compounding-engineering

Create engaging changelogs for recent merges to main branch

Create or edit Claude Code skills with expert guidance on structure and best practices

Validate and prepare documentation for GitHub Pages deployment

Create a new custom slash command following conventions and best practices

Heal skill documentation by applying corrections discovered during execution with approval workflow

Use this agent when you need to verify that a UI implementation matches its Figma design specifications. This agent should be called after code has been written to implement a design, particularly after HTML/CSS/React components have been created or modified. The agent will visually compare the live implementation against the Figma design and provide detailed feedback on discrepancies. Examples: - <example> Context: The user has just implemented a new component based on a Figma design. user: "I've finished implementing the hero section based on the Figma design" assistant: "I'll review how well your implementation matches the Figma design." <commentary> Since UI implementation has been completed, use the design-implementation-reviewer agent to compare the live version with Figma. </commentary> </example> - <example> Context: After the general code agent has implemented design changes. user: "Update the button styles to match the new design system" assistant: "I've updated the button styles. Now let me verify the implementation matches the Figma specifications." <commentary> After implementing design changes, proactively use the design-implementation-reviewer to ensure accuracy. </commentary> </example>

Use this agent PROACTIVELY when design work isn't coming together on the first attempt. If you've made 1-2 design changes and the result still feels off, suggest using this agent with 5x or 10x iterations for deeper refinement. This agent takes screenshots, analyzes what's not working, implements improvements, and repeats N times to systematically fix design issues. Perfect when colors feel wrong, layouts aren't balanced, or the overall aesthetic needs work that single changes can't achieve. <example>Context: User asks to change button color but result still looks off. user: "Change the button to blue" assistant: [makes change, takes screenshot] "The button is now blue, but I notice the overall color balance still feels off. Would you like me to use the design-iterator agent with 5 iterations to systematically improve the color harmony and visual balance?" <commentary>PROACTIVE USE: After a simple change doesn't fully resolve the design issue, suggest the design-iterator to do deeper work.</commentary></example> <example>Context: User's design request leads to something that doesn't look right. user: "Make the hero section more modern" assistant: [makes initial changes] "I've added some modern elements, but the result isn't quite coming together. This looks like it needs iterative refinement. Let me use the design-iterator agent with 10 iterations to systematically improve typography, spacing, colors, and visual hierarchy until it feels polished." <commentary>PROACTIVE USE: When initial design work produces mediocre results, automatically suggest or use the design-iterator for comprehensive improvement.</commentary></example> <example>Context: User wants explicit iterative refinement. user: "The features section looks boring, iterate on it 10 times" assistant: "I'll use the design-iterator agent to systematically refine your features section through 10 iterations of visual improvements" <commentary>User explicitly requests iteration, use design-iterator directly.</commentary></example> <example>Context: Design task requires research and multiple passes. user: "Look at how Stripe does their pricing page and make mine better" assistant: "I'll launch the design-iterator agent with 8 iterations to research Stripe's design patterns and progressively apply those insights to your pricing page" <commentary>Competitor research combined with iterative refinement benefits from the systematic approach.</commentary></example>

Use this agent when you need to synchronize a web implementation with its Figma design by automatically detecting and fixing visual differences. This agent should be used iteratively until the implementation matches the design. <example> Context: User has just implemented a new component and wants to ensure it matches the Figma design. user: "I've just finished implementing the hero section component. Can you check if it matches the Figma design at https://figma.com/file/abc123/design?node-id=45:678" assistant: "I'll use the figma-design-sync agent to compare your implementation with the Figma design and fix any differences." <uses Task tool to launch figma-design-sync agent with the Figma URL and local URL> </example> <example> Context: User is working on responsive design and wants to verify mobile breakpoint matches design. user: "The mobile view doesn't look quite right. Here's the Figma: https://figma.com/file/xyz789/mobile?node-id=12:34" assistant: "Let me use the figma-design-sync agent to identify the differences and fix them." <uses Task tool to launch figma-design-sync agent> </example> <example> Context: After initial fixes, user wants to verify the implementation now matches. user: "Can you check if the button component matches the design now?" assistant: "I'll run the figma-design-sync agent again to verify the implementation matches the Figma design." <uses Task tool to launch figma-design-sync agent for verification> </example> <example> Context: User mentions design inconsistencies proactively during development. user: "I'm working on the navigation bar but I'm not sure if the spacing is right." assistant: "Let me use the figma-design-sync agent to compare your implementation with the Figma design and identify any spacing or other visual differences." <uses Task tool to launch figma-design-sync agent> </example>

Use this agent when you need to create or update README files following the Ankane-style template for Ruby gems. This includes writing concise documentation with imperative voice, keeping sentences under 15 words, organizing sections in the standard order (Installation, Quick Start, Usage, etc.), and ensuring proper formatting with single-purpose code fences and minimal prose. Examples: <example>Context: User is creating documentation for a new Ruby gem. user: "I need to write a README for my new search gem called 'turbo-search'" assistant: "I'll use the ankane-readme-writer agent to create a properly formatted README following the Ankane style guide" <commentary>Since the user needs a README for a Ruby gem and wants to follow best practices, use the ankane-readme-writer agent to ensure it follows the Ankane template structure.</commentary></example> <example>Context: User has an existing README that needs to be reformatted. user: "Can you update my gem's README to follow the Ankane style?" assistant: "Let me use the ankane-readme-writer agent to reformat your README according to the Ankane template" <commentary>The user explicitly wants to follow Ankane style, so use the specialized agent for this formatting standard.</commentary></example>

Use this agent when you need to research and gather external best practices, documentation, and examples for any technology, framework, or development practice. This includes finding official documentation, community standards, well-regarded examples from open source projects, and domain-specific conventions. The agent excels at synthesizing information from multiple sources to provide comprehensive guidance on how to implement features or solve problems according to industry standards. <example>Context: User wants to know the best way to structure GitHub issues for their Rails project. user: "I need to create some GitHub issues for our project. Can you research best practices for writing good issues?" assistant: "I'll use the best-practices-researcher agent to gather comprehensive information about GitHub issue best practices, including examples from successful projects and Rails-specific conventions." <commentary>Since the user is asking for research on best practices, use the best-practices-researcher agent to gather external documentation and examples.</commentary></example> <example>Context: User is implementing a new authentication system and wants to follow security best practices. user: "We're adding JWT authentication to our Rails API. What are the current best practices?" assistant: "Let me use the best-practices-researcher agent to research current JWT authentication best practices, security considerations, and Rails-specific implementation patterns." <commentary>The user needs research on best practices for a specific technology implementation, so the best-practices-researcher agent is appropriate.</commentary></example>

Write Ruby gems following Andrew Kane's proven patterns and philosophy. Use when creating new Ruby gems, refactoring existing gems, designing gem APIs, or when the user wants clean, minimal, production-ready Ruby library code. Triggers on requests like "create a gem", "write a Ruby library", "design a gem API", or mentions of Andrew Kane's style.

Capture solved problems as categorized documentation with YAML frontmatter for fast lookup

Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

Write Ruby and Rails code in DHH's distinctive 37signals style. Use this skill when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals, Basecamp, HEY, or Campfire style. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and the "clarity over cleverness" philosophy.

This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Anthropic, Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.