Token导航 LogoToken导航

Agent Skill · 前端设计

speckit-workflow(规格套件工作流程)

speckit-workflow 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。

speckit-workflow 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有未通过项,按安装量在前端设计类的 10,216 个 Skill 里排第 8,262。

总安装 303周安装 13GitHub Stars 61下载 106核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:speckit-workflow(规格套件工作流程)
来源仓库:https://github.com/melodic-software/claude-code-plugins
仓库路径:skills/speckit-workflow
安装命令:
npx skills add https://github.com/melodic-software/claude-code-plugins --skill speckit-workflow
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/melodic-software/claude-code-plugins --skill speckit-workflow

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

speckit-workflow 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。适合围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库和原始 README 核验具体用法。

安装命令:npx skills add https://github.com/melodic-software/claude-code-plugins --skill speckit-workflow。建议确认权限范围和维护状态,注意是否会触发联网、命令执行或文件读写。

来源仓库内路径:skills/speckit-workflow

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/melodic-software/claude-code-plugins --skill s…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

speckit-workflow 怎么安装?

在终端执行 npx skills add https://github.com/melodic-software/claude-code-plugins --skill speckit-wor…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

speckit-workflow 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

speckit-workflow 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

speckit-workflow 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

speckit-workflow 用的人多吗?

公开数据是累计安装 303 次,近一周安装 13 次,下载 106 次,GitHub 61 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

speckit-workflow 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
speckit-workflow

规格套件工作流程 · 本页

30361需要联网未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Spec Kit Workflow

GitHub Spec Kit 5-phase specification-driven development workflow.

When to Use This Skill

Keywords: Spec Kit, 5-phase workflow, constitution, specify, plan, tasks, implement, feature.md, design.md, tasks.md, specification workflow, GitHub Spec Kit, constitution.md, phased development

Use this skill when:

  • Implementing specification-driven development workflows
  • Creating or updating project constitution files
  • Generating feature specifications from requirements
  • Creating implementation plans from specifications
  • Breaking down plans into task lists
  • Following the full Specify → Plan → Tasks → Implement cycle

Workflow Overview

Phase 0: Constitution (One-time setup)
    ↓
Phase 1: Specify (Generate feature.md)
    ↓
Phase 2: Plan (Generate design.md)
    ↓
Phase 3: Tasks (Generate tasks.md)
    ↓
Phase 4: Implement (Code with guidance)

Phase 0: Constitution

Purpose

Establish project-wide principles, constraints, and non-functional requirements that guide ALL specifications.

File: .constitution.md

# Project Constitution

## Core Principles
- <principle 1>
- <principle 2>

## Technical Constraints
- <constraint 1>
- <constraint 2>

## Quality Standards
- <standard 1>
- <standard 2>

## Non-Functional Requirements
- Performance: <requirement>
- Security: <requirement>
- Accessibility: <requirement>

Constitution Checklist

  • Core development principles defined
  • Technical constraints documented
  • Quality standards specified
  • Non-functional requirements listed
  • Team conventions captured
  • Dependencies and integration requirements noted

When to Update

Update the constitution when:

  • New non-functional requirements emerge
  • Team conventions change
  • Architectural decisions impact all features
  • Project-wide constraints are added

Phase 1: Specify

Purpose

Transform a feature request or user story into a structured specification with EARS requirements and acceptance criteria.

Input

  • Feature request (natural language)
  • User story (As a... I want... So that...)
  • Problem statement

Output: feature.md

# Feature: <Feature Name>

## Context
### Problem Statement
<What problem does this solve?>

### Motivation
<Why is this important?>

### Scope
<What's in/out of scope?>

## Requirements

### REQ-001: <Requirement Title>
**EARS Pattern:** <ubiquitous|state-driven|event-driven|unwanted|optional>
**Priority:** <must|should|could>
**Text:** <EARS-formatted requirement>

#### Acceptance Criteria
- **AC-001:**
  - Given: <precondition>
  - When: <action>
  - Then: <outcome>

### REQ-002: ...

## Dependencies
- <dependency 1>
- <dependency 2>

## Risks
- <risk 1>
- <risk 2>

Specify Phase Checklist

  • Problem statement is clear and specific
  • All requirements use EARS patterns
  • Each requirement has acceptance criteria
  • Requirements are prioritized (MoSCoW)
  • Dependencies identified
  • Risks documented
  • Scope boundaries defined

Phase 2: Plan

Purpose

Design the technical implementation approach for the specified feature.

Input

  • feature.md from Phase 1
  • Constitution constraints
  • Existing codebase context

Output: design.md

# Design: <Feature Name>

## Overview
<High-level approach>

## Architecture

### Component Design
- <component 1>: <purpose>
- <component 2>: <purpose>

### Data Model
<Entities, relationships, schema changes>

### API Design
<Endpoints, contracts, interfaces>

## Technical Approach

### Approach Selected
<Chosen approach with rationale>

### Alternatives Considered
| Alternative | Pros | Cons | Why Not |
| --- | --- | --- | --- |
| <alt 1> | ... | ... | ... |

## Integration Points
- <integration 1>
- <integration 2>

## Testing Strategy
- Unit tests: <approach>
- Integration tests: <approach>
- E2E tests: <approach>

## Rollout Plan
<How will this be deployed?>

Plan Phase Checklist

  • Architecture aligns with constitution
  • All requirements can be addressed
  • Alternatives were considered
  • Data model is complete
  • API contracts defined
  • Testing strategy covers acceptance criteria
  • Integration points identified
  • Rollout plan exists

Phase 3: Tasks

Purpose

Break down the design into implementable tasks with clear deliverables.

Input

  • design.md from Phase 2
  • feature.md requirements for traceability

Output: tasks.md

# Tasks: <Feature Name>

## Task List

### TSK-001: <Task Title>
**Status:** pending
**Requirement:** REQ-001
**Estimated Effort:** <S|M|L|XL>

**Description:**
<What needs to be done>

**Deliverables:**
- [ ] <deliverable 1>
- [ ] <deliverable 2>

**Acceptance Criteria:**
- [ ] <criterion 1>
- [ ] <criterion 2>

### TSK-002: ...

## Dependency Graph

TSK-001 → TSK-003 TSK-002 → TSK-003 TSK-003 → TSK-004


## Effort Summary

| Size | Count | Typical Duration |
| --- | --- | --- |
| S | <n> | < 2 hours |
| M | <n> | 2-4 hours |
| L | <n> | 4-8 hours |
| XL | <n> | > 8 hours |

Tasks Phase Checklist

  • Every requirement has at least one task
  • Tasks are independently deliverable
  • Dependencies are mapped
  • Effort estimates provided
  • Acceptance criteria are testable
  • No task is larger than XL
  • Critical path identified

Phase 4: Implement

Purpose

Execute tasks with continuous validation against specifications.

Input

  • tasks.md from Phase 3
  • design.md for technical guidance
  • feature.md for acceptance criteria

Workflow

1. Select next task (respecting dependencies)
2. Review task deliverables and acceptance criteria
3. Implement the task
4. Validate against acceptance criteria
5. Mark task complete
6. Repeat until all tasks done

Implementation Checklist (Per Task)

  • Task dependencies are complete
  • Implementation follows design
  • Code passes acceptance criteria
  • Tests written and passing
  • Documentation updated
  • Task marked complete in tasks.md

Feature Completion Checklist

  • All tasks marked complete
  • All acceptance criteria verified
  • All tests passing
  • Documentation complete
  • Feature reviewed against original request

Phase Transitions

Phase 0 → Phase 1

Gate: Constitution exists and is current

Validation:

  • .constitution.md file exists
  • Constitution reviewed within last quarter
  • No blocking updates needed

Phase 1 → Phase 2

Gate: Specification is complete and valid

Validation:

  • All requirements use EARS patterns
  • All requirements have acceptance criteria
  • Priorities assigned
  • Dependencies identified
  • Stakeholder approval (if required)

Phase 2 → Phase 3

Gate: Design is implementable

Validation:

  • Design addresses all requirements
  • Architecture aligns with constitution
  • Technical approach selected
  • Integration points defined
  • Testing strategy documented

Phase 3 → Phase 4

Gate: Tasks are ready for implementation

Validation:

  • All tasks mapped to requirements
  • Dependencies graphed
  • Effort estimated
  • No blocking dependencies external to feature
  • Development environment ready

Prompts Reference

Specify Prompt

Located at: prompts/specify.prompt.md

Key sections:

  • Context extraction from user input
  • EARS pattern application
  • Acceptance criteria generation
  • Prioritization guidance

Plan Prompt

Located at: prompts/plan.prompt.md

Key sections:

  • Architecture design
  • Alternatives analysis
  • Testing strategy
  • Integration planning

Tasks Prompt

Located at: prompts/tasks.prompt.md

Key sections:

  • Task decomposition
  • Dependency mapping
  • Effort estimation
  • Acceptance criteria mapping

File Organization

.specs/
├── <feature-name>/
│   ├── feature.md      # Phase 1 output
│   ├── design.md       # Phase 2 output
│   └── tasks.md        # Phase 3 output
└── ...

.constitution.md        # Phase 0 (project root)

Quick Commands

PhaseCommandDescription
0/spec:constitutionCreate/update constitution
1/spec:specifyGenerate specification
2/spec:planGenerate design
3/spec:tasksGenerate task breakdown
4/spec:implementGuided implementation
All/spec:speckit:runFull workflow

Integration with Canonical Spec

Spec Kit outputs map to the canonical specification model:

Spec KitCanonical Field
feature.md contextcontext.problem, context.motivation
REQ-xxxrequirements[].id
EARS textrequirements[].text
Priorityrequirements[].priority
AC-xxxrequirements[].acceptance_criteria[]
design.mdimplementation_notes

References

Detailed Documentation:

Related Skills:

  • spec-management - Specification workflow navigation
  • canonical-spec-format - Canonical specification structure
  • ears-authoring - EARS requirement patterns
  • gherkin-authoring - Acceptance criteria syntax

Last Updated: 2025-12-24

Version History

  • v1.0.0 (2025-12-26): Initial release

平台分布

Codex

34.92%
按下载量换算37

Claude

30.48%
按下载量换算32

Cursor

17.69%
按下载量换算19

Gemini CLI

10.25%
按下载量换算11

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills