plan-workflow

Deep research for application features including external APIs, business logic, technical specifications, UX analysis, and recommendations. Creates feature-spec.md ready for plan-workflow.

Create detailed parallel implementation plans with task dependencies and file paths. Step 2 of the planning workflow, requires shared.md from shared-context.

Unified planning workflow - research, analyze, and generate parallel implementation plans in one command. Combines shared-context and parallel-plan with checkpoint support and optimized agent deployment.

Create shared context document with relevant files, patterns, tables, and docs for a new feature. Step 1 of the planning workflow.

Use this agent when the user discusses researching a new feature, needs comprehensive analysis before building something, or wants to understand external APIs, business requirements, and technical specifications for a planned feature. This agent orchestrates deep research across multiple dimensions and produces a feature-spec.md. <example> Context: User is planning a new feature and needs research before implementation. user: "I want to add Plex integration to the app. Can you research the APIs and figure out what we need?" assistant: "I'll use the feature-researcher agent to conduct comprehensive research on Plex integration including API analysis, business requirements, technical specs, and UX patterns." <commentary> User needs multi-dimensional research for a new feature involving external APIs. The feature-researcher agent orchestrates parallel research agents to produce a complete feature spec. </commentary> </example> <example> Context: User wants to understand requirements before building a feature. user: "Before we build the payment system, I need a full analysis - what Stripe APIs do we need, what the user flow looks like, and what the technical architecture should be." assistant: "Let me use the feature-researcher agent to research the payment system across all dimensions - external APIs, business logic, technical architecture, and UX." <commentary> User explicitly wants comprehensive pre-implementation research covering external services, UX, and architecture - exactly what the feature-researcher agent does. </commentary> </example> <example> Context: User mentions needing a feature spec or research document. user: "I need a feature spec for the new dashboard before we start planning tasks." assistant: "I'll deploy the feature-researcher agent to create a comprehensive feature-spec.md with research on all aspects of the dashboard feature." <commentary> User needs a feature spec document, which is the primary output of the feature-researcher agent. </commentary> </example>

This skill should be used when the user asks to "research a feature", "create a feature spec", "analyze external APIs for a feature", "plan feature research", "generate a feature-spec.md", or mentions needing comprehensive research before implementing a new feature. Also triggered by the /feature-research command. Creates feature-spec.md ready for plan-workflow.

Create detailed parallel implementation plans by orchestrating analysis agents and validation, then synthesizing dependency-aware tasks into parallel-plan.md. Use after shared-context to prepare implementation-ready planning artifacts.

Unified planning workflow - research, analyze, and generate parallel implementation plans in one command. Combines shared-context and parallel-plan with checkpoint support and optimized agent deployment.

Create shared context documentation for a feature by orchestrating parallel research agents, writing research artifacts, and synthesizing verified architecture, patterns, integrations, and docs into shared.md. Use as Step 1 before parallel-plan when preparing implementation context.