Vibe to Prod

Guided 13-layer production-readiness self-check for a vibe-coded app. Use when the user asks "is this production ready", "what am I missing before launch", "ship check", "did I forget anything", or wants to harden an AI-generated MVP. Walks the 13 layers, runs cheap detections + manual tests, emits a per-layer PASS/GAP scorecard. Lighter than /audit (which is full due-diligence).

41 stars 1 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add wolverin0/claude-skills --skill vibe-to-prod
Manual install
git clone --depth 1 https://github.com/wolverin0/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/vibe-to-prod ~/.claude/skills/vibe-to-prod

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

From the SKILL.md

# Skill: vibe-to-prod

A fast, friendly self-check that walks the **13-layer production stack** against
the current project and tells the user what separates their demo from a product.
This is the "finish the last 20%" companion (see playbook `PRIN-1`).

**This is NOT `/audit`.** `/audit` is heavyweight due-diligence: isolated
subagents per domain, hard-stops, a dual-layer report, a deterministic verdict.
`vibe-to-prod` is a single-pass guided walk that a founder runs on their own app
to find gaps quickly. If the user wants exhaustive evidence-cited findings or an
acquisition-grade report, point them to `/audit` instead.

## Source of truth

Read the playbook first — it holds the layer definitions, thresholds, failure
modes, and manual tests this skill checks against:

```
view ~/.codex/context/production-readiness-playbook.md
```

Cite playbook anchors (`L1`-`L13`, `FM-*`, `CHK-*`) in every gap you report so
the user can read the depth. Do not paste the playbook back; reference it.

## When to use

- "Is my app ready to ship / go to production?"
- "What am I missing before launch?" / "Did I forget anything?"
- "Harden this" / "make this production-ready" on a vibe-coded MVP.
- After a demo works and the user wants to know the gap to a real product.

## Process

### 1. Detect the stack (don't assume)
Identify language, framework, DB, auth, hosting, and whether there's a
front-end bundle and a paid/AI API. Read the manifest (`package.json`,
Read the full skill on GitHub

Details

Skill name
vibe-to-prod
Path
skills/vibe-to-prod/SKILL.md
Repo updated
17 November 2026

FAQ

What does the Vibe to Prod skill do?

Guided 13-layer production-readiness self-check for a vibe-coded app. Use when the user asks "is this production ready", "what am I missing before launch", "ship check", "did I forget anything", or wants to harden an AI-generated MVP. Walks the 13 layers, runs cheap detections + manual tests, emits a per-layer PASS/GAP scorecard. Lighter than /audit (which is full due-diligence).

How do I install the Vibe to Prod skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add wolverin0/claude-skills --skill vibe-to-prod. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Vibe to Prod popular?

It lives in wolverin0/claude-skills, which has 41 GitHub stars and 1 forks.

Related skills

UI UX Pro Max

41

wolverin0/claude-skills

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism,

Frontend & Design

Audit Blind Spots

41

wolverin0/claude-skills

Walk the B1-B19 AI-to-AI blind-spot catalog systematically. Use during the audit pipeline AFTER hard-stops and Tambon hunt and BEFORE the 13 domain audits. Output: PRESENT / NOT PRESENT for each B-class with evidence. Findings flow into the appropriate domains.

AI, LLMs & Agents

Audit Decisions

41

wolverin0/claude-skills

Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.

Marketing, Sales & Business

Wage Hour QA

43

AlsKozlov/ru-legal

Q&A по нормам рабочего времени и оплаты. РФ specifics: ст.91 (40 ч/нед стандарт), ст.99 сверхурочные (max 4 ч в 2 дня и 120 ч/год), ст.103 сменный режим, ст.108 перерывы, ст.111 выходные, ст.113-114 праздники, ст.146-149 районные коэффициенты + северные надбавки + сверхурочные, ст.150 совмещение профессий, ст.152-154 повышенная оплата.

Testing & QA

Validate Piles Notation

45

pjt222/agent-almanac

Parse and validate PILES (Puzzle Input Line Entry System) notation for specifying piece fusion groups in jigsawR. Covers syntax validation, parsing into group lists, plain-language explanation, adjacency verification against puzzle results, and round-trip serialization. Use when validating user-supplied PILES strings before passing to generate_puzzle(), debugging fusion group issues, explaining the notation to users, or testing round-trip parse/serialize fidelity.

Testing & QAIn 1 list

Write Testthat Tests

45

pjt222/agent-almanac

Write comprehensive testthat (edition 3) tests for R package functions. Covers test organization, expectations, fixtures, mocking, snapshot tests, parameterized tests, and achieving high coverage. Use when adding tests for new package functions, increasing test coverage for existing code, writing regression tests for bug fixes, or setting up test infrastructure for a package that lacks it.

Testing & QAIn 1 list

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.