Agent
A review helper that checks whether a written specification gives an AI coding agent enough information to complete the work. It is used through the `/spec-review` command.
Agent
A review helper that checks whether a written specification gives an AI coding agent enough information to complete the work. It is used through the `/spec-review` command.
Agent
A business-analysis helper for reviewing software specifications, focusing on goals, user stories, acceptance criteria, rules, roles, permissions, and unusual cases.
Agent
An API and integration review helper for checking specifications that describe connections between software systems.
Agent
An agent that reviews a software specification along three questions: what is being built, how it will be built, and how it will be verified. It is designed to run through the /spec-review command.
Agent
A lightweight agent that reviews a software specification and identifies which areas it covers, such as data, APIs, infrastructure, user interfaces, risks, or AI. It also gives an early estimate of the specification's size or scope.
Agent
An agent that reviews the data parts of a software specification, acting like a data architect. It checks models, fields, relationships, database choices, storage, validation, and related rules.
Agent
A specialist subagent that reviews infrastructure, security, and non-functional requirements in technical specifications. It is designed to be called by a specification-review command, not directly.
Agent
A subagent that reviews a specification for things that could go wrong. It considers technical, business, operational, schedule, and security risks and suggests ways to reduce them.
Agent
A supporting agent that estimates the size and structure of a software specification. It looks at features, dependencies, data models, APIs, interfaces, integrations, business logic, and tests.
Agent
A subagent that reviews a specification from the perspective of writing tests. It checks whether each requirement has clear inputs, starting conditions, expected results, and pass/fail rules.
Agent
A helper for reviewing user-interface specifications, meaning plans for screens, forms, and how people use them. It checks user journeys, screen states, accessibility, and behavior on different device sizes.
Agent
A task-classification agent for deciding how incoming work should be handled. It accepts a web link, issue reference, or local file, retrieves the source content, saves the full specification temporarily, and classifies its complexity and signals.