Borrowing it
Nothing to install: this file belongs to anhtester/ClaudeCode_Playwright_Demo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anhtester/ClaudeCode_Playwright_Demo/main/.claude/commands/analyze_requirement_document.mdgit clone --depth 1 https://github.com/anhtester/ClaudeCode_Playwright_DemoWrote 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/commands/anhtester/claudecode_playwright_demo/analyze_requirement_document)<a href="https://agentmods.dev/commands/anhtester/claudecode_playwright_demo/analyze_requirement_document"><img src="https://agentmods.dev/badge/commands/anhtester/claudecode_playwright_demo/analyze_requirement_document/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/commands/anhtester/claudecode_playwright_demo/analyze_requirement_document"><img src="https://agentmods.dev/badge/commands/anhtester/claudecode_playwright_demo/analyze_requirement_document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00032 | $0.02126 |
| Opus 5.5 | $0.00013 | $0.00850 |
| Sonnet 5.5 | $0.00006 | $0.00425 |
| Haiku 4.5 | $0.00003 | $0.00213 |
Grade A, and why
analyze_requirement_document 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 — 176 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
requirements_analyzer(tại.agent/skills/requirements_analyzer/SKILL.md) để hiểu cách phân tích yêu cầu chuẩn trước khi bắt đầu.
Workflow: Phân Tích Requirement Document
Workflow này phân tích requirement documents (Jira tickets, .doc files, user stories, design mockups) và sinh ra một tài liệu phân tích chi tiết. KHÔNG sinh test cases — chỉ tập trung vào hiểu, phân rã, và phát hiện rủi ro/mơ hồ trong yêu cầu.
Khi nào sử dụng
- User cung cấp Jira ticket (.doc) hoặc requirement document và yêu cầu "phân tích"
- User muốn hiểu rõ scope, acceptance criteria, và dependencies trước khi viết test
- User cần danh sách các điểm mơ hồ (ambiguities) để clarify với PO/BA
- User nói: "phân tích requirement", "review yêu cầu", "analyze this ticket"
Đầu vào (Input)
Agent cần thu thập từ user:
| # | Input | Bắt buộc | Mô tả |
|---|---|---|---|
| 1 | Requirement document | ✅ | File .doc, .md, URL Jira, hoặc text mô tả yêu cầu |
| 2 | Mockup/Screenshot | ⭕ Khuyến khích | Hình ảnh UI design, wireframe, hoặc screenshot hiện tại |
| 3 | Related tickets | ⭕ Tùy chọn | Các ticket phụ thuộc hoặc liên quan (dependencies) |
| 4 | Context bổ sung | ⭕ Tùy chọn | Thông tin về hệ thống hiện tại, business domain |
[!NOTE] Nếu user chỉ cung cấp file .doc mà không có mockup, agent vẫn phải phân tích đầy đủ dựa trên nội dung document. Nếu có mockup/screenshot, agent phân tích UI chi tiết hơn.
Các bước thực hiện
Bước 1: Thu thập và đọc hiểu (Information Gathering)
- Đọc requirement document được user cung cấp (file .doc, .md, hoặc URL)
- Nếu file .doc format HTML (export từ Jira): parse HTML để trích xuất nội dung
- Xác định: Ticket ID, Type, Priority, Status, Reporter, Assignee, Fix Version, Sprint, Labels
- Đọc mockup/screenshot nếu có — phân tích UI layout, components, fields
- Kiểm tra related tickets nếu có trong cùng thư mục hoặc được user cung cấp
- Đọc và tóm tắt dependencies
- Xác nhận đã nắm được bối cảnh → tiếp tục phân tích
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 · 176 lines · 32 tokens per session scan A c42454e3f5c3
analyze_requirement_document is a command published in the GitHub repository anhtester/ClaudeCode_Playwright_Demo (3 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 2,126 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
review
Review changes using MCP validation.
test
Write tests using MCP-powered discovery.
implement
Implement features using plan and MCP verification.
plan
Create implementation plan using MCP-powered discovery.
boot
Command "boot" from ready-to-release/eac, covering boot, instructions, example initialization report and notes.
CHANGELOG
All notable changes to eac-mcp-server will be documented in this file. The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.