aidd-jan

Conduct a thorough code review focusing on code quality, best practices, security, test coverage, and adherence to project standards and functional requirements. Use when reviewing code, pull requests, or completed epics.

Collaboratively review, explore, and discuss a pull request with the user, then post a unified review. Use when the user wants help reviewing a PR, wants to understand changes together, or craft review comments interactively.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Hotspot analysis: run churnex, interpret the ranked results, and recommend specific files to review or refactor with concrete strategies. Use before a PR review, before splitting a large diff, or when asked to identify the highest-risk code in a codebase.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Collaborate with non-technical stakeholders (CEOs, product managers, project managers) to build features and fix bugs. Only invoke when the user explicitly requests this mode (e.g. "/aidd-stakeholder-collaborating", "use stakeholder mode", "use the non-techie skill").

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Conduct a thorough code review focusing on code quality, best practices, security, test coverage, and adherence to project standards and functional requirements. Use when reviewing code, pull requests, or completed epics.

Guide for creating and iterating on custom Cursor subagents. Use when users want to create a new subagent (or update an existing one) — specialized AI assistants with their own context window, system prompt, and permissions.

Debug issues by investigating code, identifying root causes, and recommending fixes — without writing or modifying code. Use when the user reports a bug, unexpected behavior, an error, or asks to investigate or debug something.

Write production implementation code for features, components, functions, and APIs. Use when the user asks to implement, build, create, or add functionality — including React components, server functions, database facades, and general JS/TS code.

Write clear, direct, engaging prose for documentation, READMEs, blog posts, and other .md files. Use when the user asks to write, edit, or review documentation, markdown content, or any non-code prose.

Guide for creating and iterating on custom Claude Code subagents. Use when users want to create a new subagent (or update an existing one) — specialized AI assistants with their own context window, system prompt, tool access, and permissions.

Run a test-driven development cycle. Use when implementing features, fixing bugs via TDD, or when the user asks for TDD, red-green-refactor, or test-first development.

Write unit, functional, integration, and E2E tests following RITEway principles (Readable, Isolated, Thorough, Explicit). Use when the user asks to write tests, add test coverage, create a test suite, or test a function/module/component/page. Supports Vitest, bun:test, and Playwright.