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 YiShu5/claude-skills --skill rule-prd-generatorgit clone --depth 1 https://github.com/YiShu5/claude-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/yishu5/claude-skills/rule-prd-generator)<a href="https://agentmods.dev/skills/yishu5/claude-skills/rule-prd-generator"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/rule-prd-generator/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/yishu5/claude-skills/rule-prd-generator"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/rule-prd-generator.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 | $0.00104 | $0.01311 |
| Opus 5 | $0.00052 | $0.00656 |
| Sonnet 5 | $0.00021 | $0.00262 |
| Haiku 4.5 | $0.00010 | $0.00131 |
Grade A, and why
rule-prd-generator 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.
What it actually says
规则 PRD生成
目标
把业务材料转成一份跨职能团队能共同评审、据此设计研发、测试验收和运营交接的正式 PRD。文档首先服务人的判断和协作,不把实现提示词冒充产品需求。
核心原则
- 区分信息层级: 明确标注已确认需求、已知事实、产品建议、暂定方案和待决策项。不得把会议中的个人提议、演示效果或产品建议写成已定需求。
- 先收敛再补全: 合并重复表述,区分内容需求、交互建议和技术方案;对冲突项保留决策记录,不用模糊措辞掩盖分歧。
- 不凭空补业务规则: 缺少的信息如果会改变用户、范围、权限、数据来源或主流程,先提出一个最关键的问题;其他内容可用明确标注的假设继续整理。
- 保留产品边界: 区分 Demo、MVP 和生产系统;区分统一入口、统一身份、单点登录、数据同步和系统整合。未经验证,不得宣称外部系统已接通或权限已打通。
- 让需求可验收: 功能规则、权限、状态、异常和验收标准应能观察或测试。避免“体验良好”“操作方便”“尽量快”等无法判定的表述。
- 尊重现有文档: 修改已有 PRD 时先读取当前版本、目录、变更记录和相关章节,做增量修订;除非用户明确要求,不整篇推倒重写。
工作方式
1. 整理输入
先识别材料属于访谈记录、业务提案、现有 PRD、评审反馈还是版本新增需求。提取:
- 目标用户、使用场景和要解决的问题;
- 已确认范围、候选需求、明确不做和后续考虑;
- 业务规则、数据来源、权限、依赖、负责人和时间约束;
- 原始材料中的冲突、缺口和未经证实的结论。
用户要求保留来源时,为合并后的需求记录提出人或原始出处;否则不在正文堆叠聊天记录。
2. 先同步 Gap
起草前给出简短 Gap,优先暴露会影响方案的事项:
- 产品目标或成功标准不明确;
- 用户、角色或可见范围不明确;
- 主流程缺少前置条件或完成结果;
- 外部系统、数据源或接口能力未经确认;
- 负责人、内容维护机制、异常处理或回退方式缺失;
- 指标只有名称,没有口径、目标值或不达标动作。
只有必须由用户决定且不同答案会产生明显不同 PRD 时才暂停询问;一次问一个决定性问题。用户要求先出初稿时,用“暂定/待确认”继续,不擅自定案。
3. 选择文档粒度
- 新建正式 PRD、重构现有文档或跨多个模块时,读取并采用 正式 PRD 结构与检查表。
- 小范围改版时只更新受影响章节、版本记录、验收标准、风险和待确认项,避免为了套模板扩大改动。
- 用户提供参考 PRD 时,复用其信息组织方式和术语,不复制与当前产品无关的内容。
4. 写功能规则
每个核心功能按实际需要说明:
- 目的、使用角色和前置条件;
- 用户入口、主流程和完成结果;
- 展示内容、关键字段和交互规则;
- 数据来源、更新方式和数据归属;
- 可见范围、操作权限及附件/直达链接权限;
- 空状态、加载状态、失败状态和边界情况;
- 可观察的验收标准。
不要强行为简单功能填满所有字段;只保留会影响设计、研发、测试或业务验收的内容。
5. 完成交付检查
交付前确认:
- 目标、范围、角色、流程、页面和详细规则彼此一致;
- P0/P1/P2 或本期/后续/不做边界清楚;
- 敏感内容在列表、搜索、详情、直达链接和附件上使用一致权限;
- 外部依赖区分“已确认可用”和“待技术验证”;
- 指标包含口径、时间窗、目标值、负责人和不达标动作,未确认的目标明确标注为建议值;
- 每个 P0 主流程及关键异常都有验收标准;
- 待确认事项写明当前处理方式和最晚确认节点;
- 版本更新同步进入变更记录,没有残留旧口径。
输出要求
- 默认使用简体中文 Markdown,先给结论和 Gap,再给完整 PRD 或增量修订内容。
- 标题、表格和编号以便于评审与引用为准,不追求章节数量。
- 将业务确认项放在正文,将纯技术实现细节留给技术方案;只有技术约束会影响产品边界时才写入 PRD。
- 如果用户后续要交给编码 Agent,再基于已确认 PRD 单独生成实现任务,不把两类文档混在一起。
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.
- 3d ago First seen · 86 lines · 104 tokens per session scan A dbc10ada0658
rule-prd-generator is a skill published in the GitHub repository YiShu5/claude-skills (83 stars, last pushed 4d ago), licensed MIT. It adds 104 tokens to every session and 1,311 once invoked, about $0.0005 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 2026-09-07.
Other skills, from other repositories
finalize-phase
Completes feature/epic workflows after deployment with comprehensive walkthrough generation for epics (v5.0+), roadmap updates, artifact archival, documentation, and branch cleanup. Use after /ship-prod, /deploy-prod, or /build-local completes, or when user asks to finalize. (project).
implementation-phase
Executes implementation tasks using Test-Driven Development, prevents code duplication through anti-duplication checks, and maintains quality through continuous testing. Use when implementing features from tasks.md, during the /implement phase, or when the user requests TDD-based implementation. (project).
roadmap-integration
Manages product roadmap via GitHub Issues (brainstorm, prioritize, track). Auto-validates features against project vision (from overview.md) before adding to roadmap. Use when running /roadmap command or mentions 'roadmap', 'add feature', 'brainstorm ideas', or 'prioritize features'.
task-status-sync
Enforce atomic task status updates through task-tracker commands only. Prevent manual edits to NOTES.md and tasks.md that break synchronization. Auto-trigger when detecting Edit/Write attempts to task files, task completion mentions, or status update discussions. Auto-convert manual edit attempts to equivalent…
workflow-detection
Provides centralized workflow type detection for all phase and deployment commands.
epic-sprints
Generate sprint breakdown with dependency graph and execution layers for epic workflows.