Install
$ agentstack add skill-yangyue1974-product-thinking-playbook-product-thinking-playbook ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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
- [Scenario-first · 场景先于功能](principles/01-scenario-first.md)
- [Spec before code · 先定性,再动手](principles/02-spec-before-code.md)
- [Aesthetic as stance · 气质即立场](principles/03-aesthetic-as-stance.md)
- [Subtitle as promise · 副标题是承诺](principles/04-subtitle-as-promise.md)
II. Boundary 边界
- [Subtract, don't add · 做减法而非加法](principles/05-subtraction-over-addition.md)
- [Vision non-negotiable · 愿景不妥协](principles/06-vision-non-negotiable.md)
- [Product boundary = user's decision path · 产品边界 = 用户决策路径](principles/07-product-boundary.md)
- [Infrastructure mindset · 克制:不是基础设施该做的别做](principles/08-infrastructure-mindset.md)
III. Execution 执行
- [Decisive & meticulous · 决策果断,细节挑剔](principles/09-decisive-and-meticulous.md)
- [Borrow existing cognition · 借力已有认知](principles/10-borrowed-cognition.md)
- [Commander posture · 指挥者姿态](principles/11-commander-posture.md)
- [Content standards > technical standards · 内容标准 > 技术标准](principles/12-content-standards-first.md)
IV. Quality 品质
- [End-to-end fixes · 端到端修复](principles/13-end-to-end-fixes.md)
- [Design vs execution error · 设计错误 vs 执行错误](principles/14-design-vs-execution-error.md)
- [Experience before review · 先用再评](principles/15-experience-before-review.md)
- [Security = product quality · 安全 = 产品品质](principles/16-security-as-quality.md)
V. Closed Loop 闭环
- [Core metric bound to real engagement · 核心指标绑定真实投入](principles/17-real-engagement-metrics.md)
- [Persistence is trust · 持久化 = 信任基础](principles/18-persistence-is-trust.md)
- [Cross-platform parity + honest permissions · 跨端一致 + 权限诚实](principles/19-honest-parity.md)
- [Distribution is part of the product · 分发是产品的一部分](principles/20-distribution-is-product.md)
Case studies
Every principle above is grounded in a real project. The full development conversations:
- [Contra Code](case-studies/contra-code.md) · VS Code Contra overlay
- [AudioLib](case-studies/audiolib.md) · Audio library API service
- [Gospel Hub](case-studies/gospel-hub.md) · Gospel music aggregator
- [Spybook](case-studies/spybook.md) · Interactive detective fiction
- [Tarot](case-studies/tarot.md) · AI tarot consultation
- [Xianxia](case-studies/xianxia.md) · AI xianxia novel generation
How to invoke
In Claude Code:
> Using product-thinking-playbook, help me decide: should this feature go in now?
In your own head:
> Read through quick-reference.md, find the line that hurts most.
Three core postures · 三个核心姿态
English: > 1. Intent stands firm: scenario, aesthetic, vision — each clearly articulated, you'd push back on a one-character change. > 2. Execution holds up: decisive direction × meticulous detail; you're the commander, not the contractor. > 3. Loop closes: it works → it stands up to scrutiny → users can actually reach it.
中文: > 1. 立意定得住:场景、气质、愿景都能说清楚,别人改一字都不舒服。 > 2. 执行扛得住:果断拍板 × 细节不放过,自己是指挥者不是乙方。 > 3. 闭环做得到:能跑起来 → 经得起推敲 → 用户真的能用到。
Distilled from the full-process conversations of 6 shipped products · 2026-04 基于 6 个已上线产品的全过程对话提炼 Author @yangyue1974 · 43.group
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: yangyue1974
- Source: yangyue1974/product-thinking-playbook
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.