BeClaude

ring-tw-team

New
193Community RegistryGeneralby Presenter Name ยท MIT

Technical writing specialists for functional and API documentation. 3 specialized agents (functional-writer, api-writer, docs-reviewer) and 4 documentation skills covering voice/tone, structure, API field descriptions, and quality review. Enforces clear, consistent documentation standards.

Community PluginView Source

Overview

<p align="center"> <img src="assets/ring-banner.png" alt="Ring by Lerian" width="100%" /> </p>

๐Ÿ’ 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 4 active plugins, 71 skills, and 33 agents (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 across the entire software delivery value chain.

โœจ Why Ring?

Without Ring, AI assistants often:

  • โ€ขSkip tests and jump straight to implementation
  • โ€ขMake changes without understanding root causes
  • โ€ขClaim tasks are complete without verification
  • โ€ขForget to check for existing solutions
  • โ€ขRepeat known mistakes

Ring solves this by:

  • โ€ขEnforcing proven workflows - Test-driven development, systematic debugging, proper planning
  • โ€ขProviding 71 specialized skills (16 core + 33 dev-team + 18 product planning + 4 technical writing)
  • โ€ข33 specialized agents - 2 planning/analysis + 24 developer/reviewer + 4 product research + 3 technical writing
  • โ€ขAutomating skill discovery - Skills load automatically at session start
  • โ€ขPreventing common failures - Built-in anti-patterns and mandatory checklists

๐Ÿงญ Project Identity

Ring is Lerian-first, open-source-friendly. Design decisions prioritize the Lerian engineering team's daily needs while keeping the architecture clean and reusable for external adoption. This means:

  • โ€ขLerian-specific skills stay active โ€” Internal integrations and domain-specific workflows remain in the marketplace because the team uses them
  • โ€ขThe architecture is universal โ€” Skills, agents, and the plugin system work with any codebase or team
  • โ€ขArchival is usage-driven โ€” Skills are archived when they stop being used, not because they're "too specific"

๐Ÿค– Specialized Agents

Planning & Analysis Agents (default plugin):

  • โ€ขring:review-slicer - Review slicer (groups large multi-themed PRs into thematic slices for focused parallel review)
  • โ€ขring:codebase-explorer - Deep architecture analysis (deep-analysis, complements built-in Explore)
  • โ€ขUse ring:reviewing-code skill to orchestrate parallel review workflow

Developer Agents (dev-team plugin):

  • โ€ขring:backend-go - Go backend specialist for financial systems
  • โ€ขring:backend-ts - TypeScript/Node.js backend specialist (Express, NestJS, Fastify)
  • โ€ขring:bff-ts - BFF & React/Next.js frontend with Clean Architecture
  • โ€ขring:ui-designer - Visual design specialist
  • โ€ขring:frontend - Senior Frontend Engineer (React/Next.js)
  • โ€ขring:devops - DevOps and infrastructure specialist
  • โ€ขring:prompt-reviewer - Agent Quality Analyst
  • โ€ขring:qa - Backend QA specialist (unit, integration, load, chaos)
  • โ€ขring:qa-frontend - Frontend QA specialist (accessibility, visual, E2E, performance)
  • โ€ขring:sre - Observability and reliability specialist
  • โ€ขring:ui-engineer - UI component specialist (design systems, accessibility)
  • โ€ขring:helm - Helm chart specialist (chart structure, security, Lerian conventions)
  • โ€ขring:code-reviewer - Foundation review (architecture, code quality, design patterns)
  • โ€ขring:logic-reviewer - Correctness review (domain logic, requirements, edge cases)
  • โ€ขring:security-reviewer - Safety review (vulnerabilities, OWASP, authentication)
  • โ€ขring:test-reviewer - Test quality review (coverage, edge cases, assertions, test anti-patterns)
  • โ€ขring:nil-reviewer - Nil/null safety review (traces pointer risks, missing guards, panic paths)
  • โ€ขring:dead-code-reviewer - Dead code review (orphaned code detection, reachability analysis, dead dependency chains)
  • โ€ขring:commons-reviewer - lib-commons package usage review (lifecycle, tenancy, http, idempotency, security, database, messaging, outbox; reinvented-wheel opportunities)
  • โ€ขring:obs-reviewer - Conditional specialist for tracing, metrics, logging, runtime recovery, redaction, constants, and SafeGo implications
  • โ€ขring:systemplane-reviewer - Conditional specialist for runtime config, hot-reload knobs, admin config, tenant-scoped settings, and systemplane imports
  • โ€ขring:streaming-reviewer - Conditional specialist for business events, outbox, producers, broker publishing, CloudEvents, manifests, and catalogs
  • โ€ขring:tenancy-reviewer - Multi-tenant usage review (lib-commons/multitenancy patterns, tenant isolation, JWT tenantId propagation)
  • โ€ขring:perf-reviewer - Performance review (code hotspots, infra misconfigurations, Go/TypeScript/Python)

Standards Compliance: Refactor-capable dev-team agents produce a ## Standards Compliance output section with conditional requirement:

- Optional when invoked directly or via ring:running-dev-cycle

- MANDATORY when invoked from ring:planning-backend-refactor (triggered by **MODE: ANALYSIS ONLY** in prompt)

When mandatory, agents load Ring standards via WebFetch and produce comparison tables with:

- Current Pattern vs Expected Pattern

- Severity classification (Critical/High/Medium/Low)

- File locations and migration recommendations

See dev-team/docs/standards/*.md for standards source. Cross-references: CLAUDE.md (Standards Compliance section), dev-team/skills/planning-backend-refactor/SKILL.md

Product Research Agents (ring-pm-team plugin):

  • โ€ขring:repo-researcher - Repository structure and codebase analysis
  • โ€ขring:web-researcher - Industry best practices research
  • โ€ขring:docs-researcher - Framework documentation research
  • โ€ขring:product-designer - Product design and UX research

Technical Writing Agents (ring-tw-team plugin):

  • โ€ขring:guide-writer - Functional documentation (guides, tutorials, conceptual docs)
  • โ€ขring:api-writer - API reference documentation (endpoints, schemas, examples)
  • โ€ขring:docs-reviewer - Documentation quality review (voice, tone, structure, completeness)

_Plugin versions are managed in .claude-plugin/marketplace.json_

๐Ÿ“ฆ Archived Plugins

The following plugins have been archived and are not actively maintained. They remain available in .archive/ for reference:

PluginDescriptionStatus
pmm-teamProduct Marketing (GTM, positioning, competitive intel)Archived - functionality may be restored based on demand
finance-teamFinancial planning and analysisArchived - under evaluation
ops-teamOperations managementArchived - under evaluation

_To restore an archived plugin, move its folder from .archive/ to the root directory and register it in marketplace.json._

๐Ÿ–ฅ๏ธ Supported Platforms

Ring works across multiple AI development platforms:

PlatformNative manifestSymlink installerStatus
Claude Codeโœ… marketplace.jsonโœ… --claudeSource of truth
Codexโœ… .codex-plugin/โœ… --codex (built)Both paths work
OpenCodeโœ… .opencode/โœ… --opencode (built)Both paths work
Cursorโœ… .cursor-plugin/โŒ not in installerNative only
Factory AIโŒโœ… --factoryInstaller only

Two install mechanisms:

  • โ€ขNative manifest โ€” the harness installs Ring directly from this repo via its own package manager (opencode.json, Cursor plugin marketplace, Codex plugin manifest). No local build step, no manual symlink work. Best for end users and CI.
  • โ€ขSymlink installer (ring-install.sh) โ€” symlinks from your local harness config dir into a cloned Ring repo. For Codex/OpenCode, the installer builds a transformed tree at .ring-build/ first (namespace + frontmatter rewrites). Best for local development with hot-reload against the source tree.

See the `Native plugin install` and `Symlink installer` sub-sections below for usage.

๐Ÿš€ Quick Start

Native plugin install (per harness)

Each Ring plugin ships native manifests for Claude Code, Codex, Cursor, and OpenCode. The harness installs the plugin directly from this repo via its own package manager โ€” no transformation step, no local installer.

HarnessMechanismPer-plugin entry points
Claude Code.claude-plugin/marketplace.json (root)All 4 plugins enumerated in one marketplace file
Codex<plugin>/.codex-plugin/plugin.jsondefault ยท dev-team ยท pm-team ยท tw-team
Cursor<plugin>/.cursor-plugin/plugin.jsondefault ยท dev-team ยท pm-team ยท tw-team
OpenCode<plugin>/.opencode/ (INSTALL + JS plugin)default ยท dev-team ยท pm-team ยท tw-team

`ring-default` is the foundation plugin โ€” install it alongside any other Ring plugin since it provides the using-ring bootstrap that orients agent behavior. Example for OpenCode:

json
{
  "plugin": [
    "ring-default@git+https://github.com/lerianstudio/ring.git#main",
    "ring-dev-team@git+https://github.com/lerianstudio/ring.git#main"
  ]
}

Each harness's INSTALL.md (for OpenCode) or plugin.json (for Codex/Cursor) carries the exact install command for that platform.

Symlink installer (local dev)

ring-install.sh symlinks your harness's local config dir into this cloned Ring repo. For Codex and OpenCode, it first builds a transformed tree at .ring-build/ (namespace + frontmatter rewrites required by those tools).

Supported targets: Claude Code, Factory AI, OpenCode, Codex. Not supported by the installer: Cursor (use the native plugin install above).

bash
# Clone the repo
git clone https://github.com/lerianstudio/ring.git ~/ring
cd ~/ring

# Interactive menu (lets you pick targets)
bash ring-install.sh

# Or target specific harnesses without the prompt:
bash ring-install.sh --claude               # Claude Code (per-file symlinks)
bash ring-install.sh --factory              # Factory AI (per-file symlinks)
bash ring-install.sh --opencode             # OpenCode (builds .ring-build/opencode/ first)
bash ring-install.sh --codex                # Codex    (builds .ring-build/codex/ first)
bash ring-install.sh --all                  # All four supported targets
bash
bash ring-install.sh install --opencode --codex   # install symlinks for selected targets
bash ring-install.sh remove                        # remove all Ring symlinks
bash ring-install.sh build                         # rebuild .ring-build/{opencode,codex} only
bash ring-install.sh clean                         # remove .ring-build/ outputs
bash ring-install.sh doctor                        # verify install + build outputs
bash ring-install.sh all --all -y                  # clean + build + install for all targets, no prompt

Flags: --yes / -y (skip confirmation), --dry-run (preview without changes), --force (back up non-symlink collisions), --verbose.

Claude Code Plugin Marketplace

For Claude Code users, you can also install from the marketplace:

  • โ€ขOpen Claude Code
  • โ€ขGo to Settings โ†’ Plugins
  • โ€ขSearch for "ring"
  • โ€ขClick Install

Manual Installation (Claude Code only)

bash
# Clone the marketplace repository
git clone https://github.com/lerianstudio/ring.git ~/ring

# Skills auto-load at session start via hooks
# No additional configuration needed for Claude Code

Code Analysis Pipeline

The ring:reviewing-code pipeline uses Mithril, an external code analysis tool installed via go install. Mithril performs static analysis, AST extraction, call graph generation, and context compilation for AI-assisted code review.

Install via go install github.com/lerianstudio/mithril@latest. See the Mithril repository for full installation details and release notes.

First Session

When you start a new Claude Code session with Ring installed, you'll see:

code
## Available Skills:
- ring:using-ring (Check for skills BEFORE any task)
- ring:test-driven-development (RED-GREEN-REFACTOR cycle)
- ring:reviewing-code (9 defaults + conditional specialist dispatch)
- ring:exploring-codebases (Two-phase codebase exploration)
... and 73 more skills

๐ŸŽฏ Core Skills

Start Here

code
Before ANY action โ†’ Check skills
Before ANY tool โ†’ Check skills
Before ANY code โ†’ Check skills
code
RED โ†’ Write failing test โ†’ Watch it fail
GREEN โ†’ Minimal code โ†’ Watch it pass
REFACTOR โ†’ Clean up โ†’ Stay green

๐Ÿ“š All 71 Skills (Across 4 Plugins)

Core Skills (ring-default plugin - 16 skills)

Testing & Quality (2):

  • โ€ขring:test-driven-development - Write test first, watch fail, minimal code
  • โ€ขring:fixing-lint - Parallel lint fixing with agent dispatch

Collaboration & Planning (5):

  • โ€ขring:reviewing-code - Parallel 9 defaults + conditional specialist dispatch with severity-based handling
  • โ€ขring:creating-worktrees - Isolated development
  • โ€ขring:committing-changes - Smart commit organization with atomic grouping, conventional commits, and trailers
  • โ€ขring:writing-plans - Author phased implementation plans (phase โ†’ epic โ†’ task) from a spec; first phase detailed into dispatch-ready tasks, later phases epic-level for rolling-wave elaboration
  • โ€ขring:executing-plans - Rolling-wave execution of a phased plan: implement the detailed phase, checkpoint with the user, elaborate the next phase against the real codebase, repeat

Meta Skills (3):

  • โ€ขring:using-ring - Mandatory skill discovery
  • โ€ขring:writing-skills - TDD for documentation
  • โ€ขring:testing-skills-with-subagents - Skill validation

Integration (1):

  • โ€ขring:delegating-to-gandalf - Send tasks to Gandalf (AI team member) via webhook for Slack, Google Workspace, and Jira interactions

Session & Learning (4):

  • โ€ขring:exploring-codebases - Two-phase codebase exploration
  • โ€ขring:generating-release-guides - Generate Ops Update Guide from git diff analysis
  • โ€ขring:visualizing - Generate self-contained HTML pages to visually explain systems, code changes, and data
  • โ€ขring:creating-handoffs - Create handoff documents capturing session state for seamless context-clear and resume

Audit & Readiness (1):

  • โ€ขring:auditing-production-readiness - 44-dimension production readiness audit; runs explorers in batches of up to 10, appends incrementally to a single report; output: scored report (0-430, max 440 with multi-tenant) with severity ratings. See default/skills/auditing-production-readiness/SKILL.md for invocation and implementation details.

Developer Skills (ring-dev-team plugin - 33 skills)

Orchestration & Refactoring (7):

  • โ€ขring:using-dev-team - Introduction to developer specialist agents
  • โ€ขring:running-dev-cycle - Lean backend development cycle orchestrator driven by a rolling-wave phased plan (phases โ†’ epics E-X.Y โ†’ tasks T-X.Y.Z): Gate 0 implementation-owned TDD/coverage/docker-compose/runtime/delivery verification per task, Gate 8 review + Gate 9 validation per epic, phase boundary (Step 11.5) closes each phase and elaborates the next against the real codebase
  • โ€ขring:running-dev-cycle-frontend - Lean frontend development cycle orchestrator on the same rolling-wave phased plan (Gate 0 per task, Gate 7 review per epic, Gate 8 validation per task, phase boundary per phase)
  • โ€ขring:planning-backend-refactor - Backend/codebase standards analysis
  • โ€ขring:planning-frontend-refactor - Frontend standards analysis and task generation
  • โ€ขring:planning-codebase-simplification - Whole-codebase structural simplification sweep (hunts unjustified abstractions, adapters, shims; KILL/REVIEW/KEEP output; DELETE-by-default burden of proof for pre-public applications)
  • โ€ขring:managing-dev-cycle - Development cycle state management (phase/epic status reporting and cancellation)

Backend Gate Skills:

  • โ€ขring:implementing-tasks - Gate 0: TDD implementation
  • โ€ขring:adding-multi-tenancy - Multi-tenant adaptation (database-per-tenant isolation, integrated into Gate 0)
  • โ€ขring:hardening-dockerfiles - Docker image security audit for Docker Hub Health Score grade A
  • โ€ขring:creating-helm-charts - Helm chart creation and maintenance following Lerian conventions
  • โ€ขring:mapping-service-resources - Service/module/resource hierarchy scanner for dispatch layer
  • โ€ขring:implementing-readyz - Comprehensive readiness probes (/readyz) with per-dependency status and TLS validation
  • โ€ขring:instrumenting-streaming-events - Wire lib-streaming event emission from a validated instrumentation map

Testing & Validation:

  • โ€ขring:detecting-goroutine-leaks - Goroutine leak detection and regression testing
  • โ€ขring:load-testing-with-k6 - k6 load test generation following Lerian platform conventions
  • โ€ขring:validating-acceptance-criteria - Gate 9: User approval
  • โ€ขring:writing-dev-reports - Assertiveness scoring and metrics
  • โ€ขring:verifying-code - Atomic Go code verification with MERGE_READY/NEEDS_FIX verdict

Migration & Reference (6):

  • โ€ขring:using-lib-commons - Comprehensive reference for lib-commons v5.0.2 (Lerian's shared Go library with 30+ packages)
  • โ€ขring:using-runtime - Deep reference and 6-angle audit for lib-observability/runtime: SafeGo, panic recovery, observability trident, policy selection, framework integration. Catches naked goroutine launches that cause silent production failures.
  • โ€ขring:using-assert - Deep reference and 6-angle audit for lib-observability/assert: production runtime assertions with observability trident, full domain predicate catalog (double-entry, transaction state machine, financial validations), AssertionError unwrapping patterns. Converts financial invariants into production-enforced rules.
  • โ€ขring:migrating-to-lib-systemplane - Migrate Lerian Go services from .env/YAML config to systemplane (database-backed hot-reloadable config)
  • โ€ขring:generating-llms-txt - Generate or audit llms.txt files following llmstxt.org spec for AI-friendly repository entry points
  • โ€ขring:applying-licenses - Repository license management (Apache 2.0, Elastic v2, Proprietary)

Security (1):

  • โ€ขring:auditing-dependency-security - Supply-chain gate for dependency installations (validates identity, vulnerabilities, suspicious signals)

Frontend Quality Skills (1):

  • โ€ขring:checking-frontend-quality - Frontend quality checks in modes accessibility (axe-core/WCAG), visual (snapshots/viewports), e2e (Playwright 3-browser), performance (Lighthouse/Core Web Vitals), or all; dispatches ring:qa-frontend

Frontend and backend dev-cycle workflows both use ring:reviewing-code (core plugin) as the review gate.

Product Planning Skills (ring-pm-team plugin - 18 skills)

Pre-Development Workflow (includes ring:using-pm-team + 9 gates):

  • โ€ขring:using-pm-team - Introduction to product planning workflow
  1. ring:researching-features - Research phase (parallel agents)
  2. ring:writing-prds - Business requirements (WHAT/WHY)
  3. ring:mapping-feature-relationships - Feature relationships
  4. ring:writing-trds - Technical architecture (HOW)
  5. ring:designing-api-contracts - Component contracts
  6. ring:designing-data-model - Entity relationships
  7. ring:pinning-dependency-versions - Technology selection
  8. ring:decomposing-phases-and-epics - Phased plan: phases + epics, rolling wave
  9. ring:detailing-tasks - Phase 1 task detailing: dispatch-ready tasks, no code

Workflow Orchestrators:

  • โ€ขring:planning-small-features - 5-gate orchestrator for small features (<2 days)
  • โ€ขring:planning-large-features - 10-gate orchestrator for large features (>=2 days)

Additional Planning Skills:

  • โ€ขring:validating-ux-completeness - Gate 1.5/2.5: Design validation for UI features
  • โ€ขring:planning-delivery - Gate 4 (Small) / Gate 9 (Large): Delivery roadmap and timeline
  • โ€ขring:tracking-delivery - Delivery progress tracking against roadmap
  • โ€ขring:reconciling-predev-docs - Deep cross-reference review of pre-dev documentation artifacts

Technical Writing Skills (ring-tw-team plugin - 4 skills)

Documentation Creation:

  • โ€ขring:using-tw-team - Introduction to technical writing specialists
  • โ€ขring:structuring-documentation - Document hierarchy and organization
  • โ€ขring:applying-voice-and-tone - Voice and tone guidelines (assertive, encouraging, human)
  • โ€ขring:reviewing-docs - Quality checklist and review process

๐Ÿ’ก Usage Examples

Building a Feature

code
User: "Add user authentication to the app"
Claude: I'm using ring:planning-small-features to scope this feature...
        [Pre-dev workflow: PRD, TRD, tasks]
Claude: I'm using ring:test-driven-development to implement...
        [RED-GREEN-REFACTOR cycle for each component]
Claude: I'm using ring:reviewing-code to validate...
        [9 defaults + conditional specialist parallel dispatch]

Fixing a Bug

code
User: "The app crashes when clicking submit"
Claude: Investigating the crash:
        Phase 1: [Gathering evidence]
        Phase 2: [Pattern analysis]
        Phase 3: [Hypothesis testing]
        Phase 4: [Implementing fix with test]

Planning a Project

code
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 10 gates]

Code Review (Parallel, 9 Defaults + Conditional Specialists)

code
User: "Review my authentication implementation"
Claude: Dispatching all 9 default reviewers plus triggered conditional specialists in parallel...
        [Launches ring:code-reviewer, ring:logic-reviewer, ring:security-reviewer,
         ring:test-reviewer, ring:nil-reviewer,
         ring:dead-code-reviewer, ring:perf-reviewer, ring:tenancy-reviewer,
         ring:commons-reviewer simultaneously]
        Conditional specialists trigger only when the diff touches their stack:
        lib-observability, lib-systemplane, or lib-streaming.

        Code reviewer: PASS. Clean architecture, good tests.
        Business reviewer: FAIL. Missing password reset flow (HIGH severity).
        Security reviewer: FAIL. JWT secret hardcoded (CRITICAL severity).
        Test reviewer: PASS. Good coverage, assertions well-structured.
        Nil-safety reviewer: PASS. No unguarded nil dereferences found.
        Performance reviewer: PASS. No hotspots or goroutine leaks found.
        Multi-tenant reviewer: PASS. No multi-tenant code in scope.
        lib-commons reviewer: PASS. Correct shared-library usage, no reinvented wheels detected.

        Aggregating issues by severity:
        - CRITICAL: JWT secret hardcoded in auth.ts:42
        - HIGH: Password reset flow missing from requirements

        Review report complete. No files changed by reviewers.
        Fixes require a separate implementation step, then a new review run.

Key benefits:

  • โ€ขAll reviewers run simultaneously (not sequential)
  • โ€ขComprehensive - Get all feedback at once, easier to prioritize
  • โ€ขReport-only boundary - Reviewers report findings; remediation is a separate step
  • โ€ขSpecialized lanes - Each reviewer owns a clear domain to avoid duplicate slop

๐Ÿ—๏ธ Architecture

Monorepo Marketplace - Multiple specialized plugin collections:

code
ring/                                  # Monorepo root
โ”œโ”€โ”€ .claude-plugin/
โ”‚   โ””โ”€โ”€ marketplace.json              # Multi-plugin marketplace config (4 active plugins)
โ”œโ”€โ”€ default/                          # Core Ring plugin (ring-default)
โ”‚   โ”œโ”€โ”€ skills/                       # 16 core skills
โ”‚   โ”‚   โ”œโ”€โ”€ skill-name/
โ”‚   โ”‚   โ”‚   โ””โ”€โ”€ SKILL.md             # Skill definition with frontmatter
โ”‚   โ”‚   โ””โ”€โ”€ shared-patterns/         # Universal patterns (15 patterns)
โ”‚   โ”œโ”€โ”€ hooks/                       # Session initialization
โ”‚   โ”‚   โ”œโ”€โ”€ hooks.json              # Hook configuration
โ”‚   โ”‚   โ”œโ”€โ”€ session-start.sh        # Loads skills at startup
โ”‚   โ”‚   โ””โ”€โ”€ generate-skills-ref.py  # Auto-generates quick reference
โ”‚   โ”œโ”€โ”€ agents/                      # 2 planning/analysis agents
โ”‚   โ”‚   โ”œโ”€โ”€ review-slicer.md             # Review slicing for large PRs (`ring:review-slicer`)
โ”‚   โ”‚   โ””โ”€โ”€ codebase-explorer.md         # Deep architecture analysis (`ring:codebase-explorer`)
โ”‚   โ””โ”€โ”€ docs/                       # Documentation
โ”œโ”€โ”€ dev-team/                      # Developer Agents plugin (ring-dev-team) - 33 skills, 24 agents
โ”‚   โ””โ”€โ”€ agents/                      # 24 specialized developer/reviewer agents
โ”‚       โ”œโ”€โ”€ backend-go.md       # Go backend specialist (`ring:backend-go`)
โ”‚       โ”œโ”€โ”€ backend-ts.md   # TypeScript/Node.js backend specialist (`ring:backend-ts`)
โ”‚       โ”œโ”€โ”€ bff-ts.md # BFF & React/Next.js specialist (`ring:bff-ts`)
โ”‚       โ”œโ”€โ”€ devops.md              # DevOps and infrastructure specialist (`ring:devops`)
โ”‚       โ”œโ”€โ”€ ui-designer.md             # Visual design specialist (`ring:ui-designer`)
โ”‚       โ”œโ”€โ”€ frontend.md             # Frontend engineer (`ring:frontend`)
โ”‚       โ”œโ”€โ”€ helm.md                 # Helm chart specialist (`ring:helm`)
โ”‚       โ”œโ”€โ”€ code-reviewer.md                 # Foundation review (`ring:code-reviewer`)
โ”‚       โ”œโ”€โ”€ logic-reviewer.md       # Correctness review (`ring:logic-reviewer`)
โ”‚       โ”œโ”€โ”€ security-reviewer.md             # Safety review (`ring:security-reviewer`)
โ”‚       โ”œโ”€โ”€ test-reviewer.md                 # Test quality review (`ring:test-reviewer`)
โ”‚       โ”œโ”€โ”€ nil-reviewer.md           # Nil/null safety review (`ring:nil-reviewer`)
โ”‚       โ”œโ”€โ”€ dead-code-reviewer.md            # Dead code analysis (`ring:dead-code-reviewer`)
โ”‚       โ”œโ”€โ”€ commons-reviewer.md          # lib-commons usage review (`ring:commons-reviewer`)
โ”‚       โ”œโ”€โ”€ obs-reviewer.md    # Conditional observability review (`ring:obs-reviewer`)
โ”‚       โ”œโ”€โ”€ systemplane-reviewer.md      # Conditional runtime-config review (`ring:systemplane-reviewer`)
โ”‚       โ”œโ”€โ”€ streaming-reviewer.md        # Conditional event producer review (`ring:streaming-reviewer`)
โ”‚       โ”œโ”€โ”€ tenancy-reviewer.md         # Multi-tenant usage review (`ring:tenancy-reviewer`)
โ”‚       โ”œโ”€โ”€ perf-reviewer.md          # Performance review (`ring:perf-reviewer`)
โ”‚       โ”œโ”€โ”€ prompt-reviewer.md       # Agent quality reviewer (`ring:prompt-reviewer`)
โ”‚       โ”œโ”€โ”€ qa.md                    # Backend QA specialist (`ring:qa`)
โ”‚       โ”œโ”€โ”€ qa-frontend.md           # Frontend QA specialist (`ring:qa-frontend`)
โ”‚       โ”œโ”€โ”€ sre.md                           # Observability and reliability specialist (`ring:sre`)
โ”‚       โ””โ”€โ”€ ui-engineer.md                   # UI component specialist (`ring:ui-engineer`)
โ”œโ”€โ”€ pm-team/                    # Product Planning plugin (ring-pm-team)
โ”‚   โ””โ”€โ”€ skills/                      # 18 product planning skills
โ”‚       โ”œโ”€โ”€ writing-prds/          # PRD authoring
โ”‚       โ”œโ”€โ”€ writing-trds/          # TRD authoring
โ”‚       โ”œโ”€โ”€ designing-api-contracts/ # API contract design
โ”‚       โ”œโ”€โ”€ designing-data-model/   # Data model design
โ”‚       โ””โ”€โ”€ detailing-tasks/        # Task detailing
โ””โ”€โ”€ tw-team/                         # Technical Writing plugin (ring-tw-team)
    โ”œโ”€โ”€ skills/                      # 4 documentation skills
    โ”œโ”€โ”€ agents/                      # 3 technical writing agents
    โ””โ”€โ”€ hooks/                       # SessionStart hook

๐Ÿค Contributing

Adding a New Skill

For core Ring skills:

  1. Create the skill directory

``bash mkdir default/skills/your-skill-name ``

  1. Write SKILL.md with frontmatter

```yaml --- name: ring:your-skill-name description: Single paragraph (โ‰ค500 chars target, 1,536 cap). States WHAT the skill does, WHEN to invoke, and WHEN to skip. ---

# Your Skill Name

## When to use - Specific condition that mandates this skill - Another trigger condition

## Skip when - When NOT to use โ†’ alternative skill - Another exclusion ```

Schema fields:

- Required: name (must use ring: prefix), description - Optional: argument-hint, allowed-tools, model, disable-model-invocation, user-invocable, paths - Trigger / skip / sequence / related content lives in body H2 sections (## When to use, ## Skip when, ## Sequence, ## Related). See docs/FRONTMATTER_SCHEMA.md for the canonical schema.

  1. Update documentation

- Skills auto-load via default/hooks/generate-skills-ref.py - Test with session start hook

  1. Submit PR

``bash 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:

  1. Create plugin structure

``bash mkdir -p product-xyz/{skills,agents,hooks,lib} ``

  1. Register in marketplace

Edit .claude-plugin/marketplace.json:

``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" } ``

  1. Follow core plugin structure

- Use same layout as default/ - Create product-xyz/hooks/hooks.json for initialization - Add skills to product-xyz/skills/

Skill Quality Standards

  • โ€ขMandatory sections: When to use, How to use, Anti-patterns
  • โ€ขInclude checklists: TodoWrite-compatible task lists
  • โ€ขEvidence-based: Require verification before claims
  • โ€ขBattle-tested: Based on real-world experience
  • โ€ขClear triggers: Unambiguous "when to use" conditions

๐Ÿ“– Documentation

  • โ€ขSkills Quick Reference - Auto-generated at session start from skill frontmatter
  • โ€ขCLAUDE.md - Repository guide for Claude Code
  • โ€ขMANUAL.md - Quick reference for all skills, agents, and workflows
  • โ€ขARCHITECTURE.md - Architecture diagrams and component relationships
  • โ€ขInstaller - Multi-platform installation and migration

๐ŸŽฏ Philosophy

Ring embodies these principles:

  1. Skills are mandatory, not optional - If a skill applies, it MUST be used
  2. Evidence over assumptions - Prove it works, don't assume
  3. Process prevents problems - Following workflows prevents known failures
  4. Small steps, verified often - Incremental progress with continuous validation
  5. Learn from failure - Anti-patterns document what doesn't work

๐Ÿ“Š Success Metrics

Teams using Ring report:

  • โ€ข90% reduction in "works on my machine" issues
  • โ€ข75% fewer bugs reaching production
  • โ€ข60% faster debugging cycles
  • โ€ข100% of code covered by tests (enforced by TDD)

๐Ÿ™ Acknowledgments

Ring is built on decades of collective software engineering wisdom, incorporating patterns from:

  • โ€ขExtreme Programming (XP)
  • โ€ขTest-Driven Development (TDD)
  • โ€ขDomain-Driven Design (DDD)
  • โ€ขAgile methodologies
  • โ€ขDevOps practices

Special thanks to the Lerian Team for battle-testing these skills in production.

๐Ÿ“„ License

MIT - See LICENSE file

๐Ÿ”— Links


Remember: If a skill applies to your task, you MUST use it. This is not optional.

Install & Usage

1
Create the skills directory
mkdir -p .claude/skills
2
Download the skill file
mkdir -p .claude/skills && curl -o .claude/skills/ring-tw-team.md https://raw.githubusercontent.com/lerianstudio/ring/main/tw-team/SKILL.md
3
Invoke in Claude Code
/ring-tw-team
View source on GitHub
code-reviewdocumentationapiagenttechnical-writingapi-docsguidestutorials

Frequently Asked Questions

What is ring-tw-team?

Technical writing specialists for functional and API documentation. 3 specialized agents (functional-writer, api-writer, docs-reviewer) and 4 documentation skills covering voice/tone, structure, API field descriptions, and quality review. Enforces clear, consistent documentation standards.

How to install ring-tw-team?

To install ring-tw-team, create the .claude/skills directory in your project, then run the curl command to download the skill file. Once installed, invoke it in Claude Code with /ring-tw-team.

What is ring-tw-team best for?

ring-tw-team is a community categorized under General. It is designed for: code-review, documentation, api, agent, technical-writing, api-docs, guides, tutorials. Created by Presenter Name.