compound-engineering

Create Architecture Decision Records with format selection and lifecycle management

Run comprehensive agent-native architecture review with scored principles

Create engaging changelogs for recent merges to main branch

Review docs/solutions/ for stale learnings -- keep, update, replace, or archive

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

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

Generate ranked improvement ideas by scanning the codebase, divergent ideation, adversarial critique, and impact ranking

Full autonomous engineering workflow (plan, build, review, ship)

```markdown

**ALWAYS use these Bash commands. NEVER use mcp__claude-in-chrome__* tools.**

Report a bug in the compound-engineering plugin

Reproduce a GitHub issue bug with visual evidence (Playwright screenshots, log analysis). Takes a GitHub issue number. For non-issue bug validation, use the bug-reproduction-validator agent.

Resolve PR review comments with cluster analysis and parallel agents. Use when bulk-fixing PR comments after triage.

Resolve all pending CLI todos using parallel processing

Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md. Use when setting up compound-engineering for a new project, configuring review agents, or running initial plugin setup.

Run browser tests on pages affected by current PR or branch

Triage and categorize findings for the CLI todo system

Run comprehensive pre-PR verification (build, types, lint, tests, security scan, diff review)

Explore requirements and approaches through collaborative dialogue before planning implementation

Parallel-agent workflow to document a solved problem for team reuse. Use after debugging, fixing, or resolving a non-trivial issue.

Post-ship documentation sync. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, and optionally bumps the version.

Transform feature descriptions into well-structured project plans following conventions

- [ ] Use clear, descriptive headings with proper hierarchy (##, ###)

**Best for:** Simple bugs, small improvements, clear features

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

Execute work plans efficiently while maintaining quality and finishing features

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.

Compares web UI against Figma designs and reports discrepancies. Optionally implements fixes. Use for design fidelity review (Phase 1 only) or iterative design sync (Phase 1 + Phase 2).

Researches best practices, framework documentation, and implementation patterns for any technology. Use when you need official docs, version-specific constraints, industry standards, or community conventions.

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 this codebase's structure, documentation, conventions, and project-specific implementation patterns. Use when onboarding to the repo or understanding its conventions. For external best practices, use best-practices-researcher.

WCAG 2.1 accessibility audit: keyboard navigation, screen reader, contrast, ARIA, forms, cognitive. Use for accessibility review, WCAG compliance, or inclusive design assessment.

Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use after code review to assess structural patterns, when adding services, evaluating refactors, or checking codebase consistency. For granular code-level review, use the code-review skill.

Cloud infrastructure design: multi-cloud, Well-Architected Framework, cost optimization, disaster recovery, migration strategies. Use when reviewing cloud architecture or planning infrastructure.

Produces a simplification analysis report (no code changes). Use after implementation to identify YAGNI violations and simplification opportunities. For actual refactoring, use the simplifying-code skill.

Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.

Persona-driven Python and TypeScript code review with extremely high bar for type safety, naming conventions, and modern patterns. Use after implementing features or modifying code. For broader review workflow, use the code-review skill.

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

Performs security audits for vulnerabilities, input validation, auth/authz, hardcoded secrets, and OWASP compliance. Use when reviewing code for security issues or before deployment.

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.

Validates, reproduces, and root-cause analyzes bug reports (does not fix). Use when a bug report needs verification and root cause identification before committing to a fix. For GitHub issue bugs with visual reproduction, use the /reproduce-bug command. For fixing, use the debugging skill.

CI/CD pipeline design, deployment strategies (blue-green, canary, rolling), GitOps workflows, release orchestration. Use for pipeline optimization or deployment automation. Not for Docker/container review or observability (use devops-engineer).

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

Docker containerization, monitoring/observability, and incident management. For postmortems, follows the debugging skill. Use when reviewing Dockerfiles, optimizing containers, setting up observability, or responding to incidents. Not for CI/CD pipeline design or release strategies (use deployment-engineer).

Implements a single pre-triaged PR review comment mechanically. Use when a specific comment's action is clear and agreed -- not for judgment calls (use receiving-code-review skill) or bulk resolution (use /resolve-pr command).

Build applications where agents are first-class citizens. Use when designing autonomous agents, MCP tools, or self-modifying agent-loop architectures.

Pre-implementation brainstorming process: deep interview protocol, approach exploration, and design doc generation. Provides process knowledge for `/workflows:brainstorm`. Use when brainstorming inline without the full command workflow, or when clarifying ambiguous requirements.

Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs, MRs, or diffs.

Document solved problems for team reuse. Provides process knowledge for /workflows:compound. Use when documenting a resolved issue, writing up lessons learned, capturing a post-mortem, adding to the knowledge base, or building searchable institutional knowledge after debugging.

Systematic root-cause debugging with verification. Use when debugging, troubleshooting, or facing errors, stack traces, broken tests, flaky tests, or regressions. For validating bug reports before fixing, use bug-reproduction-validator agent.

Structural review of documents for gaps, clarity, completeness, and organization. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the next workflow step. For exploring new ideas from scratch, use brainstorming instead.

File-based todo and task tracking in the todos/ directory. Use when creating, triaging, listing, or managing todo files, tracking work items, managing the backlog, converting PR comments to tracked tasks, or checking todo status and dependencies.

Visual design and aesthetic direction for frontend interfaces. Use when building web pages, landing pages, dashboards, or applications where visual identity matters. For React patterns and testing, use react-frontend.

Manage Git worktrees for isolated parallel development. Use when creating, listing, switching, or cleaning up git worktrees, or when needing isolated branches for concurrent reviews or feature work.

Defensive Bash scripting for Linux: safe foundations, argument parsing, production patterns, ShellCheck compliance. Use when writing bash scripts, shell scripts, cron jobs, or CLI tools in bash.

Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md. Use when asked to update, create, or init these context files. Not for general markdown editing.

Enhanced reasoning via /think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade, /postmortem. Use when stress-testing reasoning or applying structured thinking.

Node.js backend patterns: layered architecture, TypeScript, validation, error handling, security, deployment. Use when building REST APIs, Express/Fastify/Hono/NestJS servers, or server-side TypeScript.

Coordinate multi-agent swarms for parallel and pipeline workflows. Use when coordinating multiple agents, running parallel reviews, building pipeline workflows, or implementing divide-and-conquer patterns with subagents.

Modern PHP 8.4 and Laravel patterns: architecture, Eloquent, queues, testing. Use when working with Laravel, Eloquent, Blade, artisan, PHPUnit, PHPStan, or building/testing PHP applications with frameworks. Not for PHP internals (php-src) or general PHP language discussion.

Pine Script v6 patterns: syntax, performance, error diagnosis, backtesting, visualization. Use when working with PineScript, TradingView, indicators, strategies, or backtesting.

Software implementation planning with file-based persistence (.plan/). Use when asked to plan, break down a feature, or starting complex tasks. Apply proactively before non-trivial coding.

PostgreSQL schema design, query optimization, indexing, and administration. Use when working with PostgreSQL, JSONB, partitioning, RLS, CTEs, window functions, or EXPLAIN ANALYZE.

Python patterns for CLI tools, async concurrency, and backend services. Use when working with Python code, building CLI apps, FastAPI services, async with asyncio, background jobs, or configuring uv, ruff, ty, pytest, or pyproject.toml.

React architecture patterns, TypeScript, Next.js, hooks, and testing. Use when working with React component structure, state management, Next.js routing, Vitest, React Testing Library, or reviewing React code. For visual design and aesthetic direction, use frontend-design instead.

Process code review feedback critically: check correctness before acting, push back on incorrect suggestions, no performative agreement. Use when responding to PR/MR review comments or implementing reviewer suggestions received from others.

Transforms vague prompts into precise, structured AI instructions. Use when asked to refine, improve, or sharpen a prompt, do prompt engineering, write a system prompt, or make AI instructions more effective.

Session retrospective and skill audit. Use when asked to reflect, do a retrospective, review lessons learned, audit what went well or wrong, or review session effectiveness.

Simplifies, polishes, and declutters code without changing behavior. Use when asked to simplify, clean up, refactor, declutter, remove dead code or AI slop, or improve readability. For analysis-only reports without code changes, use code-simplicity-reviewer agent.

Tailwind CSS v4 patterns: CSS-first config, utility classes, component variants, v3 migration. Use when styling with Tailwind, configuring @theme tokens, using tailwind-variants/CVA, migrating v3 to v4, or fixing Tailwind styles and dark mode.

Terraform and OpenTofu configuration, modules, testing, state management, and HCL review. Use when working with Terraform, OpenTofu, HCL, tfvars, tftest, state migration, or IaC patterns.

Enforces fresh verification evidence before any completion claim. Use when about to claim "tests pass", "bug fixed", "done", "ready to merge", or handing off work.

Generic test writing discipline: test quality, real assertions, anti-patterns, and rationalization resistance. Use when writing tests, adding test coverage, or fixing failing tests for any language or framework. Complements language-specific skills.

Prose editing, rewriting, and humanizing text for natural tone. Use when asked to write, rewrite, edit, humanize, proofread, fix tone, or remove AI language. For copy, docs, blog posts, emails, or PRs.

1 hook across 1 event