itsvedantkumar

A written plan or numbered task list already exists and the ask is to carry it out: work the tasks in order, verify each, pause at the review checkpoint between phases.

Three or more independent units of work exist (files, packages, endpoints, rival approaches) and none needs another's result. Fans out N agents in ONE batched message, returns one table.

About to write implementation code or a bugfix and no test fails for that behaviour yet: write the failing test first, watch it fail, then write the minimum that passes.

Requirements are settled, nothing is written down about how, and the work is more than one edit: produce the plan document, file map, bite-sized tasks, one verification per task.

Apply when a struct, enum, or type can hold an invalid combination of fields that shouldn't compile. Redesign it so illegal states can't be represented — model the cases as separate variants.

While polishing UI that already renders, when visual quality is the bar: production-grade typography, motion, spacing, and brand-vs-product modes beyond the stock design level.

First, and only when the shape is undecided: explore intent and requirements for new capability before any plan or test. Skip it for a bugfix or a change whose shape is known.

Before writing a UI component in a React/Tailwind repo: pull a vetted accessible primitive from a shadcn-compatible registry (npx shadcn add). Hand-roll only what none has.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a spec or requirements for a multi-step task, before touching code

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use before hand-writing any UI component in a React/Tailwind repo - pull a vetted, accessible primitive from a shadcn-compatible registry (npx shadcn add); hand-roll only what no registry has.

No scripted way to prove this repo's UI, CLI, or service actually works. Generates an executable .claude/verify.sh gate plus a verify-<app> skill and feature map. Use for 'add verification here'.

Use when the user floats a plan, design or decision and wants it stress-tested, or says grill me, poke holes, what am I missing, or tear this apart. A round-based interview before code.

Use when building or polishing any UI where visual quality matters: production-grade typography, motion, spacing, and brand-vs-product design modes beyond the stock frontend-design bar.

Use before merging or shipping a change that only one reviewer (or none) has seen, especially auth, payments, or agent-written code, and on "tear this apart", "stress test this", "what am I missing".