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 PANGKAIFENG/ai-product-manager-skills --skill customer-requirement-discoverygit clone --depth 1 https://github.com/PANGKAIFENG/ai-product-manager-skillsWrote 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/pangkaifeng/ai-product-manager-skills/customer-requirement-discovery)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/customer-requirement-discovery"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/customer-requirement-discovery/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/pangkaifeng/ai-product-manager-skills/customer-requirement-discovery"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/customer-requirement-discovery.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 | $0.00144 | $0.01871 |
| Opus 5 | $0.00072 | $0.00936 |
| Sonnet 5 | $0.00029 | $0.00374 |
| Haiku 4.5 | $0.00014 | $0.00187 |
Grade A, and why
customer-requirement-discovery 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
客户需求发现与澄清助手
Overview
帮助销售、客户成功和售前先在内部把模糊需求问清楚,再生成一份可一次发给客户的澄清清单。核心不是套固定问卷,而是识别当前最影响目标、方案、可行性、范围和验收的未知项。
默认输出 Markdown。用户明确要求 Excel 时,再调用可用的电子表格能力转换;本 Skill 不直接报价。
Phase Routing
先判断当前处于哪个阶段,只执行当前阶段:
- 内部需求发现:信息模糊,先向销售/客户成功追问。
- 客户澄清清单:内部信息已基本榨干,整理一次性外发问题。
- 客户回复回收:拿到客户回答后,形成需求摘要和可行性判断。
- 轻量 Demo:需求达到 Demo 门槛,或用户明确要求带假设先做概念验证。
- 下游交接:需要报价范围、正式 PRD 或研发实施时交给对应流程。
不要在第一轮同时完成所有阶段。内部需求发现阶段必须提出问题并等待内部用户回答。
Internal Discovery
读取 references/discovery-playbook.md,建立并持续更新需求台账:
- 已确认事实;
- 假设;
- 未知项;
- 冲突;
- 风险;
- 证据来源;
- 当前需求成熟度。
每轮只选择 1-3 个信息增益最高的问题。最多五轮,但信息足够时必须提前停止;不要为了用满轮次而继续问。优先利用销售已有信息,不要把可由内部确认的问题直接甩给客户。
问题选择原则:
- 回答会改变业务目标、用户流程、输入输出或验收;
- 回答会改变通用技术可行性、数据/集成路径、合规边界或 Demo 形态;
- 回答会消除当前事实冲突或高风险假设。
平台、数量、频率、时效、准确率不是固定必问项。只有它们确实会改变当前需求的实现或验收时才问。
每轮回复保持简洁:先用一小段复述本轮理解,再列本轮问题。不要提前生成最终客户清单。
Customer Clarification List
当内部用户明确要求生成清单、连续两轮没有新的高价值信息,或已到第五轮时,读取 references/output-templates.md,合并并重写问题:
- 必答不超过 8 个;
- 选答不超过 5 个;
- 一个问题只确认一个核心决策;
- 使用客户语言,避免内部技术术语;
- 给出建议回答方式或示例,使客户可以一次答完;
- 删除销售已经确认、可以内部推断或不会改变方案的问题;
- 对仍不可避免的假设,明确标记为“如未回复,将按此假设讨论,不构成交付承诺”。
清单只用于一次性收集客户信息,不包含内部可行性结论、产品能力底牌、成本或交期承诺。
Post-Reply Assessment
客户回复回来后,输出四部分:
- 内部需求评估:目标、角色、业务流程、输入、处理、输出、依赖、约束、验收、风险和剩余未知项。
- 客户确认版需求摘要:只写客户已确认内容;假设单列。
- 通用技术可行性:按
references/feasibility-and-boundaries.md判断为通常可行、有条件可行、需技术验证或当前不建议,并写出证据和条件。 - 下一步建议:补充验证、轻量 Demo、报价范围或正式 PRD。
不要把“AI 可以理解”“理论上能做”当作可行性证据。不要承诺准确率、平台数据稳定性、工期、价格或最终架构。
Conditional StyleWork Context
只有在用户或客户明确提到 StyleWork,或内部用户确认需求要落入 StyleWork 时,才读取:
references/stylework-product-context.mdreferences/stylework-ui-baseline.mdreferences/stylework-source-manifest.md
StyleWork 场景必须把两类判断分开:
- 通用技术可行性:不依赖某个产品,判断数据、模型、集成、流程、合规和验收是否成立。
- StyleWork 适配判断:映射为现有能力、直接复用、配置、扩展、新建或技术验证,并指出依据版本。
StyleWork 适配不能反向改写通用可行性。未经版本证据确认的 UI、菜单、数据源和第三方连接不得写成现有能力。
Lightweight Demo
满足以下任一条件时才进入 Demo:
- 目标用户、核心任务、主要输入、关键处理、期望输出和 Demo 验证目标已基本明确;
- 用户明确要求在信息不足时先做概念 Demo,并接受显式假设。
What ships with it
12 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.
- agents/openai.yaml 300 B
- assets/demo-brief-template.md 1.3 KB
- evals/evals.json 3.3 KB
- evals/green-forward-test.md 2.6 KB
- evals/red-baseline.md 2.1 KB
- evals/release-review.md 3.3 KB
- references/discovery-playbook.md 3.2 KB
- references/feasibility-and-boundaries.md 2.2 KB
- references/output-templates.md 1.8 KB
- references/stylework-product-context.md 3.3 KB
- references/stylework-source-manifest.md 3.0 KB
- references/stylework-ui-baseline.md 2.5 KB
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 · 129 lines · 144 tokens per session scan A 9abf1f26d097
customer-requirement-discovery is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 13d ago), licensed MIT. It adds 144 tokens to every session and 1,871 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.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
sequential-think
Multi-step reasoning engine for complex analysis and systematic problem solving. Use when: (1) Complex debugging scenarios with multiple layers, (2) Architectural analysis and system design, (3) Problems requiring hypothesis testing and validation, (4) Multi-component failure investigation, (5) Performance bottleneck…