principle-build-the-lever

Guides building rerunnable codemods, scripts, and generators instead of manual edits.

136|8|Updated May 9, 2026
One-click install
npx skills add https://github.com/Sma1lboy/rove --skill principle-build-the-lever-sma1lboy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: principle-build-the-lever
Source: https://github.com/Sma1lboy/rove/tree/main/.agents/skills/pstack/skills/principle-build-the-lever
Command: npx skills add https://github.com/Sma1lboy/rove --skill principle-build-the-lever-sma1lboy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Non-trivial work done by hand is slow, inconsistent, and impossible for a reviewer to re-verify without redoing it. 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 result is a rerunnable artifact rather than a one-off manual effort. ## Core Features & Use Cases - Lever-First Workflow: Do the first unit by hand to learn the recipe, then build a tool that reproduces it, verified by diffing the tool's 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, encode the recipe, verification contract, and do-not-touch fences as a shared skill outside the delegates' write scope. - Use Case: Migrating hundreds of files to a new API? Instead of editing each file manually, write a codemod, prove it on one file against your hand edit, then rerun it across the codebase and commit it for future reruns. ## Quick Start Ask the agent to apply the build-the-lever principle to your next migration or bulk edit so it produces a rerunnable script instead of manual changes.

Frequently Asked Questions about principle-build-the-lever

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate repetitive code edits across many files?▼

Do the first edit by hand to learn the recipe, then write a codemod or script that reproduces it. Verify the tool by rerunning it on that first file and diffing against your manual version, then run it across all remaining files.

When should I write a script instead of doing edits manually?▼

Build a tool for any non-trivial work, including one-off tasks where the script is what makes the result checkable. Skip it only for genuinely trivial changes, meaning a couple of obvious edits you can verify at a glance.

How do I keep subagents consistent when delegating bulk work?▼

Write the recipe, verification contract, and do-not-touch fences as a single skill file that every subagent reads. Keep that file outside the delegates' write scope so they cannot quietly modify the shared contract.

What are the limitations of hand-done bulk changes?▼

Hand-done changes can only be re-verified by redoing them, so a reviewer must trust the author blindly. A deterministic script turns verification into a rerun, which is why this principle treats the tool itself as the reviewable artifact.

Should I commit the automation script after the task is done?▼

Commit the tool whenever the work outlives the session, so future runs rerun it instead of redoing the work. Keep the script minimal per the laziness protocol: the smallest tool that does or proves the job, never a framework.