By dmedina-dev
Plugin development toolkit: 7 skills for creating Claude Code plugins, agents, commands, hooks, and MCP integrations. Curated from anthropics/claude-code.
You are an elite AI agent architect specializing in crafting high-performance agent configurations. Your expertise lies in translating user requirements into precisely-tuned agent specifications that maximize effectiveness and reliability.
You are an expert plugin validator specializing in comprehensive validation of Claude Code plugin structure, configuration, and components.
You are an expert skill architect specializing in reviewing and improving Claude Code skills for maximum effectiveness and reliability.
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
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.
Personal plugin marketplace for Claude Code. Curated collection of independent plugins — install all or pick what you need.
# Add marketplace (once per machine)
/plugin marketplace add dmedina-dev/dev-forge
# Install all working plugins at once
/plugin install forge-init
/forge-init:install-all
# Or install individually
/plugin install forge-keeper # context maintenance (recommended always-on)
/plugin install forge-superpowers # TDD, debugging, collaboration patterns
/plugin install forge-extended-dev # discovery → design → deep review → PR review
/plugin install forge-brainstorming # teammate-driven full lifecycle (requires forge-superpowers)
/plugin install forge-security # security reminder hooks
/plugin install forge-commit # commit/PR commands
/plugin install forge-hookify # custom hook rules engine
/plugin install forge-ralph # persistent loop technique
/plugin install forge-frontend-design # distinctive UI/UX design
/plugin install forge-channels-telegram # Telegram channel bridge (requires Bun)
Always-on plugins for daily development.
| Plugin | Purpose | Commands |
|---|---|---|
| forge-keeper | Context maintenance + PreCompact hook | /sync, /status, /recall, /segment-doc |
forge-keeper commands:
/sync — analyze changes, propose CLAUDE.md + rules + exemplars updates/status — context health report with drift detection/recall — search session log for past decisions/segment-doc — split monolithic .md into focused pieces for better context loading| Plugin | Purpose | Commands |
|---|---|---|
| forge-superpowers | TDD, debugging, parallel agents, code review, worktrees, plans | Skills-based (auto-triggered) |
| forge-extended-dev | 4-phase development workflow (requires forge-superpowers) | /feature-dev, /deep-review, /pr-review |
| forge-brainstorming | Teammate-driven full lifecycle with 5 persistent agents (requires forge-superpowers) | /brainstorming |
| Plugin | Purpose | Commands |
|---|---|---|
| forge-commit | Git commit and PR workflow | /commit, /commit-push-pr, /clean-gone, /release |
| forge-security | Security reminder hooks (XSS, injection, eval, etc.) | Passive — hooks on Edit/Write |
| forge-hookify | Custom hook rules engine with .local.md rules | /hookify, /hookify-list, /hookify-configure, /hookify-help |
| forge-ralph | Persistent loop: Claude keeps working across stop events | /ralph-loop, /cancel-ralph, /ralph-help |
| forge-frontend-design | Distinctive, production-grade UI/UX design | Skill-based (auto-triggered) |
| forge-ui-expert | UI/UX design intelligence: 67 styles, 96 palettes, 57 font pairings, 13 stacks | Skill-based (auto-triggered) |
| forge-profiles | Plugin profile manager — switch plugins + MCP servers per work mode | /profile-create, /profile-list, /profile-change |
| Plugin | Purpose | Commands |
|---|---|---|
| forge-channels-telegram | Telegram bridge — push messages into running session, reply from Claude | Skills: telegram:configure, telegram:access (auto-triggered) |
Install when needed, uninstall after. Don't consume context when not in use.
| Plugin | Purpose | When to install |
|---|---|---|
| forge-init | Project bootstrapper + install-all + AGENTS.md generation | New project: /forge-init:init then /forge-init:install-all then uninstall |
| forge-plugin-dev | Plugin development toolkit (7 skills, 3 agents) | Developing plugins: /create-plugin then uninstall |
| forge-context-mcp | MCP server setup guide (Context7, Serena, XRAY) | Setting up codebase intelligence: configure servers then uninstall |
claude --plugin-dir plugins/<name>docs/dependencies.mdCurated plugins retain their original authorship. No claim of original authorship is made for curated content.
Original author: Jesse Vincent (@obra)
| Plugin | Upstream | Version |
|---|---|---|
| forge-superpowers | superpowers | v5.0.6 |
npx claudepluginhub dmedina-dev/dev-forge --plugin forge-plugin-devGit workflow commands: /commit (smart commit with style-matching), /commit-push-pr (branch → commit → push → PR), /clean_gone (remove stale branches), /release (bump changed plugins, tag, push).
Exports a dev-forge marketplace into a new standalone repository. Interview-driven: select plugins, apply customizations, generate complete marketplace structure. Designed to be uninstalled after use.
Create custom hooks from natural language to prevent unwanted behaviors. Regex-based rules in .local.md files, no coding or restart required.
Security reminder hook: warns about potential security issues (command injection, XSS, eval, pickle, etc.) when editing files. Passive, low overhead.
Keeps CLAUDE.md, project docs and memories in sync after development sessions. Context-aware semantic detection plus explicit /sync command for human-driven updates. Safety-net git-based hook at relaxed thresholds.
Complete plugin development toolkit for creating, refactoring, and validating Claude Code plugins and agents. Use when creating new plugins/skills/agents, refactoring existing plugins/skills, validating frontmatter, or restructuring plugin components. Includes specialized agents for assessment, planning, execution, and validation workflows.
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Claude Code 插件開發工具包,提供七個專業技能、三個代理和完整的工作流程命令,用於構建高品質插件
High-intelligence Claude Code copilot with deep code reasoning, evidence-driven planning, orchestration-first execution, model routing, context budgeting, CI/CD integration, enterprise security, plugin development, prompt engineering, performance profiling, agent teams, channels (event-driven autonomy with CI webhook, mobile approval relay, Discord bridge, and fakechat dev profile), interactive tutorials, LSP integration, security-hardened hook script library, MCP Prompts coverage, common workflow packs, runtime selection guide, computer-use patterns, checkpointing, scheduled-task blueprints, repo bootstrap scanner, hook policy engine (8 installable packs), layered memory deployment, role-based subagent packs (implementer, debugger, migration-lead, dependency-auditor, release-coordinator), 5 agent-team topology kits, autonomy operating mode (4 profiles + 3 gates), and a queryable 15-tool MCP documentation server with autonomy advisor.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.