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 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/prd-writer)<a href="https://agentmods.dev/skills/skinnerlee1225/enterprise-prd-toolkit/prd-writer"><img src="https://agentmods.dev/badge/skills/skinnerlee1225/enterprise-prd-toolkit/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/prd-writer"><img src="https://agentmods.dev/badge/skills/skinnerlee1225/enterprise-prd-toolkit/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 | $0.00452 | $0.04526 |
| Opus 5 | $0.00226 | $0.02263 |
| Sonnet 5 | $0.00090 | $0.00905 |
| Haiku 4.5 | $0.00045 | $0.00453 |
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 10d 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Writer(輕量版)— 施工藍圖等級的產品需求文件
設計理念
一份好的 PRD 不是「思考文件」,而是「施工藍圖」。判斷標準很簡單:
- 工程師看完能直接開發,不需要回頭問 PM「這個情況怎麼處理?」
- QA 看完能直接寫測試案例,不需要猜測邊界條件
- UAT 時不會出現「我以為是這樣」的分歧
這個 skill 的存在就是為了確保每份 PRD 都達到這個標準。
文件結構
PRD 應包含以下層次,根據產品複雜度可以增減,但核心四件事(AC、複雜度、畫面狀態、Out of Scope)不可省略:
1. 產品概述與目標
2. 功能規格(每個功能點)
├── 功能描述
├── 規則/邏輯
├── 驗收標準(AC) ← 必要
└── Out of Scope ← 必要
3. User Flow / 畫面規格
├── 每個畫面的狀態列舉 ← 必要
├── 頁面跳轉條件
└── API 呼叫時機
4. 風險與對策
5. MVP 路線圖
└── 複雜度標注(非工時估算) ← 必要
6. 成功指標(KPIs)
核心標準一:驗收標準(Acceptance Criteria)
每個功能點都必須附上驗收標準。這是 PRD 從「想法」變成「可執行規格」的關鍵。
格式
使用 Given / When / Then 三段式,每條 AC 搭配 Edge Case 說明:
| 規則 | Given / When / Then | Edge Case |
|---|---|---|
| [規則名稱] | Given [前置條件,含具體數值]When [觸發事件]Then ① [結果 1] ② [結果 2] ③ [結果 3] | • [邊界情境 1]• [邊界情境 2]• [邊界情境 3] |
撰寫原則
寫 AC 的時候,腦中要想著三個人:
- 工程師:他需要知道確切的觸發條件和預期行為。「帳戶淨值 ≤ $95,000」比「虧損太多」有用一千倍。
- QA:她需要知道邊界條件。週末跳空怎麼辦?多筆訂單同時觸發呢?這些如果不寫,測試的時候才發現就來不及了。
- 客服:他需要知道系統會做什麼,這樣才能回答用戶的問題。「訂單被拒絕,返回 NEWS_WINDOW 錯誤碼」比「系統會處理」清楚太多。
具體要求
- Given 中必須包含具體數值或狀態(不是「某個帳戶」,而是「$100,000 帳戶」或「帳戶狀態 = Active」)
- When 必須是可觀測的事件(不是「用戶做了什麼不好的事」,而是「即時淨值 ≤ $95,000」)
- Then 使用編號列出所有系統行為,順序即執行順序
- Edge Case 列出至少 2-3 個邊界情境,特別是:
- 兩個規則同時觸發時的優先級
- 時區/日期邊界的處理
- 資料不完整或異常時的降級行為
範例
| 日虧損 -5% | **Given** 當日開盤淨值 = $100,000
**When** 即時淨值(含未實現損益)≤ $95,000
**Then** ① 所有持倉立即市價平倉
② 當日禁止新開倉
③ 挑戰狀態 → Failed
④ 發送失敗通知 Email + Dashboard 彈窗 |
• 跨日隔夜持倉的跳空缺口:以新日開盤淨值重新計算基準
• 多筆訂單同時觸發:平倉順序以 ticket ID 遞增為準
• 週末跳空低於 -5%:以週一開盤第一個 tick 觸發 |
核心標準二:複雜度標注(取代工時估算)
規則
PRD 正文中絕對不要寫工時估算(「3-5 人天」、「0.5 人天」這類數字)。原因:
- 工時估算是工程師的職責。PM 在 PRD 裡寫了數字,工程師會覺得被預設了結論,容易產生摩擦。
- 不同團隊、不同技術棧,同樣的功能開發時間可以差 3-5 倍。PRD 裡的數字很快就會過時。
- 更好的做法是標注「技術複雜度」,讓工程師在 Sprint Planning 時自行估算。
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.
- 10d ago First seen · 300 lines · 452 tokens per session scan A f047f4d562f6
prd-writer is a skill published in the GitHub repository skinnerlee1225/enterprise-prd-toolkit (45 stars, last pushed 1mo ago), licensed MIT. It adds 452 tokens to every session and 4,526 once invoked, about $0.0023 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
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…
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…
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…
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…
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.