Principle Build the Lever

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.

107 stars 21 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Dimon94/skills --skill principle-build-the-lever
Manual install
git clone --depth 1 https://github.com/Dimon94/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/principle-build-the-lever ~/.claude/skills/principle-build-the-lever

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Build the Lever

When the work isn't trivial, build the tool that does it instead of doing it by hand.

A codemod, generator, or script does the work the same way every time and reruns for free. The tool is one artifact a reviewer can read and rerun to check the work. Hand-done changes can only be re-verified by redoing them. A deterministic script turns "trust me" into "run this".

Default to building the lever. Skip it only when the task is trivial, a couple of obvious edits you can see at a glance.

- Do the first unit by hand to learn the recipe, then build the tool. Prove it by rerunning it on that unit and diffing against your hand-done version. Make the lever safe to rerun.
- Codemod or script for edits, generator for repetitive files, a dump-to-sqlite query for analysis, a rerunnable check for verification.
- A deterministic lever beats fan-out. If the tool can process every unit in one pass, run it yourself. Don't fan out delegates to hand-apply what a script can do.
- When you fan work out to subagents, write the lever as a skill they all read: the recipe, the verification contract, and the do-not-touch fences in one artifact. Keep it outside the delegates' write scope so they can't quietly edit the contract.
- Applying this principle produces a file. If you cited it and there is no codemod, script, generator, or delegate skill in the diff, you didn't apply it.
- Commit the lever when the work outlives the session.
Read the full skill on GitHub

Details

Skill name
principle-build-the-lever
Repository
Dimon94/skills
Path
skills/principle-build-the-lever/SKILL.md
Repo updated
18 November 2026
Copies
Found in 3 GitHub repos

FAQ

What does the Principle Build the Lever skill do?

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.

How do I install the Principle Build the Lever skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Dimon94/skills --skill principle-build-the-lever. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Principle Build the Lever popular?

It lives in Dimon94/skills, which has 107 GitHub stars and 21 forks, and is included in 2 curated skill lists.

Related skills

Maintain Verification Skill

107

Dimon94/skills

Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".

Git & Code ReviewIn 2 lists21

Create Verification Skill

107

Dimon94/skills

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.

Software DevelopmentIn 2 lists21

How

107

Dimon94/skills

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

Software DevelopmentIn 2 lists21

Agent Browser

260

cafe3310/public-agent-skills

为 Agent 设计的自动化浏览器 CLI 工具,也能操作 Electron 桌面应用。当需要与网站交互(包括页面导航)时使用

AI, LLMs & Agents30

Wasm Wasmtime

293

mohitmishra786/low-level-dev-skills

WebAssembly runtime skill using wasmtime. Use when running WASM modules with wasmtime CLI, working with WASI preview2, using the component model, embedding wasmtime in Rust applications, limiting execution with fuel metering, or debugging WASM with DWARF in wasmtime. Activates on queries about wasmtime, WASI, WASM component model, wasmtime embedding, WIT interfaces, fuel metering, or server-side WebAssembly.

AI, LLMs & Agents36

Chat Screenrec Extractor

260

cafe3310/public-agent-skills

将群聊滚屏录屏视频切帧、交互式框选配置ROI、本地Apple Vision OCR识别,并通过去重算法与LLM整合输出分群Markdown聊天记录

AI, LLMs & Agents30

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.