Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates specs/tech-architecture/tech-stack.md and specs/adr/ inline as decisions crystallise. Use when user wants to stress-test a plan against their project's domain language and documented decisions.
Doc-grounded variant of grill-me — stress-tests plan assumptions by fetching and citing real library or API documentation. Every challenge must cite a real URL. Use when the plan depends on a specific library or external API.
Provides a systematic, research-driven workflow for implementing new Vibe components - for the @vibe/core library (located in "packages/core") - from initial research through final validation. Emphasizes studying existing patterns, following established conventions, and systematic progression through types, component implementation, styling, testing, and documentation to ensure consistency and quality.
Use this rule to get a high-level project overview, identify the core function of each crate, understand major subsystems, and find the entry-point documentation for components.
User Education & Support Specialist. Use this agent to generate FAQs, troubleshoot from code logic, and manage documentation as a first line of defense. It turns technical complexity into accessible guides for users.
Product vision (docs/ux/vision.md): apply when defining what the product is and what it refuses to become, when a proposed feature feels off-strategy, or when a scope argument has no document that settles it
Founder Operating Context. Use to create or update the canonical founder/startup context document so every fundraising, growth, product, and recruiting workflow runs on concrete company facts instead of generic assumptions.
Create or update a reusable product marketing context document with positioning, audience, ICP, use cases, and messaging. Use at the start of a project to avoid repeating core marketing context across tasks.
Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
Prevent content duplication in documentation, reports, and code. Check for existing content before creating new. Consolidate duplicates to single source of truth.
Get started with DeepRead OCR. Automatically obtains an API key via device authorization flow (RFC 8628), then walks through first document, structured extraction, and blueprints.
Comprehensive guide for base components in `@vibe/core` library (BaseInput, BaseList, BaseListItem, InfoText, FieldLabel). Documents their usage patterns, accessibility requirements, form integration patterns, and what consumers need to provide for optimal accessibility and UX. These components serve as foundational building blocks for complex UI components like dropdowns, text fields, and other form controls. Those components are internal, for developing components in Vibe, and are not intended to be exported from the `@vibe/core` library.
Author Diagrammer JSON for the Diagrammer viewer. Use whenever the user asks for a mind map, concept map, flowchart, tree, dependency graph, ER diagram, or timeline. Output a single JSON document conforming to the schema below.
Block dangerous git commands (push, force push, reset --hard, clean, branch -D, checkout/restore .) and enforce Conventional Commits & Branch Protection before an AI agent runs them. Installs hook scripts for Claude Code, Cursor, Cursor CLI, and Gemini CLI; documents Google Antigravity Terminal deny lists. Use when the user wants git safety hooks, to block git push or destructive git in agents, or to mirror the same policy across AI coding tools.
Full expert review protocol. 8-expert, 2-wave deliberation for comprehensive codebase and documentation review. Invoke before major milestones, after shipping feature clusters, or before staging/production deployment.
Full expert review protocol. 8-expert, 2-wave deliberation for comprehensive codebase and documentation review. Invoke before major milestones, after shipping feature clusters, or before staging/production deployment.
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md those are already markdown, use WebFetch directly.