skills

Cross review code using a subagent with a specified model. Use when the user asks to review code changes AND specifies a model to use (e.g., 'review with opus', 'use sonnet to review', 'review changes with gemini'). The key differentiator from the regular code-review skill is that the user explicitly specifies which model should perform the review. The root agent reconstructs what changed from its own conversation history — no git commands are used.

Design distinctive, production-grade frontend interfaces — mockups as HTML pages or working application pages. Use when the user asks to design a web page, landing page, UI mockup, dashboard, application page, or any visual HTML interface. Supports single designs, multiple variant generation, and integration with existing project frameworks.

Browser automation with Playwright. Use when the user asks to test a website, take screenshots, check responsive design, test login flows, fill forms, check broken links, or automate any browser task.

Comprehensive code review using parallel specialized subagents. If a PR URL is provided, fetches PR details and can post comments. If no PR is provided, reviews the diff between the current branch and its base branch plus any uncommitted changes. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it.

Use when the user asks to initialize a repo, create AGENTS.md, generate contributor guidelines, or set up agent-oriented documentation for a codebase.

Review code changes for correctness, security, performance, and code quality. Use when the user asks to review a diff, review code changes, review commits, or perform a code review. Input can be: (1) a text diff pasted directly, (2) one or more git commit hashes to extract the diff from, or (3) a git range like abc123..def456. The user may also provide task description or requirements that motivated the change.

This skill should be used when the user asks to "install a skill", "import a skill", "add this skill", "try this skill from GitHub", or mentions installing, importing, or adding any AI coding skill/prompt from an external source. Gates external skill installs with a security assessment and installs across all supported CLIs.

This skill should be used when the user asks to "check this repo", "audit this project", "is this repo safe", "review this open source tool", or when another skill (git, install-mcp, install-skill) needs a security assessment of an external/public repository or package. Provides a unified security, quality, and privacy assessment.

Audit a repository's preparedness for autonomous AI coding agents - evaluates 86 checks spanning code quality, testing, documentation, security, and observability across 5 tiers (Bronze to Diamond)

This skill should be used when the user asks to "install an MCP server", "add this MCP server", "set up MCP", "configure this MCP tool", "add this to my MCP config", or mentions installing, setting up, or configuring any MCP (Model Context Protocol) server from an external source. Gates external MCP server installs with a security assessment and configures across all supported CLIs.

This skill should be used when the user asks to "clone a repo", "git clone", "check out this repo", "install this tool from GitHub", "try this open source project", or mentions cloning, checking out, or installing any Git repository. Automatically gates public repo clones with a security assessment before execution.