Skills for working with Claude Code: creating skills and orchestrating task agents
Use this skill when creating custom Claude Code subagents, designing agent configurations, deciding between agent scopes (user vs project), configuring tool restrictions, or setting up lifecycle hooks. Helps design focused agents with appropriate capabilities.
Use this skill when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions or structure, or converting Claude Code sub-agents to skills. This includes designing skill workflows, writing SKILL.md files, organizing supporting files with intention-revealing names, and leveraging CLI tools and Node.js scripting.
Use this skill when launching Task agents, batch processing multiple files, delegating work to sub-agents, or running parallel operations. Provides XML prompt structure, agent type selection, and coordination patterns.
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 marketplace of skill plugins for coding agents using Claude Code CLI.
Practical skills for coding agents: React/Next.js optimization and safe Vitest execution.
| Skill | Description |
|---|---|
| developing-react-apps | 47 performance optimization rules for React and Next.js applications covering async patterns, bundle optimization, server/client rendering, re-render prevention, and more |
| running-vitest-safely | Safe Vitest test execution with proper flags to prevent hung processes, manage watch mode, set timeouts, and ensure proper cleanup |
Skills for working with Claude Code: creating skills, creating custom agents, and orchestrating task agents.
| Skill | Description |
|---|---|
| creating-agents | Create custom Claude Code subagents with appropriate scopes, tool restrictions, and lifecycle hooks for specialized domain experts |
| creating-skills | Create new Claude Code skills, edit existing skills, or convert sub-agents to skills. Includes guidance on SKILL.md structure, naming conventions, and best practices |
| orchestrating-task-agents | Best practices for delegating work to Task agents including XML prompt structure, agent type selection, parallel/sequential coordination, and skill invocation patterns |
Adversarial debate for code reviews and implementation planning using specialized multi-agent teams.
| Skill | Description |
|---|---|
| debating-code-reviews | Orchestrate a team of 4 specialized reviewers (Tracer, Architect, Breaker, Prosecutor) who independently analyze code, then debate each other's findings to catch more bugs |
| debating-implementation-plans | Orchestrate a team of 4 planning specialists (Scout, Planner, Critic, Prosecutor) who independently analyze a task, then debate to produce a validated implementation plan |
Add the marketplace to Claude Code:
/plugin marketplace add adbutterfield/coding-agent-plugins
Then install the plugins you want:
/plugin install coding-skills@coding-agent-plugins
/plugin install meta-skills@coding-agent-plugins
/plugin install debate-skills@coding-agent-plugins
Or install all:
/plugin install coding-skills@coding-agent-plugins meta-skills@coding-agent-plugins debate-skills@coding-agent-plugins
The developing-react-apps skill was initially based on react-best-practices from Vercel Labs. It has since been revised to follow official Claude Code skill authoring best practices and the Agent Skills Specification, along with personal experience crafting skills that agents can effectively use.
MIT
npx claudepluginhub adbutterfield/coding-agent-plugins --plugin meta-skillsAdversarial debate skills for coding agents: multi-persona code review debates and pre-implementation planning debates
Practical skills for coding agents: React/Next.js optimization and safe Vitest execution
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Multi-agent collaboration plugin for Claude Code. Spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any problem that benefits from diverse solutions. Evaluate by metric or LLM judge, merge the winner. 7 slash commands, agent templates, git DAG orchestration, message board coordination.
Agent Skills for improving SKILL.md files: mine repeated workflows from history, personalize and audit existing skills, or generalize personal skills for publication.
Create and validate production-grade agent skills with 100-point marketplace grading
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
Professional skill creation with TDD workflow. Features dual-mode (fast/full), behavioral validation, and automated quality gates for 9.0/10+ scores.