Development plugins

Build and maintain dotCMS sites — content types, pages, templates, containers, VTL, and headless Next.js.

3 skills · 1 MCP server

Kilo-specific Architect-side skills: kilo-mcp-orchestrator, kilo-mcp-metrics-analyst, kilo-mcp-conflict-resolver, plus the kilo-mcp-orchestrator-agent subagent. Install this if you're the orchestrating AI delegating to Kilo via MCP. The MCP server itself (server.py) is registered separately - see README.md.

3 skills · 1 agent

Implements features following Specification-Driven Development

2 skills · 2 agents

Comprehensive 7-phase feature development workflow with specialized agents for codebase exploration, architecture design, and quality review.

1 command · 3 agents

Guided feature-development workflow (code-explorer, code-architect, code-reviewer agents). Vendored from anthropics/claude-plugins-official and pinned for review.

1 command · 3 agents

Prompt rhetoric coach — optimize prompts before dispatching subagents

1 skill · 1 command · 1 MCP server · hooks

Plans and lands work that spans several pull requests as ordered stacks, with a PR size gate and a stack overlap check

4 skills

Playwright MCP + agents pour les tests E2E automatises

3 agents · 1 MCP server

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

LocalStack Community Edition expertise with MCP server: local AWS development, docker-compose setup, cdklocal/awslocal tooling, init hooks, and 40 MCP tools for S3/SQS/SNS/Lambda/DynamoDB

1 skill · 2 commands · 1 MCP server

Git workflow: grouped conventional commits with QA and hook compliance, template-driven pull requests, merged-branch purge across local and remote, a pull request driven to green through reviewer threads and checks, and a hook that redirects a second PR against the default branch to a stack

4 skills

Refactoring and debugging agents for code cleaning and bug fixing

2 commands · 2 agents

Create or expand formal design specifications for an app, package, or codebase — numbered, layered, cross-linked markdown that defines what exists in the current branch. Includes development guidelines and design guidelines with greenfield discovery and existing-project adoption. Head of the spec-creator → spec-planner → spec-builder pipeline; its specs feed spec-planner.

4 skills

Python-specific tools: 7 agents, 2 commands, 1 skill for Python code review, testing, and type checking

2 skills · 2 commands

Runs a budget-aware Agent Health audit for Codex, Claude Code, agent instructions, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.

1 skill · 3 agents

Runs a budget-aware Agent Health audit for Codex, Claude Code, agent instructions, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.

1 skill · 3 agents

Runs a budget-aware Agent Health audit for Codex, Claude Code, agent instructions, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.

1 skill · 3 agents

Runs a budget-aware Agent Health audit for Codex, Claude Code, agent instructions, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.

1 skill · 3 agents

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.

3 commands · hooks

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

3 commands · hooks

Your ChatGPT/Codex and Grok subscription models in Claude Code's /model picker. A local gateway routes claude-gpt-* models to OpenAI's Codex backend, claude-grok-* models to Grok, and everything else to api.anthropic.com, so you switch between Claude, GPT-5.x, and Grok mid-session like any other model. No API keys.

3 skills · hooks

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

3 commands · hooks

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

3 commands · hooks

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

3 commands · hooks

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents