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 test-case-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/test-case-writer)<a href="https://agentmods.dev/skills/skinnerlee1225/enterprise-prd-toolkit/test-case-writer"><img src="https://agentmods.dev/badge/skills/skinnerlee1225/enterprise-prd-toolkit/test-case-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/test-case-writer"><img src="https://agentmods.dev/badge/skills/skinnerlee1225/enterprise-prd-toolkit/test-case-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 | $0.00285 | $0.02054 |
| Opus 5.5 | $0.00114 | $0.00822 |
| Sonnet 5.5 | $0.00057 | $0.00411 |
| Haiku 4.5 | $0.00028 | $0.00205 |
Grade A, and why
test-case-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 1mo 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
測試案例產生器（Test Case Writer）
在流程的位置
prd-writer / enterprise-prd-writer ──→ AC（Given/When/Then + Edge Case）
↓
【test-case-writer】← 展開成可執行測試案例
↓
QA 執行 / 自動化
分工界線：
| Skill | 負責 | 不負責 |
|---|---|---|
| enterprise-prd-writer | 定義需求與 AC | 不展開逐條測試步驟 |
| test-case-writer | 把 AC 展開成可執行測試案例 | 不改需求、不寫測試程式碼 |
如果輸入的 PRD 沒有 AC，先提醒使用者「這份缺 AC，測試案例會不完整」， 再就現有資訊盡量產出，並標出哪些是因缺 AC 而假設的。
核心原則
1. 每條 AC 至少展開成一組正常 + 邊界 + 異常
一條 Given/When/Then 不等於一個測試案例。它至少要拆成：
- 正常路徑（Happy Path）：條件成立，預期結果發生
- 邊界值（Boundary）：剛好在門檻上、門檻 ±1、最小/最大值
- 異常路徑（Negative）：條件不成立、輸入非法、前置失敗
PRD 的 AC 若已附 Edge Case，每個 Edge Case 至少對應一個測試案例。
2. 每個測試案例都可獨立執行、可判定通過與否
一個合格的測試案例，QA 拿到不必再問任何人就能跑。所以每條必須有：
- 前置條件（Precondition）：具體到可以建立的資料狀態
- 測試步驟（Steps）：一步一動作
- 預期結果（Expected）：明確、可觀察、可判定 pass/fail
禁止「驗證功能正常」這種無法判定的預期結果。
3. 用 PRD 的具體數值，不要自己發明
AC 的 Given 有數值（如「起點權益 10,000、上限 5%」），測試案例就用那些數值，
並補上邊界值（=門檻、門檻 ±1）。PRD 沒給的數值標 TBD，不要憑空填。
4. 覆蓋這幾類，缺一要說明
正常、邊界、異常之外，金融/後台類需求還要覆蓋：
- 併發 / 冪等：同請求送兩次、兩人搶同資源
- 權限：不同角色、未授權存取
- 安全：越權、繞過前置檢查
- 狀態機：非法狀態轉換、同時觸發多規則的優先級
某類不適用要寫「本功能無此類（因為…）」，不要默默略過。
執行流程
Step 0：讀 PRD，盤點 AC 與規則
讀完輸入的 PRD / AC，列出所有 R-xx 規則與 AC-xx。若沒有編號，自己編。
確認每條 AC 的 Given 有沒有具體數值——沒有的先標記，測試案例會受影響。
Step 1：為每條 AC 展開測試案例
依「正常 → 邊界 → 異常」逐條展開。每個測試案例給一個 ID（TC-<AC>-<序號>）。
Step 2：補跨 AC 的整合與非功能測試
- 整合流程：跨多條規則的完整 user flow 走一遍
- 併發/冪等/權限/安全：依核心原則 4 補上
Step 3：標優先級與類型
- 優先級：P0（阻斷發布）/ P1（重要）/ P2（次要）
- 類型：正常 / 邊界 / 異常 / 併發 / 權限 / 安全 / 整合
Step 4：輸出（見下方格式）+ 覆蓋率自檢
輸出格式
測試案例表（每個功能區塊一張）
### 提現 — 新地址鎖定（對應 AC-01 / R-03）
| TC ID | 類型 | 前置條件 | 步驟 | 預期結果 | Pri |
|---|---|---|---|---|---|
| TC-01-1 | 正常 | 用戶 10:00 新增地址 X | 20:00 對 X 發起提現 | 拒絕，提示隔日 10:00 解鎖；記錄稽核 | P0 |
| TC-01-2 | 邊界 | 地址 X 新增剛滿 24h | 對 X 發起提現 | 放行 | P0 |
| TC-01-3 | 邊界 | 地址 X 新增差 1 分鐘滿 24h | 對 X 發起提現 | 拒絕 | P0 |
| TC-01-4 | 異常 | 刪除 X 後再重新加入 | 對 X 發起提現 | 依 Open Q 定義（標 TBD） | P1 |
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.
- 1mo ago First seen · 159 lines · 285 tokens per session scan A 7abca9e27bdc
test-case-writer is a skill published in the GitHub repository skinnerlee1225/enterprise-prd-toolkit (45 stars, last pushed 3mo ago), licensed MIT. It adds 285 tokens to every session and 2,054 once invoked, about $0.0011 per session on Opus 5.5. 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
user-story-writer
Escribir historias de usuario bien estructuradas con criterios de aceptación y casos extremos. Úsalo cuando te pidan escribir historias de usuario, crear tickets a partir de un resumen de características, convertir un PRD en historias o redactar criterios de aceptación. Produce historias listas para estimar en formato…
prompt-regression-suite
Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use when asked to stop prompt changes breaking production, set up golden tests or CI gates for an LLM feature, or test a model/prompt upgrade before shipping it. Produces a golden case set, per-case…
ai-eval-plan
Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an AI feature, or build a regression gate. Produces an eval plan — task definition, datasets, metrics & rubrics, baselines, automated + human…
ai-agent-reliability
Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real. Use when asked how do I test my AI agent, make my automation reliable, my agent works sometimes, or how do I trust an AI workflow in production. Produces a map of where…
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…