subagent-driven-development

Automated task execution is achieved by dispatching a fresh subagent for each task in your implementation plan, followed by a two-stage review process for spec compliance and code quality. This ensures structured task management and iterative refinement within a single session.

Subagent-driven development is a process where independent subagents handle distinct coding tasks from a detailed plan. A rigorous two-stage review process checks spec compliance and code quality after each task, ensuring high-quality code through automated self-reviews.

Automated code reviews are set up by implementing a two-stage review process after each subagent completes a task. The first stage checks for spec adherence, and the second stage assesses code quality, ensuring high standards without manual oversight between steps.

Yes, you can execute a feature plan with multiple distinct coding tasks in a single session. The process manages development by dispatching a dedicated subagent for each task, followed by automated spec compliance and quality assessments.

Yes, a detailed feature plan with multiple distinct coding tasks is required. The Skill works by reading an implementation plan, such as the file 'docs/plans/feature-plan.md', and breaking it down into independent tasks for individual subagents to execute.

The best way to ensure spec compliance is using a two-stage review process after each task execution. The first stage rigorously checks the implemented code against the original specification, while the second stage evaluates overall code quality.