Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lucky2024-pllove/requirements-to-prd
Transforms user requirements (fragmented or complete) into a full product PRD using a seven-layer methodology: opportunity, problem, insight, solution design, requirement expression, prioritization and versioning, and validation/closed-loop. Combines problem definition (JTBD, 5 Whys, problem statement), insight (persona, journey, constraints), design (use cases, flows, state, MVP), and expression (EARS, user stories, Given-When-Then, NFRs) with MoSCoW/RICE-style prioritization.
Passed 16 of 22 test cases with the skill, and 10 of 22 without it.
and 6 more in the full report
6 fixed10 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are designing an automated order cancellation rule: when an order remains unpaid for 30 minutes, the system automatically cancels it and restores inventory; while the order is in payment processing state, cancellation requests must be blocked. Structure these behaviors in the PRD functional requirement section.
| Checked | Without skill | With skill |
|---|---|---|
| Formats system behaviors using EARS syntax in section 5. | Missed | Passed |
| Labels event-driven or state-driven rules with explicit EARS taxonomy markers. | Missed | Passed |
The instructions your model reads when the skill loads.
用户在对话中提供一段或多段需求（零散、口头、草稿或较完整），需要输出一份可供设计/研发/测试/业务对齐的完整产品 PRD 时，按本 Skill 的工作流与模板执行。
主交付物为 Markdown 结构正文（可写入用户指定本地路径或直接在对话中输出）。
可选：用户明确要求将 PRD 同步到飞书（云文档/知识库）且本机已安装并配置官方 lark-cli 时，按 references/lark-cli.md 与各 lark-* Skill 执行；未满足条件时仅交付 Markdown。
谁提供知识库落点？
space_id + parent_node_token，或仅父节点 token 由 CLI 反查空间，见 lark-wiki）。space_id / 父节点；公开仓库内仅保留占位符示例，见 references/wiki-archive-defaults.md。不能用你的默认替代其他用户的显式提供——对外分发时应要求对方自备落点。写入飞书时建议安装的 lark-cli Skills（能力组合）见 references/lark-cli.md 首节「写入飞书时的 Skill 组合」表格；至少包含 lark-wiki（知识库）、lark-shared（授权）、lark-whiteboard（可选：流程图/Mermaid 落白板）、lark-openapi-explorer（兜底原生 OpenAPI）；将 Markdown 灌入 wiki 关联云文档时通常还需要 lark-doc（或全程改用 OpenAPI 自拼）。
待补充 或列「假设/待确认问题清单」。对用户的输入，在内心按七层逐项覆盖；若某层用户已写得很全，可合并小节，但不跳过「优先级」与「验证/指标」两块的实质性内容（即使简短）。
| 顺序 | 层 | 本 Skill 在 PRD 中的落点（最少要写到） |
|---|---|---|
| 1 | 机会识别 | §1 背景、业务目标、与战略/OKR 的对齐；无则写合理推断+待补充 |
| 2 | 问题定义 | §2 问题陈述、JTBD/5 Whys 精要、不在此层写界面细节 |
| 3 | 需求洞察 | §3 用户与角色、核心场景、现状流程摘要、约束（政策/系统/时间） |
| 4 | 方案设计 | §4 目标方案、范围、业务流程/状态、MVP 边界、异常与边界 |
| 5 | 需求表达 | §5～§9 功能（EARS）、业务规则、数据、非功能、验收（GWT） |
| 6 | 优先级 | §10 MoSCoW 或 RICE 摘要表；V1 与后续 |
| 7 | 验证交付 | §11 成功指标/埋点、上线后看哪些数、风险、待评审问题 |
test cases passed, vs 10 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.