What is skills-requirements-analyzer?

A requirements-analysis skill that turns web pages, software modules, or documents into structured requirements and user stories. It assigns traceable IDs and records unclear points, risks, permissions, and testable states.

Use it to analyze UI or project documentation, create requirements and user stories, identify ambiguities and risks, and support QA planning.

It makes vague product information easier for developers and testers to implement, review, and trace back to its source.

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/skills/skills-requirements-analyzer/SKILL.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/skills/anhtester/claude-testing-kit/skills-requirements-analyzer/github.svg)](https://agentmods.dev/skills/anhtester/claude-testing-kit/skills-requirements-analyzer)

Your own site

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

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,806 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00066	$0.10806
Opus 5	$0.00033	$0.05403
Sonnet 5	$0.00013	$0.02161
Haiku 4.5	$0.00007	$0.01081

Measured 9d ago against content hash e74058e01ef5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skills-requirements-analyzer 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 9d 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/skills/skills-requirements-analyzer/SKILL.md · 533 lines

How it starts

The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kỹ năng Phân tích Yêu cầu (Requirements Analyzer)

Kỹ năng này cung cấp các hướng dẫn chi tiết để AI (Claude Code) có thể chuyển đổi giao diện UI, cấu trúc DOM/HTML, hoặc tài liệu (Jira ticket, .doc, user story) thành tài liệu Yêu cầu rõ ràng, chi tiết, truy vết được, phục vụ trực tiếp cho QA, Tester và Developer.

1. Mục tiêu cốt lõi

Xây dựng tài liệu yêu cầu bám sát thực tế hệ thống đang chạy hoặc tài liệu gốc.
Mọi yêu cầu đều có mã REQ ID — để test cases, automation và RTM truy vết ngược được.
Đảm bảo tính bao quát: Happy Path, Edge Cases, phân quyền, trạng thái, thông báo lỗi.
Phát hiện và ghi nhận có hệ thống các điểm mơ hồ (Ambiguity) và rủi ro (Risk).

2. Quy Ước Đánh Mã (BẮT BUỘC — dùng xuyên suốt toàn chuỗi)

Loại	Format	Ví dụ	Dùng ở đâu
Requirement	`REQ-<MODULE>-<SỐ>`	`REQ-LOGIN-01`	Từng yêu cầu chức năng, business rule, validation rule
Story	`STORY-<MODULE>-<SỐ>`	`STORY-PRJ-03`	Nhóm REQ thành đơn vị công việc (backlog view) — xem mục 5
Ambiguity	`AMB-<SỐ>`	`AMB-03`	Điểm mơ hồ cần clarify với PO/BA
Risk	`RISK-<SỐ>`	`RISK-02`	Rủi ro kiểm thử

Quy tắc:

Mỗi yêu cầu đủ nhỏ để test được độc lập — nếu 1 câu chứa nhiều rule, tách thành nhiều REQ
REQ ID không đổi sau khi đã phát hành tài liệu (chỉ thêm mới, không đánh lại số)
Test cases sinh ra ở bước sau PHẢI ghi REQ ID vào cột REQ ID — đây là mắt xích để kiểm chứng "đủ case" giữa requirements và test cases

Phân vai REQ vs STORY (quan trọng):

REQ là lớp truy vết duy nhất — bất biến, mọi test case / automation / RTM đều neo vào đây
STORY chỉ là lớp nhóm việc — được phép đổi tên, gộp, tách lại theo cách team vận hành mà không ảnh hưởng tới REQ ID hay test case đã viết
❌ TUYỆT ĐỐI KHÔNG đánh lại số REQ khi tách file hay gom Story. REQ ID gắn với hành vi, không gắn với vị trí trong tài liệu

2.1. Nối tiếp mã REQ giữa các lần chạy (BẮT BUỘC — chống đụng mã)

Read the full file on GitHub · 533 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.

9d ago First seen · 533 lines · 66 tokens per session scan A e74058e01ef5

Subscribe to this mod's changes

skills-requirements-analyzer is a skill published in the GitHub repository anhtester/claude-testing-kit (53 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 10,806 once invoked, about $0.0003 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.

Claude Code Planning Writing and docs aitesting anhtester claudetestingkit test-automation test-manual

claude-testing-kit: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Kỹ năng Phân tích Yêu cầu (Requirements Analyzer)

1. Mục tiêu cốt lõi

2. Quy Ước Đánh Mã (BẮT BUỘC — dùng xuyên suốt toàn chuỗi)

2.1. Nối tiếp mã REQ giữa các lần chạy (BẮT BUỘC — chống đụng mã)

What this file has done since we first saw it

Other skills, from other repositories

RBT Manual Testing

Framework Architect

UI Debug Agent

jira_integration

Test Data Generator

Flaky Test Analyzer