By futuregerald
Portable skills, agents, and commands for Claude Code and other AI IDEs - includes a CLI installer for Cursor, Copilot, OpenCode, and VS Code
Import a Claude Code configuration archive (created by `/config:export`) onto this machine.
Export the Claude Code configuration from `~/.claude/` into a portable archive that can be imported on another machine.
Initialize a CLAUDE.md file for the current project, customized for the detected framework/language
Find and clean up stale git worktrees whose branches have been merged or are idle.
Create a GitHub issue for this project.
Use this subagent for systematic debugging of any technical issues.
Use this subagent when implementing tasks from a plan.
Performs security-focused code audit using OWASP Top 10 checklist. Use for security-sensitive code changes (auth, payments, user data, API endpoints, file uploads).
Use this subagent to verify an implementation matches its specification.
Reviews code quality for correctness, architecture, defensive coding, and testing. Use after spec compliance is verified.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when writing or modifying any Ruby code in cobalt repos. Enforces structured logging via SemanticLogger + Datadog so logs are queryable, dashboardable, and debuggable. Triggers on new interactors, jobs, services, controllers, error handling, and any business logic that should be observable.
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Uses power tools
Uses Bash, Write, or Edit tools
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 claimnpx claudepluginhub futuregerald/futuregerald-claude-pluginBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that adds a curated library of AI coding skills and agents, a cross-platform CLI installer, and an optional GitHub workflow integration with project management.
This repository works in two ways:
--plugin-dir. Provides slash commands, skills, and agents directly inside Claude Code sessions.skill-installer) -- Installs skills, agents, and commands for Claude Code, GitHub Copilot, Cursor, OpenCode, and VS Code.A CLAUDE.md file sits at the root of your project and tells Claude Code how to work in that codebase. It defines:
src/, lib/, tests/, etc.)go test ./...), typecheck (npx tsc --noEmit), and buildThe plugin auto-detects your project type (Go, Node.js/React/Next.js/AdonisJS/Svelte/Express, Rust, Python, Ruby, PHP) and generates a CLAUDE.md with real values filled in — no manual editing of {{placeholders}} required.
Generate one with:
/init-claude-md my-project-name
Or via the CLI:
skill-installer --mode config-only --target claude --yes
Skills are markdown-based instruction sets that give Claude specialized knowledge and workflows. When invoked, Claude follows the skill's process exactly. The plugin includes 48 skills covering:
Skills are invoked by name in Claude Code:
/futuregerald-claude-plugin:systematic-debugging
/futuregerald-claude-plugin:test-driven-development
/futuregerald-claude-plugin:brainstorming
Agents are dispatched via the Task tool to handle focused work with fresh context. The plugin includes 9 agents: code quality reviewer, code simplifier (with Staff Engineer review), codebase searcher, context finder (index/memory-aware read-only search), debugger, implementer, security reviewer, spec reviewer, and SQL performance reviewer.
The plugin defines a 10-phase development lifecycle in the generated CLAUDE.md:
1. RECEIVE Understand task, create todo list
2. PLAN Write implementation plan
3. REVIEW Staff Engineer sub-agent reviews the plan
4. IMPLEMENT Write code following TDD
5. TEST Run tests and type checking
6. SIMPLIFY Code-simplifier agent analyzes for improvements
7. CODE REVIEW Code-reviewer sub-agent reviews changes
8. SQL REVIEW Staff Engineer audits queries for performance, security, defensive coding
9. COMMIT Commit to feature branch
10. PUSH + PR Push and create PR (if gh available)
11. VERIFY CI Check CI passes; auto-merge when green
Each phase has a gate — the workflow doesn't advance until the gate passes. This works entirely locally. For teams using GitHub, an optional beta workflow adds issue tracking, worktrees, and autonomous PR review (see GitHub Workflow below).
Comprehensive skills library for Claude Code: planning, design, TDD, debugging, collaboration patterns, and proven techniques
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
A curated set of skills for each stage of development — propose, spec, design, plan, implement, ship.
Universal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
Harness for Claude Code — skills, /harness:* slash commands, persona subagents, lifecycle hooks, and MCP tools without per-repo `harness setup`. Sibling plugins exist for Cursor, Gemini CLI, and Codex.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use