By jeffh
Orchestrate deterministic CLI-first AI workflows by delegating to specialized agents for code engineering, UI/UX design, multi-model research, QA testing, and content analysis, with enforced structured responses, full session history capture, and Git/CLI routing.
npx claudepluginhub jeffh/claude-plugins --plugin paiVisual description specialist. Generates detailed prompts for image generation tools (DALL-E, Midjourney, Stable Diffusion). Creates visual concepts with style, composition, and mood specifications. Use for creating image prompts.
UI/UX design specialist. Creates wireframes, component specifications, user flows, and interaction patterns. Designs interfaces with accessibility, usability, and visual hierarchy in mind. Use for interface design tasks.
Code implementation specialist. Writes production-quality code, follows existing patterns, implements features, fixes bugs, and creates tests. Use for all coding tasks.
Use this agent to orchestrate comprehensive multi-perspective research using Google's Gemini model. Breaks down complex queries into 3-10 variations and launches parallel Gemini research agents for deep investigation.
Use this agent when you or any subagents need research done - crawling the web, finding answers, gathering information, investigating topics, or solving problems through research.
Quality assurance specialist. Writes and runs tests, identifies edge cases, validates implementations, and reports bugs with reproduction steps. Use for testing and validation tasks.
Information gathering specialist. Performs web research, codebase analysis, and documentation synthesis. Returns structured findings with sources. Use for research and exploration tasks.
PAI (Personal AI Infrastructure) - Your AI system core. AUTO-LOADS at session start. USE WHEN any session begins OR user asks about PAI identity, response format, stack preferences, security protocols, or delegation patterns.
Create, update, validate, and canonicalize Claude Code skills. USE WHEN user wants to create a new skill OR modify an existing skill OR validate skill structure OR fix skill format OR migrate legacy skills.
Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summarize, analyze_claims, threat modeling, etc.). Patterns run natively in Claude's context - no CLI spawning needed. Only use fabric CLI for YouTube transcripts (-y) or pattern updates (-U).
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.
Comprehensive research, analysis, and content extraction system. Multi-source parallel research using available researcher agents. Deep content analysis with extended thinking. Intelligent retrieval for difficult sites. Fabric pattern selection for 242+ specialized prompts. USE WHEN user says 'do research', 'extract wisdom', 'analyze content', 'find information about', or requests web/content research.
Create compelling story-format summaries using UltraThink to find the best narrative framing. Support multiple formats - 3-part narrative, n-length with inline links, abridged 5-line, or comprehensive via Foundry MCP. USE WHEN user says 'create story explanation', 'narrative summary', 'explain as a story', or wants content in Daniel's conversational first-person voice.
A collection of powerful plugins for Claude Code that enhance your development workflow with specialized commands and agents for codebase research, planning, and implementation.
This repository provides a plugin marketplace for Claude Code with multiple plugins to enhance your development workflow:
You can install plugins from this marketplace using one of these methods:
/plugin marketplace add jeffh/claude-plugins
If you've cloned this repository locally:
/plugin marketplace add /path/to/claude-plugins
After adding the marketplace, install the plugin:
# Interactive installation (browse all available plugins)
/plugin
# Direct installation
/plugin install humanlayer@jeffh-claude-plugins
Commands and agents from HumanLayer, optimized for Claude Code workflows. Provides 6 core slash commands (with additional variants) for complete development workflows and 6 specialized research agents.
Quick Overview:
/commit, /create_plan, /implement_plan, /validate_plan, /describe_pr, /research_codebasecodebase-analyzer, codebase-locator, codebase-pattern-finder, thoughts-analyzer, thoughts-locator, web-search-researcherJujutsu (jj) version control commands for streamlined workflows. Provides 3 slash commands specifically designed for developers using Jujutsu VCS.
Quick Overview:
/commit, /rebase, /create_prs# 1. Research and plan
/create_plan
# 2. Implement the plan
/implement_plan thoughts/shared/plans/2025-10-09-my-feature.md
# 3. Create commits
/commit
# 4. Validate implementation
/validate_plan thoughts/shared/plans/2025-10-09-my-feature.md
# 5. Generate PR description
/describe_pr
# Comprehensive research
/research_codebase
# Provide: "How does authentication work in this codebase?"
# Or spawn agents directly via Task tool for specific questions
Some commands expect a thoughts/ directory structure. See individual plugin documentation for details.
Commands and agents from humanlayer, but without the thought syncing
Matches all tools
Hooks run on every tool call, not just specific ones
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Interactive setup wizard for configuring any repository with Claude Code best practices, based on Boris Cherny's workflow
Core SimpleClaude framework with 4+1 intent-based commands and 7 specialized agents
Autonomous Development Workflows
General purpose Claude Code toolkit with research agents, skills, and introspection commands
Development workflow automation including feature development, code quality, and PR management