compound-engineering

Cancel an active ralph loop

Create engaging changelogs for recent merges to main branch

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

Enhance a plan with parallel research agents for each section to add depth, best practices, and implementation details

Validate and prepare documentation for GitHub Pages deployment

Record a video walkthrough of a feature and add it to the PR description

Create a new custom slash command following conventions and best practices

Fix incorrect SKILL.md files when a skill has wrong instructions or outdated API references

Full autonomous engineering workflow

Start a self-referential loop using the stop hook mechanism.

Report a bug in the compound-engineering plugin

Reproduce and investigate a bug using logs, console inspection, and browser screenshots

Resolve all TODO comments using parallel processing

Resolve all pending CLI todos using parallel processing

Full autonomous engineering workflow using swarm mode for parallel execution

Run browser tests on pages affected by current PR or branch

Triage and categorize findings for the CLI todo system

Explore requirements and approaches through collaborative dialogue before planning implementation

Document a recently solved problem to compound your team's knowledge

Transform feature descriptions into well-structured project plans following conventions

This template is used by the `workflows:work` orchestrator to construct prompts for execution subagents. The orchestrator fills in context blocks (marked with `{{PLACEHOLDER}}`) before passing the result to `Task(general-purpose, prompt=filled_template)`.

This template is used by the `workflows:work` orchestrator to dispatch a code quality reviewer subagent when `--review-mode inline` or `--review-mode both` is active. This reviewer is dispatched ONLY AFTER spec compliance has passed.

This template is used by the `workflows:work` orchestrator to dispatch a spec compliance reviewer subagent when `--review-mode inline` or `--review-mode both` is active. The orchestrator fills in context blocks before passing the result to a subagent.

Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees

Execute work plans efficiently while maintaining quality and finishing features

Visually compares live UI implementation against Figma designs and provides detailed feedback on discrepancies. Use after writing or modifying HTML/CSS/React components to verify design fidelity.

Iteratively refines UI design through N screenshot-analyze-improve cycles. Use PROACTIVELY when design changes aren't coming together after 1-2 attempts, or when user requests iterative refinement.

Detects and fixes visual differences between a web implementation and its Figma design. Use iteratively when syncing implementation to match Figma specs.

Researches and synthesizes external best practices, documentation, and examples for any technology or framework. Use when you need industry standards, community conventions, or implementation guidance.

Gathers comprehensive documentation and best practices for frameworks, libraries, or dependencies. Use when you need official docs, version-specific constraints, or implementation patterns.

Performs archaeological analysis of git history to trace code evolution, identify contributors, and understand why code patterns exist. Use when you need historical context for code changes.

Searches docs/solutions/ for relevant past solutions by frontmatter metadata. Use before implementing features or fixing problems to surface institutional knowledge and prevent repeated mistakes.

Conducts thorough research on repository structure, documentation, conventions, and implementation patterns. Use when onboarding to a new codebase or understanding project conventions.

Reviews code to ensure agent-native parity — any action a user can take, an agent can also take. Use after adding UI features, agent tools, or system prompts.

Software architecture review specialist. Evaluates code for SOLID compliance, clean architecture, DDD, coupling/cohesion, anti-patterns, and API design. Use when reviewing PRs, designing modules, evaluating refactors, or assessing system structure.

Code complexity eliminator and readability champion. Measures cognitive complexity, enforces function length limits, detects dead code, flags over-engineering, and enforces YAGNI with surgical precision.

Reviews database migrations, data models, and persistent data code for safety. Use when checking migration safety, data constraints, transaction boundaries, or privacy compliance.

Validates data migrations, backfills, and production data transformations against reality. Use when PRs involve ID mappings, column renames, enum conversions, or schema changes.

Produces Go/No-Go deployment checklists with SQL verification queries, rollback procedures, and monitoring plans. Use when PRs touch production data, migrations, or risky data changes.

Analyzes code for design patterns, anti-patterns, naming conventions, and duplication. Use when checking codebase consistency or verifying new code follows established patterns.

Analyzes code for performance bottlenecks, algorithmic complexity, database queries, caching, memory usage, and scalability. Use after implementing features or when performance concerns arise.

Reviews Laravel/PHP code enforcing modern Laravel 11+ and PHP 8.3+ best practices with P1/P2/P3 severity levels. Use after implementing features, modifying code, or creating new Laravel components.

Reviews NestJS code enforcing simplicity, performance, and security standards. Use after implementing features, modifying code, or creating new NestJS components.

Reviews Python code with an extremely high quality bar for Pythonic patterns, type safety, and maintainability. Use after implementing features, modifying code, or creating new Python modules.

Reviews Rust code with an extremely high quality bar for ownership correctness, idiomatic patterns, unsafe discipline, and zero-cost abstraction design. Use after implementing features, modifying code, or creating new Rust crates/modules.

Reviews TypeScript code with an extremely high quality bar for type safety, modern patterns, and maintainability. Use after implementing features, modifying code, or creating new TypeScript components.

Reviews Vue.js and Nuxt code for modern best practices, performance, accessibility, and security. Use after implementing frontend features or modifying Vue/Nuxt components.

Application security auditor aligned with OWASP Top 10 2025. Performs comprehensive security reviews covering access control, injection, supply chain, cryptography, secrets management, and API security. Use when reviewing code for security issues or before deployment.

Systematically reproduces and validates bug reports to confirm whether reported behavior is an actual bug. Use when you receive a bug report or issue that needs verification.

Addresses PR review comments by implementing requested changes and reporting resolutions. Use when code review feedback needs to be resolved with code changes.

Analyzes specifications and feature descriptions for user flow completeness and gap identification. Use when a spec, plan, or feature description needs flow analysis, edge case discovery, or requirements validation.

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".

Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.

This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when the user's request has multiple valid interpretations that need clarification.

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

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

This skill should be used to refine brainstorm or plan documents before proceeding to the next workflow step. It applies when a brainstorm or plan document exists and the user wants to improve it.

This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.

Use when completing development on a feature branch -- verifies quality, presents completion options, and cleans up

This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

This skill manages Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface, following KISS principles.

Modern Laravel 11+ / PHP 8.3+ coding standards reference. Use when writing or reviewing PHP/Laravel code to ensure convention compliance.

This skill should be used when orchestrating multi-agent swarms using Claude Code's TeammateTool and Task system. It applies when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.

Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.

Resolve all PR comments using parallel processing. Use when addressing PR review feedback, resolving review threads, or batch-fixing PR comments.

Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use when debugging unexpected errors during implementation -- provides a structured 4-phase methodology instead of trial-and-error

1 hook across 1 event