Validates if proposed or in-progress work justifies investment before designing, planning, or building non-trivial features. Use when new evidence questions motivations or facts change.
npx claudepluginhub repozy/superpowers-optimizedThis skill uses the workspace's default tool permissions.
It's easy to treat a design request as unconditional — "user asked me to design X, so I'll design the best X I can." But the right answer is sometimes "X shouldn't exist." Without a deliberate check, effort flows into comprehensive designs that solve problems that are already handled, cost more than they're worth, or whose motivation evaporated when new evidence arrived.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
It's easy to treat a design request as unconditional — "user asked me to design X, so I'll design the best X I can." But the right answer is sometimes "X shouldn't exist." Without a deliberate check, effort flows into comprehensive designs that solve problems that are already handled, cost more than they're worth, or whose motivation evaporated when new evidence arrived.
The most dangerous failure mode isn't building something wrong — it's building something unnecessary with conviction.
Answer these three questions honestly before proceeding:
Does the problem actually exist, or is it already solved? Look at what's already in place. Check whether existing mechanisms already cover the gap. If the problem was hypothetical when the work was proposed, has it since been confirmed or disproven?
Is the proposed solution proportional to the problem? Compare the complexity, maintenance burden, and token/time cost of the solution against the severity and frequency of the problem. A rare edge case doesn't justify a framework. Three lines of code don't need an abstraction.
What's the cost of NOT building this? If the answer is "nothing breaks, things are just slightly less elegant" — that's a strong signal to skip it.