browse

Answer Engine Optimization (AEO) audit and SERP analysis for AI-generated answers. Analyzes pages for AEO readiness (structured data, FAQ patterns, heading hierarchy, meta quality) and checks how queries appear in AI-powered search results (Google AI Overviews, Perplexity, ChatGPT Search). Uses the browse CLI for all page interaction.

Guided configuration generator for the browse CLI's camoufox integration. Asks the user questions to build a browse.json camoufox section or a named profile JSON file for stealth, fast-scraping, Google-safe, or custom setups.

Generative Engine Optimization (GEO) monitoring — track brand and domain visibility across AI-powered search engines: Google AI Overviews, Perplexity, and ChatGPT Search. Run multi-query sweeps, detect citations, measure domain presence, and generate cross-engine visibility reports. Uses the browse CLI with camoufox for stealth.

SEO auditing for AI agents using the browse CLI. Extracts meta tags, headings, structured data, performance metrics, link structure, and mobile rendering. Generates actionable audit reports with findings and recommendations. Works with any URL.

Fast web browsing, web app testing, and native app automation for AI coding agents. Persistent headless Chromium for web. Android, iOS, and macOS app automation via accessibility APIs. Browse URLs, read content, click elements, fill forms, run JavaScript, take screenshots, automate native apps — all through the same CLI and @ref workflow. ~100ms per command. Auto-installs Android toolchain. Works with Claude Code, Cursor, Cline, Windsurf, and any agent that can run Bash.

Stealth browsing with the camoufox runtime for AI agents. Covers Cloudflare Turnstile bypass, Google anti-bot evasion, authenticated sessions, and proxy rotation. Uses the browse CLI with --runtime camoufox and named camoufox profiles.

QA a web or app feature from a ticket, URL, acceptance criteria, or plain-language description, then generate reusable browse flows for regression coverage. Uses the `browse` skill for the actual browser or simulator interaction and keeps the QA loop focused on scenarios, evidence, and report quality.

Fast web browsing, web app testing, and native app automation for AI coding agents. Persistent headless Chromium for web. Android, iOS, and macOS app automation via accessibility APIs. Browse URLs, read content, click elements, fill forms, run JavaScript, take screenshots, automate native apps — all through the same CLI and @ref workflow. ~100ms per command. Auto-installs Android toolchain. Works with Claude Code, Cursor, Cline, Windsurf, and any agent that can run Bash.

Technical founder review of a plan before execution. Reads a plan from .ulpi/plans/<name>.md, verifies file paths exist, checks markdown/JSON consistency, challenges scope and architecture decisions, audits prerequisites/contracts/risk coverage/test gaps, scores sections, and delivers a verdict (APPROVE/REVISE/REJECT). Invoke via /plan-founder-review or when user says "review my plan", "check the plan".

Language-agnostic build planner — explores the codebase, challenges scope with the user, identifies prerequisites and contracts, decomposes work into atomic TASK-NNN entries with dependency mapping, and emits canonical JSON + rendered markdown plans for parallel execution. Use when you need a structured task DAG that is safe to execute, not just easy to read.

Orchestrate multiple specialized agents working in parallel when building independent features. Use when the task list contains 3+ unrelated tasks that don't share state or files. Matches each task to the right expert agent and launches them concurrently via the Agent tool with worktree isolation. Supports all available subagent types.

Orchestrate multiple specialized agents working in parallel to debug independent problems. Use when encountering 3+ unrelated bugs or test failures in isolated modules. Matches each problem to the right expert agent and launches them concurrently via the Agent tool with worktree isolation. Supports all available subagent types.

MANDATORY for starting any conversation or task. Establishes required workflows: discovering and using skills, invoking the Skill tool before announcing usage, performing brainstorming before coding, creating TodoWrite todos for all checklists, and selecting/invoking the correct specialized agent persona for the task domain.

Automatically orchestrate multiple specialized agents working in parallel when building independent features, modules, or performing separate investigations. Use when the task list contains 3+ unrelated features/tasks that don't share state, don't have execution dependencies, and can be understood independently. Match each feature to the right expert agent (Laravel, Next.js, React, Node, NestJS, Remix, Express, Expo, Flutter, Magento) and run them concurrently to maximize development speed.

MANDATORY for starting any conversation or task. Establishes required workflows: discovering and using skills, invoking the Skill tool before announcing usage, performing brainstorming before coding, creating TodoWrite todos for all checklists, and selecting/invoking the correct specialized agent persona for the task domain.

Technical founder review of a plan before execution. Reads a plan from plans/<name>.md, verifies file paths exist, challenges scope and architecture decisions, audits risk coverage and test gaps, scores sections, and delivers a verdict (APPROVE/REVISE/REJECT). Invoke via /plan-founder-review or when user says "review my plan", "check the plan".

Interactive build planner — explores codebase via CodeMap, challenges scope with user, decomposes features into atomic TASK-NNN entries with dependency mapping and priority assignment, produces machine-parseable task plans for parallel agent execution. Use when you need to break a feature, bug fix, or project into a structured DAG of tasks for parallel agent execution.

Automatically orchestrate multiple specialized agents working in parallel to debug, diagnose, and fix independent problems across different subsystems. Use when encountering 3+ unrelated bugs, test failures, or issues in isolated modules that don't share root causes. Match each problem to the right expert agent (Laravel, Next.js, React, Node, NestJS, Remix, Express, Expo, Flutter, Magento) to diagnose and resolve issues concurrently, maximizing debugging efficiency.

Structural code search via AST patterns. Find code by structure, not text — async functions without error handling, specific API call patterns, missing guards. Use when grep/ripgrep can't express what you need. Requires ast-grep CLI.

Pre-landing PR review. Analyzes diff against main for structural issues that tests don't catch: query safety, race conditions, trust boundary violations, conditional side effects, and more. Critical findings block /ship and /create-pr. Invoke via /branch-review-before-pr or when integrated as a gate in ship workflows.

Fix bugs found by /find-bugs, reported by the user, or encountered during development. Systematically reproduces, diagnoses root cause, plans minimal fix, implements with regression tests, verifies no regressions, and reports results. Includes bug-type-specific fix playbooks for security, logic, async, null safety, race conditions, and more. Includes framework-specific reference files for 18 frameworks/languages (Express, React, Next.js, Fastify, Hono, Remix, Laravel, Go, Gin, Echo, Fiber, Swift, Bun, Rust, Axum, Actix Web, Rocket, React Native). Handles single bugs, multi-file bugs, and batch fixes from find-bugs output. Invoke via /bugfix or when user says "fix this bug", "fix the findings", "fix finding #3", "fix the critical bugs".

Build a distributable DMG installer for any macOS Xcode project. Handles archiving, code signing, DMG creation with styled Finder window, and version management. Trigger on: "build a DMG", "create DMG installer", "package as DMG", "build for distribution", or when the user wants to distribute a macOS app outside the App Store.

Spawn a separate Claude Code agent to review code changes made in the current session or branch. Uses the Agent tool with worktree isolation so the reviewer gets an independent read-only copy. Use when the user says "claude review", "self-review", "/claude-review", or when a task plan calls for post-task review.

Review changed code for reuse, quality, and efficiency. Analyzes for unnecessary complexity, redundant abstractions, deep nesting, and unclear naming, then applies targeted simplifications while preserving all behavior. Invoke via /code-simplify or when user says "simplify this", "clean up this code", "make this simpler", "reduce complexity".

Hybrid vector+BM25 code search, symbol lookup, dependency analysis, PageRank importance scoring, coupling metrics, and circular dependency detection via the codemap CLI. Use when the user asks to search code, find symbols, analyze dependencies, find dependents, check coupling, view PageRank importance, detect circular dependencies, index a project, get file summaries, or explore architecture health. Wraps the @ulpi/codemap CLI (not MCP tools).

Run OpenAI Codex CLI to review code changes made in the current session or branch. Invokes `codex review` with focused instructions derived from the actual changes. Use when the user says "codex review", "second opinion", "rival review", "cross-review", or "/codex-review".

Use when the user asks to commit changes. Analyzes diffs deeply to draft intelligent conventional commit messages, detects scope from branch names and file paths, runs pre-commit quality checks (TypeScript, ESLint, Prettier), scans for secrets and debug artifacts, splits unrelated changes into separate commits, and verifies success. Invoke via /commit or when user says "commit", "commit this", "make a commit".

Estimate development cost of a codebase (full repo, branch diff, or single commit). Invoke via /cost-estimate or when user says "estimate cost", "how much would this cost", "development cost". Accepts optional scope args like "branch:feat/foo" or "commit:abc1234".

Use when the user asks to create a pull request, open a PR, submit changes for review, or says "/pr". Validates branch state, analyzes all commits since divergence from base, runs pre-PR quality checks, generates structured PR title and body with summary/test-plan/breaking-changes sections, pushes branch, and creates the PR via GitHub CLI (gh). Supports draft PRs, reviewer assignment, and label attachment.

Find, install, and manage AI agents across 43+ coding IDEs. Search the agentshq registry, install agents from GitHub repos or URLs, list/remove/update installed agents. Invoke via /find-agents or when user says "find an agent", "install agent", "search agents", "list agents", "remove agent", "update agents".

Use when the user asks to find bugs, review changes, security audit, or check code quality on the current branch. Analyzes full diffs against the default branch, maps attack surfaces, runs a security checklist against every changed file, verifies findings against context, and reports prioritized issues. Invoke via /find-bugs or when user says "find bugs", "review my changes", "security review", "audit this code".

Design user interfaces with comprehensive UX methodology. Produces implementation-ready specifications, component briefs, and design tokens for handoff to Next.js and React engineering agents. Use when designing new features, creating design systems, planning user flows, or specifying component behavior.

Expert in merging branches, resolving Git conflicts, worktree management, PR readiness checks, merge strategies, rollback, and GitHub workflow automation. Invoke via /git-merge-expert or when user says "merge branch", "resolve conflicts", "merge PR", "rollback merge".

Worktree-native merge engineer — git worktree lifecycle, isolated merges and conflict resolution, worktree path conventions, parallel worktree operations, and cleanup automation. Invoke via /git-merge-expert-worktree or when user says "merge in worktree", "isolated merge", "worktree merge".

Run Kiro CLI to review code changes made in the current session or branch. Invokes `kiro-cli chat` in non-interactive mode with focused review instructions derived from the actual changes. Use when the user says "kiro review", "second opinion", "rival review", "cross-review", or "/kiro-review".

Filament v5 admin panel — resources, schemas, tables, actions, relation managers, widgets, navigation, and panels. Use when working on any Filament resource, form, table, action, filter, widget, page, or panel configuration task.

Laravel 12 API development — API-only, Actions pattern, Sanctum/Passport auth, Eloquent strict mode, Redis caching/queues, Horizon, Filament admin, Pest testing. Also covers Laravel AI ecosystem: AI SDK (agents, embeddings, image/audio generation), Boost (AI-assisted development), and MCP (exposing your app to AI clients). Use when working on any Laravel route, controller, model, action, migration, job, notification, test, API endpoint, AI agent, or MCP server task.

Local dev proxy that gives projects named HTTPS domains on .test with valid TLS. Use when setting up local development environments, running dev servers, sharing localhost publicly via tunnels, or managing Docker Compose services with HTTPS. Handles framework detection (30+ frameworks), port management, DNS, certificates, and public tunnels. Trigger on: "run my dev server", "set up HTTPS locally", "share localhost", "expose my app", "local dev proxy", "tunnel", ".test domain", or when helping users start/configure web projects.

Scan a Cargo workspace or package monorepo and generate/update per-member CLAUDE.md files. Each member directory gets a focused, self-contained CLAUDE.md with real exported surface, key files, dependencies, wiring points, and conventions. Run after coding sessions, refactors, or crate/package additions to keep the AI context map current.

Scan the codebase and generate/update CLAUDE.md + reference files (exports, architecture, dev guide) with real project-specific patterns. Run after each coding session or major refactor to keep the AI context map current. Supports Laravel, Next.js, NestJS, Expo/React Native, and Node.js projects.