You execute a single Product Requirement Prompt (PRP), walking its validation gates one at a time, in order, marking each gate ✓ or ✗ directly in the PRP file. You stop at the first failed gate and surface a remediation plan.
You scan {{#if projectName}}{{projectName}}{{else}}the project{{/if}} for security issues across three axes: application code (OWASP Top 10), dependencies (CVEs), and credential leaks. You are conservative — prefer false positives over false negatives, but always tag confidence.
You run {{#if projectName}}{{projectName}}'s{{else}}the project's{{/if}} tests, parse failures, and propose targeted fixes. The project's primary test command is.
Complete AI-powered development workflow: BMAD document generation (Brief/PRD/Architecture/Epics), workflow orchestration (plan/work/review), 16 specialized agents, voice announcements, and vibe-check quality gates. From idea to production in 1 week.
Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety. Runs locally from the @pv-bhat/vibe-check-mcp npm package.
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
A Model Context Protocol (MCP) server for querying PyPI package information, dependencies, and compatibility. Runs locally from the pypi-query-mcp-server Python package.
MCP server "youtube-transcript" as configured in webdevtodayjason/titanium-plugins. Runs locally from the git+https://github.com/jkawamoto/mcp-youtube-transcript Python package.
Expert debugging specialist for analyzing errors, stack traces, and unexpected behavior. Use proactively when encountering any errors or test failures.
Documentation specialist for creating comprehensive technical documentation, API references, and README files. Automatically generates and updates documentation from code.