Agent skill

Requirement Analysis

by nuwax-ai in nuwax-ai/nuwax

把零散想法、口头需求、工单、告警浮出的问题整理成可执行的需求说明(intent);当用户提到需求分析、梳理需求、写需求文档、补全场景、功能规划,或要求开始一个新功能时使用。仅适用于新功能/大需求(跨模块、新契约、需拍板);BUG 修复与小调整不走此链,直接改+跑测试。

Apache-2.0Auto-check passed

Install Requirement Analysis

skills CLI
$ npx skills add nuwax-ai/nuwax --skill requirement-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nuwax-ai/nuwax requirement-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nuwax-ai/nuwax.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/requirement-analysis .claude/skills/requirement-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
requirement-analysis
GitHub stars
892
Token cost
~269 tokens
SKILL.md length
57 words
Files
4 (incl. references)
Repo updated
First seen
Licence
Apache-2.0

At a glance

把零散想法、口头需求、工单、告警浮出的问题整理成可执行的需求说明(intent);当用户提到需求分析、梳理需求、写需求文档、补全场景、功能规划,或要求开始一个新功能时使用。仅适用于新功能/大需求(跨模块、新契约、需拍板);BUG 修复与小调整不走此链,直接改+跑测试。

  • Works in 6 steps: 先收集上下文:原始需求、历史文档、相似功能、接口说明、权限规则、已有实现。 → 按结构整理需求:背景、目标、角色、流程、字段、状态、异常场景。 → 不确定内容必须标记 TODO,不要替产品或负责人拍板。 → …
  • SKILL.md covers 适用分级(先自检,勿为小修拖时间), 目标, 工作方式 and 输出结构, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Requirement Analysis is an agent skill from nuwax-ai/nuwax. 把零散想法、口头需求、工单、告警浮出的问题整理成可执行的需求说明(intent);当用户提到需求分析、梳理需求、写需求文档、补全场景、功能规划,或要求开始一个新功能时使用。仅适用于新功能/大需求(跨模块、新契约、需拍板);BUG 修复与小调整不走此链,直接改+跑测试。

Its SKILL.md is about 270 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/example-crud.md`, `references/output-templates.md` and `references/question-checklist.md`).

It works with Model Context Protocol. The repository describes itself as: Nuwax Agent OS - An enterprise-grade AI Agent Development and Operation Platform - Providing a complete solution for agent creation and distribution, knowledge base management… The licence is Apache-2.0.

Example prompts

  • “/requirement-analysis”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 先收集上下文:原始需求、历史文档、相似功能、接口说明、权限规则、已有实现。
  2. 按结构整理需求:背景、目标、角色、流程、字段、状态、异常场景。
  3. 不确定内容必须标记 TODO,不要替产品或负责人拍板。
  4. 需求过大先拆:一期必做 / 后续增强 / 明确不做。
  5. 输出可执行需求说明,而不是长篇 PRD。
  6. 落盘位置:plans/YYYYMMDD--intent.md(从 templates/intent.md 起步)。

What it can do on your machine

Read from SKILL.md and the folder at commit 4eff84f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Requirement Analysis loads about 269 tokens when it runs, and up to ~650 if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 57 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~269
With references · SKILL.md plus every file in references/, read only if the agent opens them
~650

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nuwax-ai/nuwax at commit 4eff84f, republished under its Apache-2.0 licence (© nuwax-ai). 57 words, ~269 tokens.

Download SKILL.mdSave it as .claude/skills/requirement-analysis/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
requirement-analysis
description
把零散想法、口头需求、工单、告警浮出的问题整理成可执行的需求说明(intent);当用户提到需求分析、梳理需求、写需求文档、补全场景、功能规划,或要求开始一个新功能时使用。仅适用于新功能/大需求(跨模块、新契约、需拍板);BUG 修复与小调整不走此链,直接改+跑测试。

Requirement Analysis(intent 阶段)

适用分级(先自检,勿为小修拖时间)

按 AGENTS.md「需求分级」:小修/BUG 修复(≤3 文件、无新契约、无需拍板)直接改 + 跑该域测试,不建 intent;中等需求只出 plan;只有新功能/大需求/跨模块才从本 skill 起步走完整链。

目标

把零散需求整理成可以继续评审、开发和测试的需求说明(SDLC 循环的 Plan 阶段工件 intent)。重点不是把话写漂亮,而是暴露缺口、明确边界、沉淀 TODO。

工作方式

  1. 先收集上下文:原始需求、历史文档、相似功能、接口说明、权限规则、已有实现。
  2. 按结构整理需求:背景、目标、角色、流程、字段、状态、异常场景。
  3. 不确定内容必须标记 TODO,不要替产品或负责人拍板。
  4. 需求过大先拆:一期必做 / 后续增强 / 明确不做。
  5. 输出可执行需求说明,而不是长篇 PRD。
  6. 落盘位置:plans/YYYYMMDD-<slug>-intent.md(从 templates/intent.md 起步)。

输出结构

md
# 需求说明:功能名称

## 背景和目标

## 用户角色

## 功能范围(本期做 / 本期不做)

## 核心流程

## 字段和状态

## 权限规则

## 异常场景

## TODO / 待确认问题

下一步(链条衔接)

intent 确认后 → grill-with-docs 拷问细化 → specs/<slug>.md → Plan mode 出 plans/YYYYMMDD-<slug>-plan.md 才动 src。模板在 templates/。

参考资料

  • references/output-templates.md / references/question-checklist.md / references/example-crud.md

© nuwax-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .agents/skills/requirement-analysis of nuwax-ai/nuwax.

  • SKILL.md
  • references/example-crud.md
  • references/output-templates.md
  • references/question-checklist.md

Open the folder on GitHubat commit 4eff84f

Compare with similar skills

Requirement Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Requirement Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Requirement Analysis this skillnuwax-ai/nuwax892—~269Automated safety check: PassApache-2.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills8.5k6 repos~3.2kAutomated safety check: NotesApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Stitch to Remotion Walkthrough Videos

    google-labs-code/stitch-skills

    Official

    Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.

    8.5k GitHub starsUsed in 6 repos~3.2k tokens
    Media & CreativeAuto-check: notes
  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed

More from nuwax-ai/nuwax

  • Grill With Docs

    nuwax-ai/nuwax

    拷问需求、方案和文档,逐步确认术语、边界、异常、风险和待确认问题;当用户要求拷问需求、挑战方案、检查边界、基于文档追问细节,或要把 intent 细化成规格时使用。仅新功能/大需求的规格收敛适用;小修/BUG 修复不适用,直接改+跑测试。

    892 GitHub stars~252 tokensUpdated yesterday
    Auto-check passed
  • 大量代码合并主干分支前的质量自查:功能逻辑内聚、代码分层、可维护性三问走查整个待合并批次;当用户要求合并主干前查质量、提测/发版/特性分支大批量合入前走查、自查内聚/分层/可维护性时使用。

    892 GitHub stars~393 tokensUpdated yesterday
    Auto-check passed

Questions about Requirement Analysis

What does Requirement Analysis do?

把零散想法、口头需求、工单、告警浮出的问题整理成可执行的需求说明(intent);当用户提到需求分析、梳理需求、写需求文档、补全场景、功能规划,或要求开始一个新功能时使用。仅适用于新功能/大需求(跨模块、新契约、需拍板);BUG 修复与小调整不走此链,直接改+跑测试。. Requirement Analysis is an agent skill from nuwax-ai/nuwax.

How do I install Requirement Analysis in Claude Code?

Run `npx skills add nuwax-ai/nuwax --skill requirement-analysis -a claude-code`. Or copy the skill folder (.agents/skills/requirement-analysis in nuwax-ai/nuwax) into .claude/skills/requirement-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Requirement Analysis in Codex?

Run `npx skills add nuwax-ai/nuwax --skill requirement-analysis -a codex`. Or copy the skill folder (.agents/skills/requirement-analysis in nuwax-ai/nuwax) into .agents/skills/requirement-analysis in your project. Codex loads it when a task matches its description.

Can I use Requirement Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nuwax-ai/nuwax --skill requirement-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/requirement-analysis, .gemini/skills/requirement-analysis, .github/skills/requirement-analysis and .opencode/skills/requirement-analysis in your project.

What does Requirement Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Requirement Analysis is instructions for the agent only.

Does Requirement Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Requirement Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Requirement Analysis use?

Requirement Analysis is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Requirement Analysis use?

About 269 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 381 tokens, read only when the agent opens those files.

What are the alternatives to Requirement Analysis?

Skills that share tags, products or a category with Requirement Analysis: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Requirement Analysis?

nuwax-ai (a GitHub organization) maintains it in nuwax-ai/nuwax, which has 892 GitHub stars. The repository was last updated on October 10, 2026.

Source: nuwax-ai/nuwax on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.