warpdotdev

Feature specifications do not automatically become accurate, publishable documentation. This skill verifies implementation details, confirms audience and structure, drafts MDX, and prepares a reviewable pull request.

Agent skills are difficult to evaluate from configuration alone. This skill reviews local conversations, scores outcomes, and drafts evidence-based improvements.

Pull request feedback can be difficult to track, implement, and answer consistently. This skill guides each decision, validates accepted changes, and previews GitHub responses before posting.

Large investigations can flood the primary agent context with irrelevant files and logs. This skill delegates read-only research and returns concise conclusions with cited evidence.

Complex pull requests are difficult to understand from diffs alone. This skill creates a validated visual walkthrough of architecture, data flow, dependencies, and user actions.

Complex decisions can suffer from narrow analysis and hidden assumptions. This skill coordinates diverse agents, compares their evidence, and produces one actionable recommendation.