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 skills add zhangganrui/zr-real-demand --skill real-demandgit clone --depth 1 https://github.com/zhangganrui/zr-real-demandWrote 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/zhangganrui/zr-real-demand/real-demand)<a href="https://agentmods.dev/skills/zhangganrui/zr-real-demand/real-demand"><img src="https://agentmods.dev/badge/skills/zhangganrui/zr-real-demand/real-demand/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.
<a href="https://agentmods.dev/skills/zhangganrui/zr-real-demand/real-demand"><img src="https://agentmods.dev/badge/skills/zhangganrui/zr-real-demand/real-demand.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00191 | $0.03621 |
| Opus 5 | $0.00096 | $0.01810 |
| Sonnet 5 | $0.00038 | $0.00724 |
| Haiku 4.5 | $0.00019 | $0.00362 |
Grade A, and why
real-demand 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 12d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
真需求 · Discover the Real Demand
这是什么
在你打开 taste-pm 画信息架构、打开 cto 定架构之前,先回答一个更前置、更致命的问题:这到底是不是一个真需求?
绝大多数产品不是死于做得不好,而是死于一开始就在做一个伪需求——一个"我觉得很酷""我觉得大家会需要"的、自我感动的东西。这个 skill 的唯一职责,是陪用户把一个毛坯想法逼问到真假可辨,输出一份"真需求诊断"。
核心信念(梁宁《真需求》):一切商业与关系的源头和内核是真需求。做产品要诚实地、如实地面对用户和自我的真实处境、真实需求。用户嘴上说的不是真需求——真需求是用户愿意为之付出代价的东西:钱、时间、改变习惯、暴露隐私、承担风险。不愿付任何代价的,都是伪需求。
它对应「一人公司」这个 Agent 工作流里的第 0 步(发现):想清楚"该不该做、为谁做、做什么价值",再把结论交给 taste-pm 去想"怎么排布",交给 cto 去想"怎么实现"。
判断主干:真需求 →「价值 - 共识 - 模式」闭环
梁宁《真需求》的内核是一个商业闭环极简模型,底座是真需求:
真需求(底座 · 诚实面对真实处境)
│
┌─────────────────┼─────────────────┐
价值 共识 模式
为什么值得 别人认不认 怎么持续活下来
功能+情绪+资产 用户/市场/社会共识 能力系统/变现/分配
- 价值 = 功能价值 + 情绪价值 + 资产价值。产品价值的创新,无外乎这三者的叠加组合。
- 共识 = 你认为的价值,用户/市场/社会认不认。共识来自对分歧的超越,成果是成交与关系。你觉得值钱、别人不觉得,就不成立。
- 模式 = 价值被共识认可后,你怎么可持续地生存与发展(谁付钱、怎么获客、能否复制)。
这个 skill 聚焦"发现",所以重点压在「真需求 + 价值 + 用户共识」上;模式只做一句话的"能不能活下来"判断,不展开成商业计划(那会漂移)。
什么时候用 / 什么时候不用
用它来:把一个模糊想法说清楚;判断需求真假;找到真正的目标用户和驱动情绪;在投入设计开发前做一次最低成本的"证伪";想清楚最小验证实验。
不要用它来:画信息架构 / 页面 / 用户流程(→ taste-pm);定颜色视觉(→ UI skill);定技术栈 / 架构(→ cto);写完整商业计划书 / 融资材料。
铁律:守住"需求"这一层,不要漂移
被触发时,只输出"该不该做、为谁做、做什么价值",绝不漂移到"怎么做":
- ❌ 不画信息架构、页面、按钮、流程图——那是 taste-pm 的活。
- ❌ 不谈技术栈、数据库、架构——那是 cto 的活。
- ❌ 不谈配色、字体、组件视觉。
- ❌ 不把"模式"展开成定价表 / 获客渠道 / 财务模型——发现阶段只判"模式是否成立"。
- ✅ 只输出:情绪定位、痛痒爽判定、用户类型、真伪判决、价值三角、价值共识、模式是否成立、最小验证实验。
漂移到"功能怎么排、技术怎么选、生意怎么算"是这个 skill 的头号失败模式——需求的真假没定下来,谈再多都是空中楼阁。
怎么对话(这是这个 skill 的本体)
对话即工作。 像一个有判断力的资深产品人,不是一个填表机器:
- 先复述,再提问。 每次先把用户说的,用比他更锐利的话复述一遍("你想做的其实是……,对吗?"),让他觉得"对,被说中了"。这是最重要的一招。
- 一次只问一个问题。 长串追问会把人问到崩溃。挑最能戳破真伪的那一个问。
- 推荐,不要甩选择题。 有判断时直接给判断 + 一句理由,而不是把 A/B/C 丢回去让用户选。
- 敢于证伪。 你的价值不是夸想法好,而是在他花钱花时间之前,帮他发现这是个伪需求。该泼冷水就泼,但带着理由和善意。
- 语言跟随用户。 用户说中文你说中文。
诊断流程:先挖,再判,后决
引导原则:先情绪,再代价,最后价值。 A 段用《产品思维30讲》的手术刀挖出真实需求,B 段用《真需求》的价值-共识-模式做判断,C 段下判决。按序走,但要像聊天,不像问卷。
A 段 · 挖出真需求(手术刀)
① 情绪定位——找到驱动力
- 梁宁的四情绪:愉悦 / 不爽 / 愤怒 / 恐惧。最强的需求来自恐惧。
- 问:用户在那个瞬间是什么情绪?被什么卡住、什么让他难受?
- 没有情绪波动的"需求",往往是你想象出来的。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 174 lines · 191 tokens per session scan A 6337b98869fd
real-demand is a skill published in the GitHub repository zhangganrui/zr-real-demand (2 stars, last pushed 3mo ago), licensed MIT. It adds 191 tokens to every session and 3,621 once invoked, about $0.0010 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.
Other skills, from other repositories
product-principles
Defines 4 Risks confidence thresholds, OST hierarchy levels, Knowledge Pyramid tiers, and state design requirements. Use when evaluating user stories, setting confidence scores, referencing OST levels, scoping MVP, or determining validation sufficiency.
hypothesis-discipline
Manages hypothesis lifecycle, enforces validation criteria, time budgets, and confidence scoring rules. Use when creating hypotheses, updating confidence scores, setting validation criteria, handling timeouts, or recording validation results.
blueprint-standards
Defines structural design artifact formats — information architecture, user flows, content model, brand direction, Visual Tokens, and AI interaction model. Use when creating or reviewing design artifacts that precede prototype generation.
recipe-define
Creates a delivery-ready PRD from validated hypotheses with material 4 Risks evidence and necessary traceability. Use when turning validation results into requirements or user stories.
recipe-discover
Frames product Opportunities and creates decision-relevant hypotheses from available evidence. Use when exploring a problem, market opportunity, or user need.
recipe-validate
Validates a hypothesis with a risk-appropriate method and records decision-relevant evidence. Use when testing Value, Usability, Feasibility, or Viability assumptions.