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 skinnerlee1225/enterprise-prd-toolkit --skill enterprise-prd-writergit clone --depth 1 https://github.com/skinnerlee1225/enterprise-prd-toolkitWrote 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/skinnerlee1225/enterprise-prd-toolkit/enterprise-prd-writer)<a href="https://agentmods.dev/skills/skinnerlee1225/enterprise-prd-toolkit/enterprise-prd-writer"><img src="https://agentmods.dev/badge/skills/skinnerlee1225/enterprise-prd-toolkit/enterprise-prd-writer/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/skinnerlee1225/enterprise-prd-toolkit/enterprise-prd-writer"><img src="https://agentmods.dev/badge/skills/skinnerlee1225/enterprise-prd-toolkit/enterprise-prd-writer.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 | $0.00603 | $0.09423 |
| Opus 5 | $0.00302 | $0.04712 |
| Sonnet 5 | $0.00121 | $0.01885 |
| Haiku 4.5 | $0.00060 | $0.00942 |
Grade A, and why
enterprise-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 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 — 1,148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
企業 PRD Writer — 施工藍圖等級的產品需求文件
1. 核心定位
一份好的 PRD 不是單純的「想法整理」,也不是 PM 的個人思考筆記。
它應該是一份可供跨職能團隊共同使用的產品施工藍圖,用來明確定義:
- 要解決什麼問題
- 為誰解決
- 系統必須呈現什麼行為
- 哪些商業規則不可被誤解
- 哪些異常與邊界情境必須處理
- 哪些內容本期明確不做
- 哪些地方仍是假設、待確認或需技術評估
- 如何驗收、如何監控、如何上線、如何回退
完成標準
PRD 的完成,不以字數、頁數或圖表數量判斷,而以以下結果判斷:
- 工程師可理解產品行為與商業規則,不需反覆追問本應由產品定義的內容。
- QA 可根據文件直接拆出主要測試案例與邊界案例。
- 設計師可理解各畫面、狀態、跳轉與例外情境。
- 利害關係人清楚知道本期做什麼、不做什麼。
- UAT 不應因需求語意模糊而出現大量「我以為」。
- 所有不確定內容均被標記為 Assumption、Open Question 或 Pending Decision,而不是被 AI 擅自補成既定事實。
2. 角色邊界
PRD 應明確區分產品需求、產品建議與技術決策,避免 PM 越界指定技術實作,也避免工程團隊誤解哪些行為不可變更。
| 類型 | 定義 | 是否可由工程團隊調整 |
|---|---|---|
| Product Requirement | 必須滿足的產品行為、商業規則、使用者結果、法規要求或 SLA | 不可直接變更,需與 Product 確認 |
| UX Requirement | 互動流程、資訊架構、提示方式與可用性要求 | 可在不影響目標與 AC 的前提下討論 |
| Product Recommendation | PM 對實作或流程的建議,不是強制技術方案 | 可由 Design / Engineering 提出替代方案 |
| Technical Decision | 架構、資料結構、重試演算法、Queue、Cache、服務拆分等技術設計 | 由 Engineering 在 TDD / ADR 中決定 |
| Operational Requirement | 後台操作、客服處理、稽核、人工介入與異常處置流程 | 需由 Product、Ops、Engineering 共同確認 |
強制原則
- 不應將技術建議寫成不可變更的產品要求。
- 不應要求 PRD 取代 Technical Design Document。
- 若某個技術細節會直接影響 SLA、合規、資金安全或使用者體驗,則可列入 PRD,但需說明其產品理由。
- Engineering 對技術可行性、效能、架構與最終技術複雜度擁有最終評估權。
3. 文件結構
3.0 輕量模式(小案子的降級路徑)
觸發條件(符合任一即啟用): 個人專案、單一功能、無合規/金流/風控需求、單人或單團隊開發。
輕量模式下只產出以下章節,其餘章節整份標記 N/A(輕量模式略過),不強制填寫:
- §5 Executive Summary(可壓縮成 3–5 句)
- §9 Scope(In / Out of Scope)
- §13 Functional Requirements
- §14 Acceptance Criteria
- §15 Edge Case Analysis(只跑相關類型,不強制 28 項全查)
- §17 Screen / System States(只列實際存在的狀態)
不啟用權限矩陣、NFR、Dependencies、Analytics、Rollout/Migration/Rollback、UAT/Release Readiness 等企業級章節,除非使用者明確要求。
目的:避免幫個人小工具寫 PRD 時,吐出一份 20 章的巨獸。若不確定是否為小案子,先問使用者一句「這是要走輕量還是完整企業級?」。
3.1 完整結構
PRD 應根據產品規模調整深度,但以下章節為標準結構:
1. 文件資訊
2. Executive Summary
3. 背景與問題定義
4. 產品目標與成功指標
5. 使用者與使用情境
6. Scope
├── In Scope
├── Out of Scope
└── Phase Boundary
7. Assumptions / Open Questions / Decisions
8. Dependencies
9. Roles & Permissions
10. Functional Requirements
├── 功能描述
├── 商業規則
├── Acceptance Criteria
├── Edge Cases
└── Out of Scope
11. User Flow / System Flow
12. Screen / System States
13. Data & Integration Requirements
14. Non-functional Requirements
15. Analytics & Observability
16. Risk & Mitigation
17. Rollout / Migration / Rollback
18. MVP / Roadmap / Complexity Assumption
19. UAT & Release Readiness
20. Appendix
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 · 1,148 lines · 603 tokens per session scan A 066245632407
enterprise-prd-writer is a skill published in the GitHub repository skinnerlee1225/enterprise-prd-toolkit (45 stars, last pushed 1mo ago), licensed MIT. It adds 603 tokens to every session and 9,423 once invoked, about $0.0030 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 2026-08-30.
Other skills, from other repositories
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…
handoff
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
discover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…
execute-fleet
Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.
customise-workflow
Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…