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 requirement-gap-findergit 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/requirement-gap-finder)<a href="https://agentmods.dev/skills/skinnerlee1225/enterprise-prd-toolkit/requirement-gap-finder"><img src="https://agentmods.dev/badge/skills/skinnerlee1225/enterprise-prd-toolkit/requirement-gap-finder/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/requirement-gap-finder"><img src="https://agentmods.dev/badge/skills/skinnerlee1225/enterprise-prd-toolkit/requirement-gap-finder.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 | $0.00380 | $0.04611 |
| Opus 5 | $0.00190 | $0.02305 |
| Sonnet 5 | $0.00076 | $0.00922 |
| Haiku 4.5 | $0.00038 | $0.00461 |
Grade A, and why
requirement-gap-finder 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求補洞助手
這個 skill 在流程的哪個位置
這是探路模式——只在「白紙、沒有 PRD」時上場,不掛在日常開發流程裡。
白紙需求 / 面試題 / 全新架構(沒有 PRD 可審)
↓
【需求補洞助手】 ← 發散:五角色掃描,產出問題清單 + 建議答案
↓
使用者自己拍板(沒有外部甲方時,使用者就是甲方;取代 grill-me)
↓
enterprise-prd-writer / prd-writer ← 落地:把拍板結果寫成 PRD
↓
開發
日常流程(已有明確需求、你熟的領域)不走這裡,直接 grill-me → PRD 即可—— 那些洞你自己的專業就補掉了,也會在 PRD 的 Definition of Ready 被抓。
分工界線(很重要,不要越界):
| Skill | 負責 | 不負責 |
|---|---|---|
| 需求補洞助手 | 白紙時找出「你還沒想到的」 | 不寫 PRD、不做格式檢查、不擅自決定 |
| grill-me | 一次一題逼出決定(有甲方可問時) | 不主動找盲點 |
| enterprise-prd-writer | 寫 PRD + 既有 PRD 的 Gap Analysis / DoR 完整度檢查 | 不做白紙的跨角色發想 |
關鍵切割: 已經有 PRD 要「稽核完整度」→ 那是 enterprise-prd-writer 的 Gap Analysis, 不是這個 skill。這個 skill 只在「還沒有 PRD」時發想。兩者不重疊。
核心原則
1. 每個問題都要附建議答案
這是這個 skill 能不能被用起來的關鍵。
五個角色一次丟 40 個問題出來,使用者會直接關掉。 每個問題都必須附上「建議預設答案」,讓使用者的成本從「思考 40 題」 降到「掃過 40 個建議,只推翻不同意的 5 個」。
建議答案要有立場,不要寫「看你的需求」。寫「建議 A,因為 B」。
2. 只問「答案不在文件裡」的問題
如果需求文件已經寫了「金額精度到小數點後 2 位」,就不要問「金額精度多少」。 掃描前先把使用者給的材料讀完。有 codebase 可以查的,去查 codebase。
3. 禁止通用廢話
以下這類輸出一律不合格:
- ❌「要考慮安全性」
- ❌「需要注意效能」
- ❌「建議做好錯誤處理」
- ❌「要考慮擴展性」
合格的長相是具體到可以一句話回答:
- ✅「同一筆訂單重複點擊送出兩次,第二次要擋在前端還是後端做冪等?建議後端用 client_request_id 做冪等鍵,前端同時 disable 按鈕。」
- ✅「用戶在填到一半離開頁面,草稿要保留嗎?建議不保留,但跳確認對話框。」
4. 標優先級,不要平鋪
阻塞開發的問題,跟「先假設、之後再修」的問題混在一起,等於沒分級。
執行流程
Step 0:讀材料、補最小上下文
先把使用者給的所有材料讀完(對話、草稿、PRD、截圖、codebase)。
如果缺少以下三項最小上下文,先問,一次問完,不要一題一題問:
- 這是新功能還是改既有功能? 改既有的話,現在的行為是什麼?
- 誰會用? 有沒有多種角色 / 權限差異?
- 平台? Web / App / 後台 / API-only?
其他一律不問——那是 grill-me 的工作,你的工作是找洞。
Step 1:先判斷哪些角色會參與
掃描前,先看這份需求實際上會動到哪幾個角色,在輸出最前面列一張「角色參與判斷表」:
| 角色 | 是否參與 | 判斷依據 |
|---|---|---|
| PM | ✅ 參與 | 一律參與(範圍與邊界永遠要盤) |
| UIUX | ❌ 無 | 純 API / 排程 / 資料遷移,沒有任何畫面 |
| Backend | ✅ 參與 | 有資料寫入與狀態變化 |
| Frontend | ❌ 無 | 無前端互動 |
| QA | ✅ 參與 | 一律參與(可測性永遠要盤) |
判斷原則:
- PM 與 QA 一律參與。 任何需求都有範圍邊界,也都要能驗收,這兩個角色不會標「無」。
- UIUX:只要完全沒有畫面(純後端 API、排程 job、資料遷移、內部函式),就標「❌ 無」。
- Frontend:沒有前端互動就標「❌ 無」。注意 UIUX 與 Frontend 是兩件事—— 有些需求有畫面設計(UIUX 參與)但前端只是靜態呈現、無複雜互動(Frontend 可標無)。
- Backend:純前端樣式調整、純文案修改,可標「❌ 無」。
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 · 326 lines · 380 tokens per session scan A 3af50819635e
requirement-gap-finder is a skill published in the GitHub repository skinnerlee1225/enterprise-prd-toolkit (45 stars, last pushed 1mo ago), licensed MIT. It adds 380 tokens to every session and 4,611 once invoked, about $0.0019 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…