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/liaogui1023/coding-plugin/prd-writer-skillnpx skills add liaogui1023/coding-plugin --skill prd-writer-skillgit clone --depth 1 https://github.com/liaogui1023/coding-pluginWrote 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/liaogui1023/coding-plugin/prd-writer-skill)<a href="https://agentmods.dev/skills/liaogui1023/coding-plugin/prd-writer-skill"><img src="https://agentmods.dev/badge/skills/liaogui1023/coding-plugin/prd-writer-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 | $0.00080 | $0.00868 |
| Opus 5 | $0.00040 | $0.00434 |
| Sonnet 5 | $0.00016 | $0.00174 |
| Haiku 4.5 | $0.00008 | $0.00087 |
Grade A, and why
prd-writer 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 3d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Writer
产品需求文档撰写 + 原型生成工作流。
工作流程
阶段1：需求采集
整理用户输入（会议记录/需求描述）为结构化格式：
## 核心业务流程
- 🔴 P0 功能名称：功能描述
## 用户端功能
- 🟡 P1 功能名称：功能描述
## 管理端功能
- 🟢 P2 功能名称：功能描述
优先级：🔴 P0（必须）/ 🟡 P1（重要）/ 🟢 P2（优化）
详细 prompt 模板见 references/prompts.md
阶段2：Feature List
按模块组织功能表格，使用 references/feature-list-template.md
完整性检查：主动指出缺失环节（如有"加购物车"但没"购物车编辑"）
阶段3：PRD 文档
使用 references/prd-template.md 生成完整 PRD。
阶段4：原型生成
Step 1: 生成设计系统
python3 scripts/ui-ux-pro-max/search.py "<产品类型> <风格>" --design-system -p "项目名"
示例：
python3 scripts/ui-ux-pro-max/search.py "travel mobile app" --design-system -p "旅行App"
python3 scripts/ui-ux-pro-max/search.py "SaaS dashboard" --design-system -p "分析平台"
Step 2: 按需获取详细设计数据
# 配色方案
python3 scripts/ui-ux-pro-max/search.py "modern elegant" --domain color
# 字体配对
python3 scripts/ui-ux-pro-max/search.py "professional" --domain typography
# UX 准则
python3 scripts/ui-ux-pro-max/search.py "mobile form" --domain ux
# 技术栈指南
python3 scripts/ui-ux-pro-max/search.py "responsive" --stack html-tailwind
可用 domain: style, color, typography, ux, product, landing, chart
可用 stack: html-tailwind, react, nextjs, vue, svelte, shadcn, swiftui, react-native, flutter
Step 3: 生成 HTML 原型
基于设计系统输出，生成单文件 HTML（Tailwind CSS + 原生 JS）。
技术规格见 references/prototype-guide.md
阶段5：部署（可选）
Cloudflare Pages 部署（国内可访问）：
cd prototype && wrangler pages deploy . --project-name=your-project
详见 references/cloudflare-deploy.md
质量检查
完成后以四角色审视，详见 references/quality-checklist.md：
- 技术负责人：实现难度、性能、安全
- 挑剔用户：操作便捷性、流程合理性
- 运营负责人：数据分析、营销推广
- 测试工程师：异常场景、边界问题
输出文件
feature_list.md- 功能清单PRD.md- 完整需求文档design-system/- 设计系统prototype.html- 可交互原型
What ships with it
35 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.
- .gitignore 13 B
- README.md 2.5 KB
- references/cloudflare-deploy.md 3.1 KB
- references/feature-list-template.md 1.5 KB
- references/prd-template.md 2.9 KB
- references/prompts.md 3.9 KB
- references/prototype-guide.md 4.4 KB
- references/quality-checklist.md 3.2 KB
- scripts/ui-ux-pro-max/core.py 10.0 KB runs code
- scripts/ui-ux-pro-max/data/charts.csv 7.4 KB
- scripts/ui-ux-pro-max/data/colors.csv 9.4 KB
- scripts/ui-ux-pro-max/data/icons.csv 13 KB
- scripts/ui-ux-pro-max/data/landing.csv 14 KB
- scripts/ui-ux-pro-max/data/products.csv 29 KB
- scripts/ui-ux-pro-max/data/react-performance.csv 14 KB
- scripts/ui-ux-pro-max/data/stacks/astro.csv 12 KB
- scripts/ui-ux-pro-max/data/stacks/flutter.csv 10 KB
- scripts/ui-ux-pro-max/data/stacks/html-tailwind.csv 11 KB
- scripts/ui-ux-pro-max/data/stacks/jetpack-compose.csv 8.0 KB
- scripts/ui-ux-pro-max/data/stacks/nextjs.csv 12 KB
- scripts/ui-ux-pro-max/data/stacks/nuxt-ui.csv 14 KB
- scripts/ui-ux-pro-max/data/stacks/nuxtjs.csv 16 KB
- scripts/ui-ux-pro-max/data/stacks/react-native.csv 9.7 KB
- scripts/ui-ux-pro-max/data/stacks/react.csv 13 KB
- scripts/ui-ux-pro-max/data/stacks/shadcn.csv 16 KB
- scripts/ui-ux-pro-max/data/stacks/svelte.csv 11 KB
- scripts/ui-ux-pro-max/data/stacks/swiftui.csv 11 KB
- scripts/ui-ux-pro-max/data/stacks/vue.csv 11 KB
- scripts/ui-ux-pro-max/data/styles.csv 94 KB
- scripts/ui-ux-pro-max/data/typography.csv 31 KB
- scripts/ui-ux-pro-max/data/ui-reasoning.csv 30 KB
- scripts/ui-ux-pro-max/data/ux-guidelines.csv 18 KB
- scripts/ui-ux-pro-max/data/web-interface.csv 7.3 KB
- scripts/ui-ux-pro-max/design_system.py 43 KB runs code
- scripts/ui-ux-pro-max/search.py 5.2 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.
- 3d ago First seen · 105 lines · 80 tokens per session scan A 281b40d950b0
prd-writer is a skill published in the GitHub repository liaogui1023/coding-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 868 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…