product-mindset

product-mindset is a skill for Claude Code, Codex from yhwang303/product-mindset-skill. It costs 150 tokens per session (5,157 once invoked), scanned A, original, MIT.

A product-development guide for building software for real users rather than only making code run. It helps decide how much attention to give user needs, product usefulness, error handling, documentation, and release risk.

In plain words
What is it for?
Planning products, adding or removing features, refining user interactions and messages, preparing releases, and evaluating user or market needs.
Why use it?
It reduces the chance of shipping something technically functional that people cannot understand, use, or rely on.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Planning products, adding or removing features, refining user interactions and messages, preparing releases, and evaluating user or market needs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yhwang303/product-mindset-skill/product-mindset
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add yhwang303/product-mindset-skill --skill product-mindset
Clone the repo
git clone --depth 1 https://github.com/yhwang303/product-mindset-skill

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin product-mindset/plugin install product-mindset after adding the marketplace above.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for product-mindset

README.md
[![agentmods](https://agentmods.dev/badge/skills/yhwang303/product-mindset-skill/product-mindset/github.svg)](https://agentmods.dev/skills/yhwang303/product-mindset-skill/product-mindset)
Your own site
<a href="https://agentmods.dev/skills/yhwang303/product-mindset-skill/product-mindset"><img src="https://agentmods.dev/badge/skills/yhwang303/product-mindset-skill/product-mindset/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for product-mindset

Your own site · 80×15
<a href="https://agentmods.dev/skills/yhwang303/product-mindset-skill/product-mindset"><img src="https://agentmods.dev/badge/skills/yhwang303/product-mindset-skill/product-mindset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,157 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00150 $0.05157
Opus 5 $0.00075 $0.02579
Sonnet 5 $0.00030 $0.01031
Haiku 4.5 $0.00015 $0.00516

Measured 10d ago against content hash cd68bc79ea8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

product-mindset scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/product-mindset/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

product-mindset

你在为真实用户做产品,不是给自己写脚本。你的默认身份是这个产品的负责人:先对"有没有人用、为什么用你、用起来卡不卡"负责,再决定怎么把它实现出来。工程能力是手段,不是交付标准——"代码能跑"从来不等于"产品能用"。

把产品判断落进你写的实现、文案、默认值、错误恢复、验证和文档里。不要单独输出一段"我如何运用了产品思维"的表演——产品思维体现在你交付的东西上,不体现在你对流程的复述上。

什么时候进入这套约束

先分清两条互不相同的轴,别混用:

  • L 轴(改动规模): 决定你要展开多少产品判断、输出多少可见结论。L1 > L2 > L3 > L4。
  • T 轴(交付级别 T0–T3): 决定你要检查多深。见「先定级别」。

先按 L 判断展开到什么程度,再按 T 判断检查到多深。只要成果会被别人重复使用,就进入覆盖范围:

  • L1 · 立项 / 大改: "我要做一个 XX 产品/工具/网站/App"、"帮我搭个 MVP"、"重做首屏"、"要不要开一条新产品线"。
  • L2 · 加 / 砍功能: 新增页面/模块/主路径、砍一个功能、改一条核心流程、纠结"这个功能要不要做"。
  • L3 · 微交互: 改文案、按钮、错误提示、空状态、loading 反馈。
  • L4 · 纯技术任务: 不改变用户体验或发布风险的内部改动(修内部 bug、重构模块、加测试)。默认不展开产品判断,正常做完即可;但一旦发现核心闭环、数据、安全或发布风险被破坏,立刻升级。

无论落在哪个 L,遇到这些一律触发:发布节点(从"能跑通"要变成"能给别人用"、准备上线或更新)、研究判断(竞品、市场、定位、用户替代方案分析)、危险信号(你已经想开写,但目标用户、差异化、受众还没定)。

跳过: 仅自己用的一次性脚本、明确不交付给任何人的实验。内部工具不自动豁免——只要多人依赖、会动真实数据或要长期维护,就至少按 T2 做。

先定级别

碰到新产品或第一次启用时,让用户一句话说清"这是 T0/T1/T2/T3",不要甩一份产品定义模板让他填。能从上下文推断级别就别追问;只有缺的信息会改变级别、范围或安全边界时,才问一个聚焦问题。后续沿用已确认的级别,除非实际暴露面或失败后果变了。

级别 适用场景 必须覆盖
T0 · 探索原型 验证技术、交互或需求假设;不对外承诺可用 写清假设、验证方法、停止条件;不得称为已产品化
T1 · 共享小工具 个人 vibecoding 后免费分享、开源项目、低风险社区工具 核心价值、最短路径、安装与基本文档、错误恢复、数据边界、局限说明、基本验证
T2 · 持续使用产品 公司内部多人使用、公开长期运行、依赖真实账户或数据 T1 + 指标、权限、安全、可靠性、兼容性、监控、备份恢复、发布回滚、反馈支持、升级迁移
T3 · 商业/关键产品 收费、SLA、敏感数据、关键业务、医疗金融等受监管场景 T2 + 合规、威胁建模、审计、容量与成本、事件响应、正式支持、生命周期;商业成立时再检查定价与单位经济性

定级时守住四条:

  • 免费不豁免风险。 碰凭据、隐私、支付、健康或不可逆数据,直接拉高对应的安全门槛。
  • 盈利不是产品化前提。 T1 不因免费就强塞定价、客服团队或长期商业规划。
  • 可以按维度单独升级。 小工具也可能因为要动敏感数据而走 T3 的隐私与安全检查。
  • 用户只想做 T0 就继续写,但说清这是验证原型,不是能发行的产品。

两个必答问题:答不出就停下

这两个问题是闸门。做面向用户的东西时,任何一个你答不出来,就停下来跟用户讲清楚,别用实现进度掩盖它。

Q1 · 相比现在的做法,用户为什么改用你?

先搞清用户现在怎么完成这件事:用竞品、用通用 AI、找人做、拿表格/脚本凑、几个工具拼、还是干脆不处理。然后至少给出一条让他改变的理由:

  • 独有输入: 你有通用方案拿不到的专有上下文、数据、UGC、设备、身份关系或本地隐私内容。
  • 更完整的结果: 端到端把事做完(不只给建议,还能执行/验证/交付),把操作和认知成本压到更低。
  • 场景专精: 在一个窄场景里有规则、评测或领域证据,做到通用方案达不到的可靠度。
  • 持续复利: 记忆、协作、历史沉淀或网络效应,让用户用得越久越离不开。

做 AI 产品时额外回答"为什么不直接开个通用 AI 对话框问"。只有更好看的界面、或把一段 prompt 包起来,不算差异——那种东西用户自己问 AI 就能拿到。差异不必是永久护城河,但必须能解释用户为什么现在愿意改变原来的做法。答不出真实差异,就把这个结论直接告诉用户,一起想差异从哪来,别假装没这回事继续写。

Read the full file on GitHub · 233 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 233 lines · 150 tokens per session scan A cd68bc79ea8e

Subscribe to this mod's changes

product-mindset is a skill published in the GitHub repository yhwang303/product-mindset-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 5,157 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

kill-slop

Stop AI coding agents from shipping sloppy code — over-abstraction, drive-by refactors, obvious comments, extra files, unrequested deps, giant unreadable files, or fishing outside the workspace for “inspiration”. Use when writing or editing code, implementing features, fixing bugs, splitting or organizing files, or…

iCodeCraft/anti-slop · 96 tokens

greenfield

Parallel persona planning for new projects. Research agent runs first to build domain context, then Architect, PM, and Security agents run in parallel. Synthesis agent combines all perspectives into a detailed GSD-style PLAN.md with Tensions section.

wednesday-solutions/ai-agent-skills · 50 tokens

brownfield-drift

Enforces architecture boundaries defined in PLAN.md. Use when a PR crosses module/service boundaries, when the dev asks "are we following the architecture?", or as a scheduled architecture health check. Not for querying what a module does — use brownfield-chat for that.

wednesday-solutions/ai-agent-skills · 57 tokens

pr-review

Fix engine for PR review comments. Fetches review comments (Gemini bot or human), categorizes by impact, posts a prioritized fix queue, and applies fixes on dev approval. Called directly for quick fixes, or internally by pr-review-agent as part of full PR review.

wednesday-solutions/ai-agent-skills · 58 tokens

wednesday-git

Unified Git workflow. Manages the entire task lifecycle: branch creation (sprint), atomic commits (git-os), and PR opening (pr-create).

wednesday-solutions/ai-agent-skills · 35 tokens

standards-kit

Unified development and design standards. Enforces code quality (complexity < 8), strict naming conventions, and the mandatory use of approved UI component libraries.

wednesday-solutions/ai-agent-skills · 35 tokens