Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问clear审计通过

spec-writer规范编写者

Agent Skill

spec-writer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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

212

周安装

9

GitHub Stars

3

下载量

74
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

3

许可证

MIT

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:spec-writer(规范编写者)
来源仓库:https://github.com/vibery-studio/templates
仓库路径:skills/spec-writer
安装命令:
npx skills add https://github.com/vibery-studio/templates --skill spec-writer
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/vibery-studio/templates --skill spec-writer

简介

spec-writer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。

  • 它可辅助 Agent 从文档、代码库或知识库中提取匹配内容,并按相关性排序返回。
  • 通过 npx skills add 命令从指定仓库安装,具体用法需结合原始 README 进一步确认。
  • 安装前建议核实权限范围、维护状态,以及是否会触发联网、命令执行或文件读写操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Spec Writer

Transform vague ideas into precise, implementable specifications that Claude Code can execute without ambiguity.

Purpose

Most AI coding failures happen because specifications are unclear. This skill extracts implicit requirements from conversations and outputs structured specs that eliminate guesswork.

Process

Phase 1: Context Extraction

Entry Check

IF user provided: problem statement + target users + success criteria
    → Proceed to Phase 2
ELSE
    → Gather missing information below (one question at a time)

Information Needed

ItemQuestionWhy Required
Problem"What problem are you solving?"Defines scope boundaries
Users"Who will use this?"Shapes UX requirements
Success"How will you know it works?"Creates acceptance criteria
Constraints"Any technical/business constraints?"Prevents wasted effort

Transition Criteria

All four items gathered + user confirmed → Phase 2


Phase 2: Requirement Analysis

Entry Check

IF Phase 1 complete:
    → Analyze and categorize requirements
ELSE
    → Return to Phase 1

Categorization Framework

FOR each requirement mentioned:
    Classify as:
    - MUST: Core functionality, non-negotiable
    - SHOULD: Important but has workarounds
    - COULD: Nice to have, time permitting
    - WON'T: Explicitly out of scope (important to document)

Output: Requirements Table

IDRequirementPriorityRationale
R1[requirement]MUST/SHOULD/COULD[why this priority]

Edge Case Discovery

FOR each MUST requirement:
    Ask: "What happens when [edge case]?"

    Common edge cases to probe:
    - Empty/null inputs
    - Maximum scale (1000x normal)
    - Concurrent access
    - Network failure
    - Permission denied
    - Invalid data format

Phase 3: User Story Generation

Entry Check

IF requirements table complete + edge cases documented:
    → Generate user stories
ELSE
    → Return to Phase 2

Story Format

AS A [user type]
I WANT TO [action]
SO THAT [benefit]

ACCEPTANCE CRITERIA:
- GIVEN [context]
  WHEN [action]
  THEN [expected result]

EDGE CASES:
- [edge case]: [expected behavior]

TECHNICAL NOTES:
- [implementation hints, if relevant]

Story Generation Rules

FOR each MUST requirement:
    → Generate 1 user story
    → Include 2-4 acceptance criteria
    → Include 1-3 edge cases

FOR each SHOULD requirement:
    → Generate 1 user story (simpler format)
    → Include 1-2 acceptance criteria

Phase 4: Technical Specification

Entry Check

IF user stories generated:
    → Ask: "Ready for technical spec, or need to adjust stories first?"

IF user confirms:
    → Generate technical specification
ELSE
    → Revise stories based on feedback

Technical Spec Structure

## Technical Specification: [Feature Name]

### Overview

[1-2 sentences describing the feature]

### Data Models

[If new data structures needed]

### API Endpoints

[If applicable]
| Method | Path | Request | Response |
|--------|------|---------|----------|

### State Changes

[What changes when this feature runs]

### Dependencies

[External services, libraries, existing code]

### Security Considerations

[Auth, validation, rate limits]

### Testing Strategy

- Unit: [what to unit test]
- Integration: [what to integration test]
- E2E: [critical user flows]

Phase 5: Output Delivery

Output Format Selection

IF user's project has existing spec format:
    → Match that format
ELSE IF user specified format preference:
    → Use requested format
ELSE
    → Use default markdown format below

Default Output Structure

# [Feature Name] Specification

## Summary

[One paragraph overview]

## Requirements

[Requirements table from Phase 2]

## User Stories

[Stories from Phase 3]

## Technical Specification

[Spec from Phase 4]

## Out of Scope

[Explicitly excluded items - prevents scope creep]

## Open Questions

[Unresolved items needing decisions]

Self-Check (Read before every response)

□ Am I gathering context or assuming? → Missing info = ask, never fill in

□ Am I asking one question at a time? → Multiple questions overwhelm users

□ Are requirements testable? → Vague requirements = implementation arguments later

□ Did I include edge cases? → Happy path only = bugs in production

□ Is the spec implementable by Claude Code? → Read it as if you'll code it: any ambiguity?

□ Did I document what's OUT of scope? → Scope creep starts with undefined boundaries

□ Are acceptance criteria specific? → "Works correctly" is not acceptance criteria → "Returns 200 with user object containing id, email" is


Integration with Other Skills

AFTER spec complete:
    Suggest: "Spec ready. Next steps:"
    - "Use /prd to expand into full PRD"
    - "Use architect-planner to design structure"
    - "Start coding with this spec as context"

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

windsurf

28.13%
按下载量换算21

OpenCode

21.81%
按下载量换算16

Codex

16.18%
按下载量换算12

Claude Code

11.93%
按下载量换算9

Antigravity

7.97%
按下载量换算6

Gemini CLI

2.84%
按下载量换算2

安全审计

Gen Agent Trust Hub

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。

来源信息

继续浏览同类 Skills