What problem does it solve? Hand-done edits, migrations, and analyses cannot be re-verified without redoing the work, leaving reviewers with nothing to rerun. This Skill enforces a working principle: for any non-trivial task, build a deterministic tool (codemod, script, generator, or delegate skill) that performs or proves the work, so the artifact itself becomes reviewable and rerunnable. ## Core Features & Use Cases - Lever-First Workflow: Do the first unit by hand to learn the recipe, then build the tool and prove it by diffing its output against the hand-done version. - Tool Selection Guidance: Choose codemods or scripts for edits, generators for repetitive files, dump-to-sqlite queries for analysis, and rerunnable checks for verification. - Subagent Coordination: When fanning work out to subagents, write the recipe, verification contract, and do-not-touch fences as a shared skill outside the delegates' write scope. - Use Case: While migrating hundreds of files to a new API, write a codemod, verify it against one hand-migrated file, rerun it across the codebase, and commit it so reviewers can rerun it instead of trusting manual edits. ## Quick Start Ask the agent to apply the build-the-lever principle to your current migration or refactoring task so it produces a rerunnable script instead of hand edits.
