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.
npx agentmods add skills/peterfei/forge-skill/design-thinking-skillnpx skills add peterfei/forge-skill --skill design-thinking-skillgit clone --depth 1 https://github.com/peterfei/forge-skillWrote 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.
[](https://agentmods.dev/skills/peterfei/forge-skill/design-thinking-skill)<a href="https://agentmods.dev/skills/peterfei/forge-skill/design-thinking-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/design-thinking-skill.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00076 | $0.02705 |
| Opus 5 | $0.00038 | $0.01352 |
| Sonnet 5 | $0.00015 | $0.00541 |
| Haiku 4.5 | $0.00008 | $0.00270 |
Grade A, and why
design-thinking-skill 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
设计思维 · 思维工具
"Design thinking is a human-centered approach to innovation." — Tim Brown, IDEO CEO
激活条件与触发词
- 直接调用：「用设计思维分析...」「共情地图」「发散构思」
- 语义触发：面对模糊的产品/服务创新需求需深入理解用户
- 组合调用：「先用设计思维定义问题，再用精益创业验证」
方法框架概览
设计思维的核心是以用户共情为起点重新定义问题，它通过发散收敛交替、快速原型迭代、跨学科协作来避免为错误的问题找到正确的答案。
核心原理（3-7个，每个须附 ≥2 个跨域证据）
原理 1: 以用户共情为起点
一句话定义：不是问用户要什么，而是观察和感受他们真正经历什么。
跨域证据：
- 产品设计：IDEO 重新设计鼠标时工程师在木材店试手感而非画图（来源：Kelley, The Art of Innovation, 2001）
- 医疗保健：Embrace 婴儿保温袋团队去尼泊尔农村观察发现电力稀缺是真正瓶颈（来源：Stanford d.school, Embrace Case, 2008）
应用方式：在解决问题前花至少 30% 时间观察和访谈用户——看他们在什么情境下做什么。
局限：小样本观察可能不代表整个用户群，需要定量验证补充。
原理 2: 问题定义比解决方案更重要
一句话定义：为错误的问题找到最佳答案仍然是错误答案。
跨域证据：
- 企业转型：IBM 不卖更快的电脑而重新定义为"帮助 CEO 做更好的决策"（来源：Gerstner, Who Says Elephants Can't Dance?, 2002）
- 金融产品：Bank of America Keep the Change 不定义储蓄工具而定义为"刷卡自动存零钱"（来源：IDEO, Keep the Change Case, 2005）
应用方式：用 HMW 格式重定义问题至少 3 次，选最有启发性的角度。
局限：过度重定义可能导致拖延。需在"定义充分"和"开始行动"间平衡。
原理 3: 发散与收敛的节奏
一句话定义：先尽可能多地产生想法，再批判性地选择和聚焦。
跨域证据：
- 创新工厂：Google X 登月工厂鼓励不可能想法，但选择时用物理可行性严格过滤（来源：Teller, Google X, 2013）
- 动画制作：Pixar Braintrust 让所有人无保留贡献然后导演决定方向（来源：Catmull, Creativity Inc., 2014）
应用方式：发散阶段禁止说"不行""但是"。收敛阶段用用户数据而非个人偏好选择。
局限：发散需时间。紧急项目必须在限定时间内完成。
原理 4: 快速原型降低试错成本
一句话定义：最低保真度的原型在最快时间获得最真实的反馈。
跨域证据：
- 消费品：3M 开发 Post-it 用自制粘合剂测试（来源：3M, Post-it Origin Story）
- VR：Palmer Luckey 用泡沫板和手机屏做 Oculus 第一原型（来源：Luckey, Oculus Kickstarter, 2012）
应用方式：第一个原型须在 1 天内做出来。纸、胶带、PPT、对话脚本都是有效材料。
局限：低保真原型在某些领域（如手术器械）不仅无用还危险。
原理 5: 跨学科协作产生突破
一句话定义：不同背景的人碰撞出的方案任何单一学科都想不出。
跨域证据：
- 科技：初代 iPhone 诞生于软件工程师、硬件工程师和设计师的争论（来源：Isaacson, Steve Jobs, 2011）
- 社会创新：IDEO.org 项目中工程师和人类学家一起下田间（来源：IDEO.org, Field Guide to HCD, 2015）
应用方式：团队中必须有至少 3 种不同背景的人。没有则引入外部观点。
局限：跨学科协作沟通成本高，领导力不足会变各说各话。
操作协议（Agentic Protocol）
Step 1: 问题分类
适用信号：
- 需要理解"用户真正要什么"
- 产品定义模糊的早期创新阶段
- 需要打破按现有方案优化的思维定式
不适用信号：
- 问题已明确定义只差执行（适用 Agile/精益）
- 纯粹技术优化（适用 TRIZ）
- 紧急运营问题
Step 2: 设计思维式分析
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.
- 4d ago First seen · 198 lines · 76 tokens per session scan A 19f3ff05f515
design-thinking-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 2,705 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
ux-principles
User research, usability heuristics, user psychology, accessibility, inclusive design, user testing, and UX metrics.
omh-accessibility-audit
This is a Hermes-native accessibility-audit workflow skill.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).
design-system-adoption
Create adoption strategy and enablement materials to drive design system usage. Use when the system exists but teams ignore it. For contribution and versioning rules, use design-system-governance (design-systems).
ux-writing
Write interface copy — microcopy, error messages, empty states, and CTAs. Use when the words are the deliverable. For content structure and ownership, use content-strategy (ux-strategy).