TDD)
🙏 Acknowledgments
Ring is built on decades of collective software engineering wisdom, incorporating patterns from:
- Extreme Programming (XP)
- Test-Driven Development (TDD)
- Domain-Driven Design (DDD)
- Agile methodologies
- DevOps practices
Special thanks to the Lerian Team for battle-testing these skills in production.
📄 License
MIT - See LICENSE file
🔗 Links
Remember: If a skill applies to your task, you MUST use it. This is not optional.