requirement-analysis

requirement-analysis is a skill for Claude Code, Codex from fishzjp/qa-skills. It costs 94 tokens per session (1,977 once invoked), scanned A, original, MIT.

A structured method for figuring out what a software requirement really means from documents, bugs, issues, and code. It records goals, scope, users, rules, exceptions, dependencies, and unanswered questions.

In plain words
What is it for?
Use it to create a requirements model for a feature or system and prepare reliable input for test planning or test-case writing.
Why use it?
It helps expose contradictions and missing details before testing or building begins, without guessing about unclear requirements.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is 证据标注(此时加载 `../core/evidence.md`):rules / states / exceptions 每条标注 evidence(level E0–E4 + source);用户在澄清环节的裁决记入 open_questions 的裁决字段,后续 skill 不得用代码推翻。.

Good fit Use it to create a requirements model for a feature or system and prepare reliable input for test planning or test-case writing.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/fishzjp/qa-skills
agentmods
npx agentmods add skills/fishzjp/qa-skills/requirement-analysis

Made for: Claude Code, Codex.

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 requirement-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/fishzjp/qa-skills/requirement-analysis/github.svg)](https://agentmods.dev/skills/fishzjp/qa-skills/requirement-analysis)
Your own site
<a href="https://agentmods.dev/skills/fishzjp/qa-skills/requirement-analysis"><img src="https://agentmods.dev/badge/skills/fishzjp/qa-skills/requirement-analysis/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.

agentmods 80×15 button for requirement-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/fishzjp/qa-skills/requirement-analysis"><img src="https://agentmods.dev/badge/skills/fishzjp/qa-skills/requirement-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,977 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01977
Opus 5 $0.00047 $0.00988
Sonnet 5 $0.00019 $0.00395
Haiku 4.5 $0.00009 $0.00198

Measured yesterday against content hash 62018a099a06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

requirement-analysis 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 yesterday.

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.

skills/requirement-analysis/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

需求分析(requirement-analysis)

回答"这个需求到底要做什么"——建立对系统的正确理解,而不是写测试。

  • 输入:PRD、设计文档、API 文档、Bug、Issue、代码仓库;旁路场景下消费 exploratory-testing 的探索笔记(系统理解 + 风险清单)
  • 输出(落盘){项目}/需求模型.md——按下方 Schema 组织,含澄清记录与用户裁决
  • 边界:不产出用例(→ test-case-writing);澄清后仍模糊的项如实标注 open_questions不硬猜

When to Use

  • 拿到 PRD/设计文档,需要系统性理解"这个需求到底要做什么"再进入测试
  • 多输入源(文档 + 代码 + Bug 单)需要交叉核对、暴露矛盾与缺口
  • test-strategy / test-case-writing 准备结构化的需求模型输入

When NOT to Use

  • 端到端测试整个需求 → qa 编排
  • 已有需求模型、直接写用例 → test-case-writing(其阶段一内联轻量研读,够用即不必先建模)
  • "这个功能应该怎么测" → test-strategy
  • 完全无文档且系统陌生 → 先走 exploratory-testing 探索,再回来建模

需求模型 Schema(产出结构)

requirement_model:
  goal:                     # 需求目标(一句话 + 成功标准)
  scope:                    # 功能范围(含明确的非目标)
  roles: []                 # 角色 → 能做什么 / 不能做什么
  inputs: []                # 输入(来源、格式、约束)
  outputs: []               # 输出(去向、格式、消费方)
  states: []                # 状态与流转(状态A --事件--> 状态B,逐条)
  rules: []                 # 业务规则,每条带 evidence(文档章节或 文件:行)
  exceptions: []            # 异常情况(错误场景的预期行为)
  dependencies: []          # 依赖关系(上下游系统、共享数据、时序依赖)
  open_questions: []        # 不明确事项 → 澄清记录(含用户裁决)

证据标注(此时加载 ../core/evidence.md):rules / states / exceptions 每条标注 evidence(level E0–E4 + source);用户在澄清环节的裁决记入 open_questions 的裁决字段,后续 skill 不得用代码推翻。

工作流

1. 输入收集与盘点

  • 清点可用输入源:PRD / 设计文档 / API 文档 / Bug 单 / FAQ / 会议纪要 / 代码仓库
  • 有代码仓库 → 主动索取(路径 + 分支 + 改动范围 + 对比基线 base——阶段 7 回归范围凭它划界),代码是静态事实的最高来源;分支名 + commit(或拉取时间)+ 对比基线记入需求模型文件头部,流水线续跑或进入执行阶段前先核对分支未变——对旧分支建模的结论不可复用,变了则标注受影响字段并复核
  • 有探索笔记(探索笔记_{主题}.md)→ 消费其"系统理解"与"风险清单"作为建模输入
  • 输入缺失项列入 open_questions(如"无性能指标文档")

2. 初读与要素提取

逐文档通读,按 Schema 的十个字段收集要素:

  • goal / scope:目标与成功标准;显式的"非目标"声明单独收录(后续要转化为验证边界)
  • roles:角色 × 能做 / 不能做(权限矩阵的雏形)
  • inputs / outputs:数据从哪来、到哪去、谁消费(无下游消费的输出是证伪线索)
  • states:状态与流转边;有代码时从代码状态字段提取实际状态机,与文档对照,差异记入澄清
  • rules:业务规则逐条编号,标注 evidence
  • exceptions / dependencies:错误场景行为、上下游依赖

3. 一致性检查(冲突发现)

  • 文档内部矛盾:同一文档不同位置对同一功能的描述不一致
  • 跨文档矛盾:PRD 与技术设计的规则 / 流程 / 字段不一致
  • 文档 vs 代码(有代码时):按 ../core/evidence.md 静态裁决规则——默认以代码为准,偏离记录并提交澄清

Read the full file on GitHub · 99 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. yesterday Changed · -9 tokens per session 62018a099a06
  2. 9d ago First seen · 99 lines · 103 tokens per session scan A e27bd20ce3c7

Subscribe to this mod's changes

requirement-analysis is a skill published in the GitHub repository fishzjp/qa-skills (27 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,977 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

qa-expert

Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.

personamanagmentlayer/pcl · 53 tokens

test-case-writer

Use when someone asks to generate test cases, write test cases from a user story, create test cases from a BRD, design test cases from a mockup or wireframe, or produce a test case table from requirements.

ukkuru/testmetry-skills · 50 tokens

test-review

A review checklist for newly written or changed automated tests using TypeScript and Playwright. Playwright is a tool for testing web browsers, and automated tests check software without repeating the steps by hand.

akovalion/paranoid-qa · 119 tokens

playwright-expert

Expert in Playwright E2E testing framework, auto-waiting mechanisms, test generation, trace viewer, and CI/CD integration. Use when the user mentions testing, end-to-end tests, QA, automation, end-to-end testing, or test automation, or when the task involves Playwright Framework, Test Organization, Advanced Features…

personamanagmentlayer/pcl · 77 tokens

selenium-expert

Expert in Selenium WebDriver, Selenium Grid, page object model, waits, cross-browser testing, and test automation frameworks. Use when the user mentions testing, end-to-end tests, QA, automation, WebDriver, or Selenium grid, or when the task involves Selenium Components, Browser Support, Advanced Features, or Basic…

personamanagmentlayer/pcl · 72 tokens

testing

A thorough testing framework for websites, user interfaces, back-end services, APIs, and builds. It checks normal use, errors, limits, and unusual combinations, and records evidence for each result.

akovalion/paranoid-qa · 85 tokens