claude

How to AI — Builder

Ship better software with Claude: test-first development, systematic debugging, code review, parallel agents, worktrees, MCP servers, and browser testing.

11 on GitHubby Ruben Hassid (How to AI)v1.0.0MITupdated 3 months agodevelopment
/

Plugin howtoai-builder from marketplace howtoai in rubenhassid1/howtoai-skills. Commands read from the repo's manifest — 12 days ago.

What it installs

Skills (7)

  • code-review

    Reviews someone's code, and handles feedback on yours — intent first, issues ranked by consequence, blocking vs non-blocking labeled. Use for "review this code", "review my PR", "look at this diff", or "how should I respond to this review comment". brand: How to AI by Ruben Hassid protocol: howtoai-

  • debug-systematically

    Finds the root cause of a bug instead of patching symptoms — reproduce, hypothesize, bisect, explain the mechanism. Use for "debug this", "why is this failing", "this test is flaky", "works locally but not in prod", or "I can't figure out why". brand: How to AI by Ruben Hassid protocol: howtoai-v1 s

  • git-worktrees

    Runs work in an isolated git worktree and closes the branch out cleanly. Use for "git worktree", "work on this in isolation", "finish this branch", "clean up my branch", "how do I merge this back", or removing a worktree without losing work. brand: How to AI by Ruben Hassid protocol: howtoai-v1 sour

  • mcp-builder

    Builds MCP servers an agent can actually use: tool design, results that fit the context budget, actionable errors, transport, auth. Use for "build an MCP server", "add an MCP tool", "expose my API to an AI assistant", or when tools get picked wrong. brand: How to AI by Ruben Hassid protocol: howtoai

  • parallel-agents

    Splits work across subagents running at once — what genuinely parallelizes, briefing each one cold, verifying what comes back. Use for "run these in parallel", "use subagents", "fan this out", "split this work up", or "delegate these tasks". brand: How to AI by Ruben Hassid protocol: howtoai-v1 sour

  • test-driven-development

    Drives implementation with the test written before the code — red, green, refactor — and knows when test-first is wrong. Use for "TDD", "write tests first", "test-driven", "add tests for this", "red green refactor", or adding a regression test. brand: How to AI by Ruben Hassid protocol: howtoai-v1 s

  • webapp-testing

    Drives a running web app in a browser to prove it works — real user flows, console and network evidence, failure paths, saved proof. Use for "test my app in the browser", "does this actually work", "check the page loads", or "verify the signup flow". brand: How to AI by Ruben Hassid protocol: howtoa

View source on GitHub

More from rubenhassid1/howtoai-skills

All 9 plugins →

Run the business side: cash flow and runway, margins, invoices, month-end close, tax prep, quarterly reviews, hiring, leads, complaints, and process docs.

12 skills

11

Design that doesn't look AI-generated: taste, visual styles, brand kits, interfaces, redesigns, motion, slides, and artifacts.

12 skills

11

Positioning, offers, pricing, launches, lead magnets, email campaigns, competitor teardowns, and the copy that sells it all.

11 skills

11

Content that sounds like you: LinkedIn posts, hooks, newsletters, video scripts, carousels, thumbnails, and performance analysis.

11 skills

11

SEO and AI-search visibility, pages at scale, paid ads, funnel diagnosis, experiments, measurement, onboarding, and referrals.

10 skills

11

Win and keep clients: call prep and recaps, cold outreach that gets replies, account research, support triage, replies, and help articles.

7 skills

11

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server

ChromeDevTools/chrome-devtools-mcp 55,181

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain How to AI — Builder?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins