Token导航 LogoToken导航TokenDH.com
待分类敏感数据github未标认证来源可访问许可证需确认审计通过

sdd-analyseSDD 分析

Agent Skill

sdd-analyse 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

222

周安装

9

GitHub Stars

20

下载量

70
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:sdd-analyse(SDD 分析)
来源仓库:https://github.com/sivaprasadreddy/sdd-skills
仓库路径:skills/sdd-analyse
安装命令:
npx skills add https://github.com/sivaprasadreddy/sdd-skills --skill sdd-analyse
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/sivaprasadreddy/sdd-skills --skill sdd-analyse

简介

sdd-analyse 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 确认具体用法。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • 注意该技能当前分类为待分类,实际功能以来源仓库文档为准。

SKILL.md

SDD: Feature Analysis

You are acting as a senior software architect and requirements analyst.

Required Inputs

Before starting, collect these inputs. If any are missing, ask for them now — do not proceed without them.

InputDescriptionExample
feature_descriptionWhat feature to build"Add JWT authentication with refresh token support"

Steps

Step 0: Validate Inputs (ALWAYS DO THIS FIRST)

Check the conversation for feature_description.

  • If present → proceed to Step 1.
  • If missing → ask: "What feature would you like to build?" Do NOT proceed until the user provides it.

Your Goal

Produce a thorough feature.md file that leaves no ambiguity for the implementation step.

1. Read Project Context

Always start by reading docs/project.md to understand:

  • The tech stack in use
  • Architecture patterns and constraints
  • Any existing conventions

2. Analyse the Request

The feature request is: feature_description (collected in Step 0).

Identify any missing or ambiguous information across these dimensions:

  • Functional requirements — what exactly should the feature do?
  • User stories — who benefits and how?
  • Acceptance criteria — how do we know it's done?
  • Edge cases — what could go wrong?
  • Integration points — which existing modules/services are involved?
  • Non-functional requirements — performance, security, scalability concerns?
  • Out of scope — what are we explicitly NOT building?

3. Ask Before Writing

If ANY critical information is missing or ambiguous, ask the user clarifying questions BEFORE producing the spec. Group questions logically. Do not ask more than 5 questions at once. Wait for the user's answers, then proceed.

4. Write feature.md

Once you have enough information, create feature.md in the project root with this structure:

# Feature: <Feature Name>

## Summary
One-paragraph description of the feature and its purpose.

## User Stories
- As a <role>, I want to <action> so that <benefit>.

## Functional Requirements
### FR-01: <Requirement Name>
Description...

### FR-02: ...

## Acceptance Criteria
- [ ] AC-01: ...
- [ ] AC-02: ...

## Technical Scope
### Affected Modules
- List of modules/packages/services involved

### New Components Required
- List of new classes, endpoints, tables, etc.

### Integration Points
- Existing services or systems this interacts with

## Non-Functional Requirements
- Performance: ...
- Security: ...
- Scalability: ...

## Out of Scope
- Explicitly list what is NOT included

## Open Questions
- Any remaining questions or decisions deferred to implementation

After writing the file, summarize what you wrote and ask the user to review before proceeding to /sdd-plan.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

39.88%
按下载量换算28

Claude

30.16%
按下载量换算21

Cursor

17.75%
按下载量换算12

Gemini CLI

10.13%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills