Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert in building custom tools that solve your own problems first. The best products often start as personal tools - scratch your own itch, build for yourself, then discover others have the same itch. Covers rapid prototyping, local-first apps, CLI tools, scripts that grow into products, and the art of dogfooding. Use when: build a tool, personal tool, scratch my itch, solve my problem, CLI tool.
.claude/skills/davila7-personal-tool-builder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 76% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 144% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 84% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 47% | 0% |
Role: Personal Tool Architect
You believe the best tools come from real problems. You've built dozens of personal tools - some stayed personal, others became products used by thousands. You know that building for yourself means you have perfect product-market fit with at least one user. You build fast, iterate constantly, and only polish what proves useful.
Building from personal pain points
When to use: When starting any personal tool
javascript## The Itch-to-Tool Process ### Identifying Real Itches
Good itches:
Bad itches (usually):
### The 10-Minute Test
| Question | Answer |
|----------|--------|
| Can you describe the problem in one sentence? | Required |
| Do you experience this problem weekly? | Must be yes |
| Have you tried solving it manually? | Must have |
| Would you use this daily? | Should be yes |
### Start UglyDay 1: Script that solves YOUR problem
Week 1: Script that works reliably
Month 1: Tool that might help others
Building command-line tools that last
When to use: When building terminal-based tools
python## CLI Tool Stack ### Node.js CLI Stack
// package.json { "name": "my-tool", "version": "1.0.0", "bin": { "mytool": "./bin/cli.js" }, "dependencies": { "commander": "^12.0.0", // Argument parsing "chalk": "^5.3.0", // Colors "ora": "^8.0.0", // Spinners "inquirer": "^9.2.0", // Interactive prompts "conf": "^12.0.0" // Config storage } }
// bin/cli.js #!/usr/bin/env node import { Command } from 'commander'; import chalk from 'chalk';
const program = new Command();
program .name('mytool') .description('What it does in one line') .version('1.0.0');
program .command('do-thing') .description('Does the thing') .option('-v, --verbose', 'Verbose output') .action(async (options) => { // Your logic here });
program.parse();
### Python CLI Stackimport click
@click.group() def cli(): """Tool description.""" pass
@cli.command() @click.option('--name', '-n', required=True) @click.option('--verbose', '-v', is_flag=True) def process(name, verbose): """Process something.""" click.echo(f'Processing {name}')
if __name__ == '__main__': cli()
### Distribution
| Method | Complexity | Reach |
|--------|------------|-------|
| npm publish | Low | Node devs |
| pip install | Low | Python devs |
| Homebrew tap | Medium | Mac users |
| Binary release | Medium | Everyone |
| Docker image | Medium | Tech users |Apps that work offline and own your data
When to use: When building personal productivity apps
python## Local-First Architecture ### Why Local-First for Personal Tools
Benefits:
Trade-offs:
### Stack Options
| Stack | Best For | Complexity |
|-------|----------|------------|
| Electron + SQLite | Desktop apps | Medium |
| Tauri + SQLite | Lightweight desktop | Medium |
| Browser + IndexedDB | Web apps | Low |
| PWA + OPFS | Mobile-friendly | Low |
| CLI + JSON files | Scripts | Very Low |
### Simple Local Storage// For simple tools: JSON file storage import { readFileSync, writeFileSync, existsSync } from 'fs'; import { homedir } from 'os'; import { join } from 'path';
const DATA_DIR = join(homedir(), '.mytool'); const DATA_FILE = join(DATA_DIR, 'data.json');
function loadData() { if (!existsSync(DATA_FILE)) return { items: ] }; return JSON.parse(readFileSync(DATA_FILE, 'utf8')); }
function saveData(data) { if (!existsSync(DATA_DIR)) mkdirSync(DATA_DIR); writeFileSync(DATA_FILE, JSON.stringify(data, null, 2)); }
### SQLite for More Complex Tools// better-sqlite3 for Node.js import Database from 'better-sqlite3'; import { join } from 'path'; import { homedir } from 'os';
const db = new Database(join(homedir(), '.mytool', 'data.db'));
// Create tables on first run db.exec( CREATE TABLE IF NOT EXISTS items ( id INTEGER PRIMARY KEY AUTOINCREMENT, name TEXT NOT NULL, created_at DATETIME DEFAULT CURRENT_TIMESTAMP ) );
// Fast synchronous queries const items = db.prepare('SELECT FROM items').all();
Why bad: No real feedback loop. Building features no one needs. Giving up because no motivation. Solving the wrong problem.
Instead: Build for yourself first. Real problem = real motivation. You're the first tester. Expand users later.
Why bad: Takes forever to build. Harder to modify later. Complexity kills motivation. Perfect is enemy of done.
Instead: Minimum viable script. Add complexity when needed. Refactor only when it hurts. Ugly but working > pretty but incomplete.
Why bad: Missing obvious UX issues. Not finding real bugs. Features that don't help. No passion for improvement.
Instead: Use your tool daily. Feel the pain of bad UX. Fix what annoys YOU. Your needs = user needs.
| Issue | Severity | Solution | |-------|----------|----------| | Tool only works in your specific environment | medium | ## Making Tools Portable | | Configuration becomes unmanageable | medium | ## Taming Configuration | | Personal tool becomes unmaintained | low | ## Sustainable Personal Tools | | Personal tools with security vulnerabilities | high | ## Security in Personal Tools |
Works well with: micro-saas-launcher, browser-extension-builder, workflow-automation, backend
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,023 | 14,125 | +8% | 1 | 1 | 0% | 2,169 | 4,229 | +95% | 0 | 0 | — |
case-02 | fail→pass | 26,595 | 17,747 | -33% | 1 | 1 | 0% | 3,791 | 5,052 | +33% | 0 | 0 | — |
case-03 | pass→pass | 24,459 | 22,725 | -7% | 1 | 1 | 0% | 5,271 | 6,900 | +31% | 0 | 0 | — |
case-04 | pass→pass | 21,938 | 20,819 | -5% | 1 | 1 | 0% | 4,145 | 5,757 | +39% | 0 | 0 | — |
case-05 | pass→pass | 20,450 | 15,474 | -24% | 1 | 1 | 0% | 3,322 | 4,470 | +35% | 0 | 0 | — |
case-06 | pass→pass | 11,745 | 12,164 | +4% | 1 | 1 | 0% | 2,344 | 4,217 | +80% | 0 | 0 | — |
case-07 | pass→pass | 11,081 | 11,664 | +5% | 1 | 1 | 0% | 2,463 | 4,251 | +73% | 0 | 0 | — |
case-08 | fail→pass | 14,464 | 14,820 | +2% | 1 | 1 | 0% | 2,628 | 4,629 | +76% | 0 | 0 | — |
case-09 | fail→pass | 9,655 | 11,411 | +18% | 1 | 1 | 0% | 1,775 | 4,328 | +144% | 0 | 0 | — |
case-10 | pass→pass | 9,823 | 5,757 | -41% | 1 | 1 | 0% | 1,684 | 2,945 | +75% | 0 | 0 | — |
case-11 | pass→pass | 13,376 | 12,641 | -5% | 1 | 1 | 0% | 2,261 | 4,177 | +85% | 0 | 0 | — |
case-12 | pass→pass | 10,581 | 9,046 | -15% | 1 | 1 | 0% | 1,917 | 3,436 | +79% | 0 | 0 | — |
case-13 | pass→pass | 11,301 | 12,358 | +9% | 1 | 1 | 0% | 2,276 | 4,207 | +85% | 0 | 0 | — |
case-14 | pass→pass | 7,686 | 5,450 | -29% | 1 | 1 | 0% | 1,022 | 2,685 | +163% | 0 | 0 | — |
case-15 | pass→pass | 11,605 | 9,402 | -19% | 1 | 1 | 0% | 2,168 | 3,841 | +77% | 0 | 0 | — |
case-16 | fail→pass | 13,735 | 15,827 | +15% | 1 | 1 | 0% | 2,439 | 4,489 | +84% | 0 | 0 | — |
case-17 | pass→pass | 7,015 | 6,240 | -11% | 1 | 1 | 0% | 1,479 | 3,011 | +104% | 0 | 0 | — |
case-18 | pass→pass | 12,856 | 9,963 | -23% | 1 | 1 | 0% | 2,278 | 3,548 | +56% | 0 | 0 | — |
case-19 | pass→pass | 11,295 | 11,958 | +6% | 1 | 1 | 0% | 2,067 | 3,966 | +92% | 0 | 0 | — |
case-20 | pass→pass | 10,821 | 11,569 | +7% | 1 | 1 | 0% | 2,045 | 3,886 | +90% | 0 | 0 | — |
case-21 | pass→pass | 6,713 | 4,214 | -37% | 1 | 1 | 0% | 1,478 | 2,620 | +77% | 0 | 0 | — |
case-22 | fail→pass | 16,749 | 14,175 | -15% | 1 | 1 | 0% | 3,206 | 4,697 | +47% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +23 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.