Seo Page

Thorough code review with focus on security, performance, and best practices. Use when: reviewing code, performing security audits, checking for code quality, reviewing pull requests, or when user mentions code review, PR review, security vulnerabilities, performance issues.

Creates, updates, and fixes Cypress tests (E2E/end-to-end and component tests). Use when the user asks to create tests, add tests, write tests, update tests, test this file/component, new spec, or fix a failing or flaky test. Apply even when the user does not say 'Cypress' (e.g. 'create tests for this file'). Prefer cypress-explain when the user only wants to explain or review tests without changing code.

Builds and customizes assistant-ui chat UI from composable, unstyled @assistant-ui/react primitives that follow Radix-style part composition. Use when assembling or styling a custom Thread, Composer, message rendering, action bar, or branch picker from building blocks: ThreadPrimitive (.Root, .Viewport, .ViewportFooter, .Messages, .Empty, .ScrollToBottom, .Suggestions), ComposerPrimitive (.Input, .Send, .Cancel, .Attachments, .AddAttachment, .AttachmentDropzone, .Quote, .Dictate, .Queue), MessagePrimitive (.Parts/.Content, .GroupedParts, .Attachments, .Quote, .GenerativeUI, .Error), ActionBarPrimitive (.Copy, .Edit, .Reload, .Speak, .StopSpeaking, feedback, .ExportMarkdown), BranchPickerPrimitive, AttachmentPrimitive, ThreadListPrimitive, ThreadListItemPrimitive, plus ChainOfThoughtPrimitive, SelectionToolbarPrimitive, SuggestionPrimitive, QueueItemPrimitive, ErrorPrimitive, and AssistantModalPrimitive. Covers MessagePrimitive.Parts children render functions for text, image, reasoning,

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, challenge an approach, or mentions "grill me".

Inspect and edit the workspace's git-backed context repository (the GTM knowledge base of markdown/MDX files) and its runtime sandbox using the Cargo CLI. Use when the user wants to browse/read/write/edit context files, run a command in the sandbox, or inspect the context knowledge graph.

Prepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates documentation (flowcharts, user stories, inline comments).