What is generate_requirements_from_website?

A command workflow for turning a supplied website page or module into a detailed requirements document. It uses a separate requirements-analysis guide and focuses on extracting behavior from the website’s interface.

Use it to analyze a website module, page, screenshot, or related material and produce structured requirements for development or testing.

It provides a traceable way to document what a website should do, including requirement IDs, risks, scope, and test-related details.

How anhtester/claude-testing-kit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to anhtester/claude-testing-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/anhtester/claude-testing-kit/main/.claude/commands/generate_requirements_from_website.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/anhtester/claude-testing-kit/generate_requirements_from_website/github.svg)](https://agentmods.dev/commands/anhtester/claude-testing-kit/generate_requirements_from_website)

Your own site

<a href="https://agentmods.dev/commands/anhtester/claude-testing-kit/generate_requirements_from_website"><img src="https://agentmods.dev/badge/commands/anhtester/claude-testing-kit/generate_requirements_from_website/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/anhtester/claude-testing-kit/generate_requirements_from_website"><img src="https://agentmods.dev/badge/commands/anhtester/claude-testing-kit/generate_requirements_from_website.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8 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. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00008	$0.01754
Opus 5.5	$0.00003	$0.00702
Sonnet 5.5	$0.00002	$0.00351
Haiku 4.5	$0.00001	$0.00175

Measured 1mo ago against content hash 0495806043a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

generate_requirements_from_website 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.

.claude/commands/generate_requirements_from_website.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow: Generate Requirements from Website Module

BẮT BUỘC (MANDATORY SKILL): Bạn PHẢI nạp và đọc kỹ nội dung của skill skills-requirements-analyzer (tại .claude/skills/skills-requirements-analyzer/SKILL.md) để biết định dạng chuẩn của tài liệu Requirements trước khi bắt đầu thực hiện tác vụ này.

Workflow này chạy nhánh UI Recon — dùng mục 2 + 2.1 (đánh mã), 3.1 (trích xuất từ UI), 4 (AMB/RISK), 5 (quy mô/tách file), 6 (cấu trúc đầu ra), 7.1 + 7.2 (strict rules). ❌ KHÔNG dùng mục 3.2 (Document Analysis) trừ khi user cung cấp kèm tài liệu — khi đó chạy 3.2 trước, 3.1 sau và đối chiếu theo mục 3.3.

Workflow này giúp bạn phân tích một module hoặc trang web được cung cấp và sinh ra tài liệu Yêu cầu (Requirements) chi tiết, chuẩn xác, có mã REQ ID truy vết được, phục vụ cho quá trình kiểm thử hoặc phát triển.

Các bước thực hiện:

Tiếp nhận thông tin (Information Gathering):
- Đọc kỹ hướng dẫn từ kỹ năng (skill) skills-requirements-analyzer để nắm bắt chuẩn đầu ra.
- Lấy thông tin URL của trang web, tên module, hoặc mô tả/hình ảnh mà người dùng cung cấp.
- Nếu cần thiết, hỏi người dùng về thông tin đăng nhập hoặc các trạng thái đặc biệt cần lưu ý.
- Nếu hệ thống có nhiều role → hỏi user account của từng role để phân tích phân quyền.
Khảo sát hệ thống (Recon & Investigation):
- Sử dụng các công cụ duyệt web (Browser tools/MCP) để truy cập vào module trang web được yêu cầu (navigate → resize 1920x1080 → snapshot).
- Inspect kỹ lưỡng cấu trúc HTML, DOM, các form nhập liệu, các nút tương tác (buttons, links), và các thông báo lỗi (validation messages — ghi nguyên văn).
- Trigger từng validation để thu thập error messages thực tế.
- Lưu ý: Không tự đoán các trường thông tin nếu không nhìn thấy trên giao diện thực tế.
Phân tích chức năng và tương tác (Analyze UI & Interactions):
- Phân tích luồng thao tác (User Flows).
- Ghi nhận các trường dữ liệu tĩnh và động (Ví dụ: TextBox, Dropdown, Checkbox).
- Ghi nhận các quy tắc nghiệp vụ hiển thị ở giao diện (Business Rules): trường bắt buộc, định dạng hợp lệ, giới hạn ký tự.
- Ghi nhận phân quyền theo role (nếu có) và các trạng thái của entity (nếu có status flow).

Read the full file on GitHub · 66 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.

1mo ago First seen · 66 lines · 8 tokens per session scan A 0495806043a7

Subscribe to this mod's changes

generate_requirements_from_website is a command published in the GitHub repository anhtester/claude-testing-kit (61 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 1,754 once invoked, about $0.0000 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.

Claude Code Planning Research aitesting anhtester claudetestingkit test-automation test-manual

case

A command for registering and managing Testany cases. A case is a reusable package containing one automated testing step, its metadata, and its scripts.

TestAny-io/testany-agent-skills · 17 tokens

import-git

Komento Testany V2:n Git-tuontien hallintaan. Git on versionhallintajärjestelmä, ja OAuth on kirjautumistapa, jossa käyttöoikeus annetaan toiselle palvelulle.

TestAny-io/testany-agent-skills · 30 tokens

runbook-writer

A runbook is a practical operations guide for deploying, monitoring, rolling back, and handling incidents in a running system. This command writes one from architecture and design documents.

TestAny-io/testany-agent-skills · 41 tokens

test-reviewer

A review process for an independent test package, checking whether its tests cover the requirements, can be run, and have supporting evidence.

TestAny-io/testany-agent-skills · 29 tokens

prototype-reviewer

A command for reviewing an interactive prototype before it moves into API design and high-level technical design. It checks that the prototype matches the requirements and user journeys, covers important states, and stays isolated from production files.

TestAny-io/testany-agent-skills · 15 tokens

test-strategy-reviewer

A command that reviews a software test strategy before detailed design and test specifications begin. It checks the planned tests, environments, dependencies, automation, and release rules.

TestAny-io/testany-agent-skills · 27 tokens

claude-testing-kit: Command for Claude Code