Product Thinking Playbook

A decision-making playbook for solo product builders. 20 principles across 5 dimensions — Intent, Boundary, Execution, Quality, Closed Loop — extracted from 6 shipped products. Use when starting a new product, stuck on a product decision, reviewing your own work, or collaborating with an AI coder who can write anything but doesn't know what to build.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add yangyue1974/product-thinking-playbook --skill product-thinking-playbook
Manual install
git clone --depth 1 https://github.com/yangyue1974/product-thinking-playbook.git /tmp/product-thinking-playbook
mkdir -p ~/.claude/skills
cp -r /tmp/product-thinking-playbook/. ~/.claude/skills/product-thinking-playbook

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

From the SKILL.md

# Product Thinking Playbook

> A judgment framework for indie developers and product people.  
> Not a "product manager handbook" — a record of what's actually going through your head *in the moment* you make a call.  
> 一套给独立开发者 / 产品人的判断框架。不是"产品经理手册",是把"做决策的那一刻在想什么"写下来。

**Each principle file below is bilingual (English first, then 中文).**

## When to use this skill

Open the corresponding principle before making the call:

- **Starting a new product** → `principles/01-scenario-first.md` → `principles/02-spec-before-code.md`
- **Feature creep, can't stop adding** → `principles/05-subtraction-over-addition.md`
- **Working with AI, product feels off** → `principles/11-commander-posture.md`
- **Have a batch of bugs, don't know where to start** → `principles/13-end-to-end-fixes.md` + `14-design-vs-execution-error.md`
- **Product "works" — what's next?** → `principles/17-real-engagement-metrics.md` + `20-distribution-is-product.md`
- **Quick lookup** → `quick-reference.md`

新产品立项 / 功能蔓延 / 收不住手 / bug 收不住 —— 打开对应的原则文件再做决定。

## Five dimensions

| Dimension | Answers | Principles |
|---|---|---|
| **I. Intent 立意** | Why does it exist? For whom? | 01–04 |
| **II. Boundary 边界** | What NOT to do? | 05–08 |
| **III. Execution 执行** | How to ship the judgment? | 09–12 |
| **IV. Quality 品质** | How to make it stick? | 13–16 |
| **V. Closed Loop 闭环** | When is it "done"? | 17–20 |

## 20 principles · index

**I. Intent 立意**
1. [Scenario-first · 场景先于功能](principles/01-scenario-first.md)
Read the full skill on GitHub

Details

Skill name
product-thinking-playbook
License
MIT
Repo updated
15 April 2026

FAQ

What does the Product Thinking Playbook skill do?

A decision-making playbook for solo product builders. 20 principles across 5 dimensions — Intent, Boundary, Execution, Quality, Closed Loop — extracted from 6 shipped products. Use when starting a new product, stuck on a product decision, reviewing your own work, or collaborating with an AI coder who can write anything but doesn't know what to build.

How do I install the Product Thinking Playbook skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add yangyue1974/product-thinking-playbook --skill product-thinking-playbook. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Product Thinking Playbook popular?

It lives in yangyue1974/product-thinking-playbook, which has 6 GitHub stars and 0 forks.

Related skills

Session Detail

6

thebpandey/session-detail

Create a detailed Markdown session archive or recovery handoff. Trigger on "session detail", "detailed session summary", "session archive", "full session detail", "full session-detail", "session-detail full", "session detail full", "session detail incremental", and "session-detail inc". Also use at a milestone when the human has authorized milestone archives. Preserve exactly two sections: session_full and context_updates. Use verified checkpoints for incrementals; otherwise produce a full archive from available evidence. Codex writes a local file first.

Writing & Content

Linkedin Profile Perfector

6

EricTechPro/linkedin-profile-perfector

Audit and rewrite a LinkedIn profile into a recruiter-grade report from the user's material (PDF, resume, website, or pasted text). Use when the user asks to optimize, improve, review, or audit their LinkedIn profile, headline, About section, or experience, or wants help with personal branding, LinkedIn for job search, LinkedIn for consulting or clients, or growing a creator profile. Runs a 7-step adaptive intake, scores every section 0-10, applies a recruiter 6-second-scan, produces Current-to-Optimized rewrites, and renders report.md plus report.html. Four goal modes re-weight the pipeline:

Writing & Content

Skill Registry

6

dungnotnull/game-account-phishing-protection-agent-skill

Complete documentation of skill registration, resolution, execution, and validation for the game-account-phishing-protection harness. Includes input/output JSON schemas, dependency management, and lifecycle hooks.

Writing & Content

Linkedin Post Max

6

noah-vl/linkedin-post-max

Use when the user wants to draft or refine a LinkedIn post, develop a vague idea into a post, brainstorm post ideas, discover fresh web content to react to ('find me some inspo', 'what's popping'), paste an actually-published post back to refine voice ('post-back for <author>'), fold an author's accumulated learnings into the canonical voice file ('fold in <author>'s learnings'), set up a new author voice profile, or maintain a personal/company LinkedIn presence with consistent voice across many posts and multiple authors.

Writing & Content

Stop Slop Zh

6

wdkang123/stop-slop-zh

Remove predictable AI writing patterns from Chinese prose. Use when drafting, editing, rewriting, or reviewing Chinese blogs, reports, essays, product analysis, and social posts to make them specific, natural, and authorial without changing facts.

Writing & Content

Humanizer Hu

6

Dexxter182/humanizer-hu

Magyar szöveg megfogalmazási szabályai generáláshoz: ne hangozzon AI-nak, és csak azt állítsa, amit a kérés vagy a forrás tartalmaz. Hívd meg, amikor magyar user storyt, specifikációt, ADR-t, jegyet, dokumentációt, e-mailt vagy ügyfélszöveget írsz: a hívó feladat adja a szerkezetet, ez a skill a nyelvet. Akkor is, ha a kérés "humanizáld" vagy "írd emberi hangon". Csak magyar folyó szövegre; gép-gép kimenetre (JSON, log, séma, parancs) ne.

Writing & Content

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