AI ワークフローツール

AI Coding リリースチェックリスト

AI コーディングツールで作成・変更したアプリを公開前に確認するためのチェックリストをローカルで生成します。

Local AI workflow tool

AI Coding Ship Checklist

Generate a launch checklist for AI-generated code. Nothing is uploaded; checked items and notes stay in this browser.

進捗0/15
Must0/7
Should0/7
Optional0/1
Cursor / editor agent · Web app / landing page · Public website

Open the changed files in Cursor, Copilot, Claude Code, Codex, Windsurf, or your git client and confirm the agent only touched the intended scope.

text-diff-checker

Run the command that your host will run, such as npm run build, next build, mvn package, flutter build, or the platform build step. A dev server is not enough.

Open a fresh browser profile or incognito window and complete the key path as a real user: landing, sign in if needed, create or submit data, and finish the expected action.

Search for secrets, service-role keys, private tokens, test credentials, and variables accidentally exposed to the frontend after AI edits.

jwt-decodertext-diff-checker

Confirm build command, output directory, runtime version, region, environment variables, custom domain, CORS, redirects, and callback URLs.

Search visible pages, README, errors, empty states, and meta tags for lorem ipsum, TODO, fake testimonials, model disclaimers, or generic marketing text.

text-diff-checkermarkdown-preview

Check 360px to 430px widths for horizontal scroll, fixed buttons covering inputs, clipped dialogs, overflowing cards, and long words breaking layout.

Force failed network calls, empty lists, invalid forms, expired sessions, and 404 or not-found states. AI-built happy paths often miss these.

Run the checks that exist in the project. If there are no automated tests, write a short manual test list instead of pretending coverage exists.

Document install, local dev, build, deploy, required env vars, known limitations, and rollback steps so the next AI session or teammate has context.

markdown-preview

For payments or external services, confirm repeated webhook delivery does not create duplicate orders, credits, emails, or records.

For public pages, inspect meta title, description, canonical URL, robots rules, sitemap inclusion, Open Graph, and whether placeholder pages are indexable.

markdown-preview

Make sure headings, FAQ answers, definitions, and tool descriptions give short, factual answers that search engines and AI assistants can quote accurately.

For APIs or external integrations, verify request payload shape, status codes, auth headers, and cURL examples that AI may have invented.

curl-converterjson-formatter

Tab through the main UI, verify focus is visible, labels are attached to inputs, buttons have names, and dialogs can be closed without a mouse.

このツールは AI ワークフローツール の一部です。 ワークフロー全体を見る · 公開前の AI Coding ワークフローチェックリスト

このツールについて

AI Coding Ship Checklist は、AI で作成したアプリや AI 支援のコード変更向けのローカル公開前チェックリストです。Cursor、GitHub Copilot、Claude Code、Codex、ChatGPT、Windsurf、Replit Agent、Bolt、Lovable などを使った後、モデルがコードを書いた後に必要な確認作業を整理します。

使い方

AI coding source、project type、stack、launch goal、risk feature を選ぶと、公開前または次の AI agent への handoff 前に使える checklist を生成します。

  1. コードの作成方法を選びます: editor agent、Copilot、CLI agent、chat からコピー、vibe coding builder、または mixed work。
  2. project type、stack、launch target、auth、payments、database、public SEO、i18n、file upload、admin、external API などを選択します。
  3. Must、Should、Optional のチェックを進め、build、env、mobile、SEO、release の証拠メモを残します。
  4. Markdown report をコピーし、PR、issue、README、release note、AI handoff prompt に使います。

機能

この初版はコードをアップロードせず、モデルを呼び出さず、品質を自動判定しません。選択内容からローカル checklist を生成します。

  • Web app、API、mobile release、browser tool、vibe-coded prototype 向けのルール。
  • build、env vars、secrets、auth、payments、webhooks、SEO、mobile、docs、observability、rollback のチェック。
  • 設定、完了状態、証拠メモをブラウザー内に保存。
  • PR、issue tracker、release note、AI agent handoff 向けの Markdown export。

よくある質問

What is an AI coding checklist?

An AI coding checklist is a release checklist for code generated or modified with AI coding tools. It focuses on verification: diff review, build commands, tests, secrets, deployment config, auth, payments, SEO, mobile layout, and release notes.

Does this tool scan my repository?

No. The checklist is generated locally from the options you choose. It does not upload files, read your repository, call an AI model, or automatically judge code quality.

Who is this useful for?

It is useful for developers using Cursor, Copilot, Claude Code, Codex, or Windsurf, and for non-developers shipping apps from Bolt, Lovable, Replit Agent, or ChatGPT-generated code.

Can I use it for vibe coding projects?

Yes. Select the AI-built prototype or vibe coding builder options. The checklist will include prototype limits, placeholder copy, env vars, mobile checks, and public launch risks.