Behavioral skill for the architect role — defines architectural methodology, domain boundary, output format, and quality gates for software architecture work.
Orchestrates feature development from start to finish.
Behavioral skill for the implementer role — defines programming methodology, domain boundary, output format, and quality gates for production code implementation.
Behavioral skill for the reviewer role — defines code review methodology, domain boundary, output format, and quality gates for code quality enforcement.
Behavioral skill for the tester role — defines TDD methodology, domain boundary, output format, and quality gates for test-first development.
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.
A collection of Claude Code plugins for coding conventions and team-based development workflows.
Coding convention skills for JVM languages. These are non-user-invocable skills loaded automatically by agents when writing or reviewing code.
| Skill | Description |
|---|---|
groovy-coding-conventions | General Groovy programming principles and design conventions |
groovy-spock-coding-conventions | Spock test structuring, mocking, data-driven tests, and interaction verification |
java-coding-conventions | General Java programming principles and design conventions |
Team-based development workflows using coordinated agents.
| Skill | Description |
|---|---|
feature | Orchestrates feature development end-to-end. Validates the repo is clean, then launches the agent team. User-invocable. |
The feature skill spawns a four-agent team that follows a TDD workflow:
| Agent | Role |
|---|---|
architect | Lead teammate. Researches the codebase, plans interactively with the user, broadcasts requirements to the team. Loads architecture convention skills. Never writes code. |
tester | Owns the red phase. Translates the architect's requirements into failing Spock tests, gets them reviewed, then hands off to the implementer. |
implementer | Owns the green phase. Makes failing tests pass, then submits code for review. Loads coding convention skills. |
reviewer | Quality gate. Reviews test and implementation code against loaded conventions. Must approve before work proceeds. |
User Request
└─► architect (plans with user)
└─► tester (writes failing tests)
└─► reviewer (approves tests)
└─► implementer (makes tests green)
└─► reviewer (approves implementation)
Located in .claude/agents/, these are available outside the team workflow:
| Agent | Description |
|---|---|
spock-test-writer | Writes Spock unit tests with strict convention compliance. Loads groovy-coding-conventions and groovy-spock-coding-conventions skills. Iterates through implement → review → fix cycles until zero violations, then runs tests. |
npx claudepluginhub joke/claude-plugins --plugin workflowsJoke's personal coding conventions
Guides AI agents through disciplined coding practices. Language and build-system agnostic core with extensible language/build skills.
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Virtual development team: TDD, debugging, code review, backlog management, and proven workflow patterns
The AI engineering workflow framework for teams — full lifecycle from ticket to post-mortem with quality gates at every stage
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses