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 prd-architectgit 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/prd-architect)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/prd-architect"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/prd-architect/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/prd-architect"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/prd-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00196 | $0.06658 |
| Opus 5 | $0.00098 | $0.03329 |
| Sonnet 5 | $0.00039 | $0.01332 |
| Haiku 4.5 | $0.00020 | $0.00666 |
Grade A, and why
prd-architect 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD 架构师（prd-architect）
中文速查
- 中文名：PRD 架构师 / 需求文档起草
- 英文稳定名：
prd-architect - 你可以这样叫我：
帮我写 PRD、帮我选 PRD 模板、把这个需求整理成 PRD、这个需求该用哪种 PRD、PRD 里补 Draw.io 流程图 - 适合：需求还在成型，需要判断 PRD 类型、当前成熟度、模板资产和后续 UI / handoff 承接
- 不适合：已有完整 PRD 要评审时改用
prd-review；只要正式 UI mockup 时改用ui-mockup-desktop-workbench；直接编码不触发
Overview
这个 Skill 负责把产品想法组织成结构匹配的 PRD。它不是固定展开重型模板，而是：
- 先判断上游输入是否足够成熟。
- 再选择
PRD-lite / PRD-standard / PRD-ai-native其中一个模板资产。 - 只加载本轮需要的附加资产；页面型 PRD 自动激活 mockup handoff 和 UI 证据链。
- 以“短背景 + 功能模块”为正文主干，把目标态 UI 和功能逻辑放在同一个模块内。
- 只有复杂链路才生成 Draw.io，不为简单需求补装饰性流程图。
- 生成文件时尽量运行 PRD shape 自检，避免把初版 PRD 写成实现方案。
- 每份 PRD 都在标题后维护一张版本记录表，让首次创建和后续迭代可追溯。
Upstream Boundaries
不要把所有输入都直接写成 PRD。先判断上游是否已经成熟：
- 问题、用户、目标或判断标准还不清楚：先转
ai-collaboration-calibration做问题校准。 - 问题已确认，但具体方案、架构、计划或产品决策需要压力测试：先转
grill-me。 - PRD 中存在重大产品、技术、商业或平台选择，且缺少证据：先转
decision-research。 - 已有 PRD/handoff 只是要判断能否交付开发：转
prd-review，由它给 readiness verdict。 - PRD 和 UI 规范都已确认，用户要正式桌面端多状态页面 mockup：转
ui-mockup-desktop-workbench。
prd-architect 可以根据上游输出起草或修订 PRD，但不自我批准 Ready for writing-plans。
Responsibilities
这个 Skill 负责：
- 判断需求复杂度和当前成熟度。
- 判断是否属于 AI-native 需求。
- 选择并加载一个 PRD 模板资产。
- 按需加载 mockup、Draw.io 或 handoff 资产。
- 组织 PRD 正文、待确认项和下一步建议。
- 在生成到文件时运行可用的确定性检查。
- 当 PRD 包含用户可见界面时，编排
ui-mockup-desktop-workbench，在同一交付中完成 HTML、关键截图和正文回填。 - 新建 PRD 时初始化
V1.0，修订时读取现有版本历史并记录本轮实际修改点。
它不负责：
- 直接决定 UI 视觉细节。
- 把 standalone HTML 当成生产代码；正式视觉实现由
ui-mockup-desktop-workbench负责，但本 Skill 负责触发、收口和验证这条交付链。 - 直接开始编码。
- 把核心规则外包给单独 guide 再让用户自己跳转理解。
- 在用户只要“初版 PRD”时展开接口字段、TypeScript、JSON schema、adapter 或 metadata 结构。
Workflow
1. Intake
先从用户输入和可发现项目上下文提炼：
- 需求描述、目标用户、当前问题、成功标准。
- 已知边界、非目标、待确认点。
- 是否涉及既有界面、截图、HTML mockup 或正式 UI mockup。
- 已有页面资产属于现状参考、与本期目标一致的目标稿，还是已经过期/结构不匹配的旧原型。
- 是否涉及 AI 协作、模型生成、推荐、记忆、人工确认或人工接管。
- 是否明确要求开发 handoff、接口字段、协议 schema 或实现计划。
- 是否会发布到钉钉或其他在线文档；若会发布，默认按“发布版正文”组织，不把本地路径当成正文信息。
如果输入缺失，可以基于明确假设先出第一版；不要把缺失业务判断伪装成已确认事实。
2. Select Template Asset
What ships with it
24 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.
- evals/evals.json 27 KB
- evals/fixtures/enterprise-trial-current.html 391 B
- evals/fixtures/legacy-five-tab-dashboard.html 351 B
- evals/fixtures/order-download-current.html 415 B
- evals/fixtures/supplier-onboarding-current.html 414 B
- evals/fixtures/team-billing-current.html 407 B
- references/drawio-templates.md 5.3 KB
- references/handoff-appendix.md 1.8 KB
- references/mockup-evidence-manifest.md 3.8 KB
- references/mockup-handoff.md 7.6 KB
- references/prd-shape-gates.md 5.3 KB
- references/prd-versioning.md 3.0 KB
- references/product-delivery-manifest.md 14 KB
- references/template-selection.md 3.3 KB
- references/templates/prd-ai-native.md 4.1 KB
- references/templates/prd-lite.md 3.0 KB
- references/templates/prd-standard.md 4.3 KB
- scripts/capture_mockup_evidence.py 6.1 KB runs code
- scripts/check_prd_shape.py 25 KB runs code
- scripts/check_prd_version_history.py 5.4 KB runs code
- scripts/validate_drawio.py 2.4 KB runs code
- scripts/validate_product_delivery_manifest.py 59 KB runs code
- tests/test_check_prd_shape.py 26 KB runs code
- tests/test_validate_product_delivery_manifest.py 47 KB runs code
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 · 357 lines · 196 tokens per session scan A a6697b8481b7
prd-architect is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 13d ago), licensed MIT. It adds 196 tokens to every session and 6,658 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
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…