agentmods.dev

generate_testcases_from_requirements

generate_testcases_from_requirements is a command for Claude Code from anhtester/claude-testing-kit. It costs 20 tokens per session (1,754 once invoked), scanned A, original, MIT.

A command that quickly turns clear requirements into manual test cases in Vietnamese, using the QUICK mode of a risk-based testing process.

In plain words
What is it for?
Reading requirements and supporting evidence, assigning missing requirement IDs, recording assumptions, and producing detailed test cases.
Why use it?
It reduces the time needed to write routine test cases while flagging unclear requirements and areas that still need verification.

Command for Claude Code

not rated 50 26d ago A scan 20 tokens original MIT
View the source file anhtester/claude-testing-kit
Install

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.

agentmods
npx agentmods add commands/anhtester/claude-testing-kit/generate_testcases_from_requirements
Clone the repo
git clone --depth 1 https://github.com/anhtester/claude-testing-kit

Made for: Claude Code.

Wrote 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.

agentmods badge for generate_testcases_from_requirements

README.md
[![agentmods](https://agentmods.dev/badge/commands/anhtester/claude-testing-kit/generate_testcases_from_requirements.svg)](https://agentmods.dev/commands/anhtester/claude-testing-kit/generate_testcases_from_requirements)
Your own site
<a href="https://agentmods.dev/commands/anhtester/claude-testing-kit/generate_testcases_from_requirements"><img src="https://agentmods.dev/badge/commands/anhtester/claude-testing-kit/generate_testcases_from_requirements.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,754 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.01754
Opus 5 $0.00010 $0.00877
Sonnet 5 $0.00004 $0.00351
Haiku 4.5 $0.00002 $0.00175

Measured 4d ago against content hash 776628142f1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate_testcases_from_requirements 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 4d 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.

.claude/commands/generate_testcases_from_requirements.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BẮT BUỘC (MANDATORY SKILL): Bạn PHẢI nạp và đọc kỹ nội dung của skill skills-rbt-manual-testing (tại .claude/skills/skills-rbt-manual-testing/SKILL.md) trước khi bắt đầu thực hiện tác vụ này. Sử dụng Mode QUICK của skill.

Command: Sinh Manual Test Cases Nhanh từ Requirements

Command này sử dụng Mode QUICK của skill skills-rbt-manual-testing để sinh test cases nhanh từ requirements đã sẵn có.

⚠️ Nguyên tắc

  • Mode: QUICK (1 lượt duy nhất, không chờ user giữa chừng)
  • Phù hợp cho module đơn giản, requirements đã rõ ràng
  • Nếu phát hiện requirements quá phức tạp hoặc mơ hồ → tự động chuyển sang FULL RBT và thông báo user
  • Tất cả output bằng Tiếng Việt

Các bước thực hiện

  1. Đọc và hiểu requirements được user cung cấp
    • Requirements đã có REQ ID → dùng nguyên mã; chưa có → agent tự gán REQ-<MODULE>-<SỐ>
  2. Mở TOÀN BỘ evidence — liệt kê docs/requirements/<module>/evidence/ và Read từng ảnh (Quy Tắc Đối Chiếu Evidence trong skill). Chưa mở xong thì chưa được ghi dòng TC đầu tiên. Tài liệu ↔ ảnh mâu thuẫn → ảnh thắng, ghi ASM-XX và báo user. Vùng không có ảnh → TC gắn @NeedsVerify
  3. Ghi nhận Assumptions: mọi điểm mơ hồ phải ghi rõ giả định đã dùng (ASM-XX) — không đoán ngầm
  4. Xác định các luồng chính: Happy Path, Negative Path, Boundary Cases, Edge Cases
  5. Áp dụng kỹ thuật thiết kế test case theo Quy Tắc Bắt Buộc trong skill:
    • Equivalence Partitioning (EP) + Boundary Value Analysis (BVA) — mọi field có ràng buộc
    • Decision Table — BẮT BUỘC khi ≥3 điều kiện kết hợp
    • State Transition — BẮT BUỘC khi có status flow
  6. Validation chuyên biệt từng trường (Field-Level Validation - 15 Field Types):
    • Liệt kê tất cả input fields trên form/UI
    • Sinh validation TCs riêng cho TỪNG trường theo đặc tính riêng (Text, Email, Phone, Date, Number, Dropdown, Checkbox/Radio, File Upload, Password, Textarea, OTP/MFA, Date Range, Rich Text, Multi-Select, Range Slider)
    • Áp dụng Bảng Field-Level Validation Checklist trong skill skills-rbt-manual-testing
    • KHÔNG gộp validation nhiều trường vào 1 test case
  7. Bao phủ Component-Level Checklist (trong skill): Data Table/List (sort/filter/search/pagination/empty state/bulk), CRUD Lifecycle, Permission/Role, Modal/Dialog, Notification, Status Flow
  8. Bao phủ Scenarios Chuyên Sâu & Non-Functional:
    • Double Submit / Race Condition (click liên tiếp nút submit, concurrent edit).
    • Session & Network Resilience (session timeout mid-form, loss of network, slow 3G).
    • Localization & UTF-8 / Emoji (tiếng Việt có dấu, emoji, ký tự đa ngôn ngữ).
    • Keyboard Accessibility (Tab order, Enter/Space trigger, Focus state).
    • HTTP Status Codes (cho API TCs).
  9. Sinh test cases đầy đủ fields & Automation Metadata:
    • TC ID (format: [DỰ_ÁN]_[MODULE]_TC_[SỐ])
    • REQ ID (bắt buộc — mã requirement mà TC cover, VD REQ-LOGIN-01)
    • Module
    • Risk Level (High / Medium / Low)
    • Test Scenario / Test Case Title
    • Pre-Condition
    • Test Steps (đánh số 1,2,3 — mỗi bước 1 hành động, dùng <br> xuống dòng trong cell)
    • Expected Result (đánh số khớp 1-1 với steps)
    • Test Data (phải cụ thể, không placeholder)
    • Priority (Critical / High / Medium / Low)
    • Automatable (Yes / No / Partial)
    • Auto Type (UI / API / Unit / N/A)
    • Tags (@Smoke, @Regression, @CriticalPath...)
  10. Chạy Self-Quality Gate (7 Tiêu chí): Unique TC ID, 1-to-1 Step-Expected matching, Concrete Test Data, Field Validation Coverage, Automation Metadata Ready, Requirement Coverage (mọi REQ có ≥1 TC — kèm Bảng Đối Soát Coverage), Evidence-verified (đã mở 100% ảnh evidence — kèm Bảng Đối Soát Evidence).
  11. Ghi file theo Quy Tắc Xuất File & Theo Dõi Tiến Độ (xem skill) — KHÔNG in bảng TC ra chat

Read the full file on GitHub · 90 lines

Changes

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.

  1. 4d ago First seen · 90 lines · 20 tokens per session scan A 776628142f1c

Subscribe to this mod's changes

generate_testcases_from_requirements is a command published in the GitHub repository anhtester/claude-testing-kit (50 stars, last pushed 26d ago), licensed MIT. It adds 20 tokens to every session and 1,754 once invoked, about $0.0001 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.

Testingaitestinganhtesterclaude-codeclaudetestingkittest-automationtest-manual
Related

Other commands, from other repositories

generate_api_tests_from_swagger

Sinh API test cases và automation scripts từ Swagger/OpenAPI specification. Hỗ trợ 2 mode — SPEC (chỉ test cases) và FULL (test cases + automation scripts).

anhtester/ClaudeCode_Playwright_Demo · 36 tokens

generate_combinatorial_test_data

Sinh test data cho ma trận kết hợp đa chiều bằng pipeline chạy thật qua nhiều modules. Input từ /generatecrossmoduletestplan.

anhtester/ClaudeCode_Playwright_Demo · 27 tokens

generate_cross_module_test_plan

Phân tích tính năng đi qua nhiều modules nối tiếp, xây dựng Module Map + Dimension Catalog, và sinh ma trận kết hợp (Pairwise/Business-critical/Full Cartesian). Hỗ trợ 2 modes — DOCUMENT (từ tài liệu) và BROWSER (inspect DOM thực tế).

anhtester/ClaudeCode_Playwright_Demo · 59 tokens

analyze_requirement_document

Phân tích requirement document (Jira ticket, .doc, user story) — sinh tài liệu phân tích chi tiết, KHÔNG sinh test cases.

anhtester/ClaudeCode_Playwright_Demo · 32 tokens

generate_testcases_from_requirements

Sinh manual test cases nhanh từ requirements (QUICK mode — không qua quy trình 6 bước).

anhtester/ClaudeCode_Playwright_Demo · 20 tokens

generate_manual_testcases_rbt

Sinh manual test cases chất lượng cao theo quy trình AI-RBT 6 bước (Risk-Based Testing) từ requirements.

anhtester/ClaudeCode_Playwright_Demo · 24 tokens