Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问许可证需确认审计通过

spec-writing规范编写

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

766

周安装

31

GitHub Stars

1

下载量

241
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:spec-writing(规范编写)
来源仓库:https://github.com/pixel-process-ug/superkit-agents
仓库路径:skills/spec-writing
安装命令:
npx skills add https://github.com/pixel-process-ug/superkit-agents --skill spec-writing
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/pixel-process-ug/superkit-agents --skill spec-writing

简介

spec-writing 用于辅助文档、README 和内容稿件的整理与改写,适合提炼结构和统一术语。

  • 适用于文档编写和内容优化的辅助工作,可检查链接和补齐章节。
  • 使用时应保留项目已有事实和路径,不要写成确定结论。
  • 涉及对外文案时需要控制语气,避免过度营销或夸大能力。
  • 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

Specification Writing

Overview

Specifications define WHAT the software should do, never HOW. This skill applies the Jobs to Be Done (JTBD) methodology to break requirements into properly scoped, testable specification files that drive autonomous implementation. Every spec produces Given/When/Then acceptance criteria free of implementation details.

This is a RIGID skill. Every phase, gate, and format rule must be followed exactly.

The Cardinal Rule

[HARD-GATE:SPEC] Specifications must NEVER contain implementation details.

ForbiddenAllowed
Code blocks or snippetsBehavioral descriptions
Variable names or function signaturesObservable outcomes
Technology choices ("use React", "use PostgreSQL")Capability requirements ("renders in browser", "persists data")
Algorithm suggestions ("use K-means clustering")Success criteria ("extracts 5-10 dominant colors")
Architecture patterns ("use MVC")User-facing behaviors
Library references ("use Zod for validation")Validation requirements ("rejects malformed input")

Why: Implementation-free specs preserve flexibility. The implementing agent can choose the best approach for the codebase, technology, and constraints — and change course without spec updates.

Phase 1: Jobs to Be Done (JTBD)

Identify the user's or system's jobs using this format:

When [situation], I want to [motivation], so I can [expected outcome].

Examples:

  • "When I upload an image, I want to extract its color palette, so I can use those colors in my design."
  • "When I receive an API request, I want to validate the payload, so I can reject malformed data before processing."

Gather jobs through discovery questions:

  1. Who is the user/actor?
  2. What situation triggers this need?
  3. What outcome do they want?
  4. What happens if they cannot accomplish this?

STOP after JTBD identification — present all jobs to the user for confirmation before breaking into topics.

Phase 2: Topics of Concern

Break each job into discrete topics. Apply the "One Sentence Without 'And'" test:

TestResultAction
"This spec covers color extraction."PASSSingle topic — one spec file
"This spec covers color extraction and palette rendering."FAILTwo topics — split into two spec files
"This spec covers user authentication and session management."FAILSplit into two specs
"This spec covers input validation for the registration form."PASSSingle topic — one spec file

Each topic becomes one specification file.

STOP after topic breakdown — confirm the list of spec files before writing them.

Phase 3: Write Specification Files

File naming convention: <int>-<descriptive-name>.md

specs/
├── 01-color-extraction.md
├── 02-palette-rendering.md
├── 03-export-formats.md
└── 04-color-accessibility.md

Specification File Template

# [Topic Name]

## Job to Be Done
When [situation], I want to [motivation], so I can [expected outcome].

## Acceptance Criteria

### [Criterion 1 Name]
- Given [precondition]
- When [action]
- Then [observable outcome]
- And [additional observable outcome]

### [Criterion 2 Name]
- Given [precondition]
- When [action]
- Then [observable outcome]

## Edge Cases
- [Describe boundary condition and expected behavior]
- [Describe error condition and expected behavior]

## Data Contracts
- Input: [Describe shape, constraints, valid ranges]
- Output: [Describe shape, guarantees, invariants]

## Non-Functional Requirements
- Performance: [measurable target, e.g., "responds within 200ms for 95th percentile"]
- Accessibility: [specific standard, e.g., "WCAG 2.1 AA"]
- Security: [specific requirement, e.g., "input sanitized against XSS"]

Acceptance Criteria Quality Rules

RuleGood ExampleBad Example
Observable behavioral outcome"Extracts 5-10 dominant colors from any image""Use K-means clustering with k=8"
Testable"Color data persists across sessions""Store in PostgreSQL JSONB column"
Specific and measurable"Palette changes appear within 500ms""Use WebSocket for real-time updates"
Independent (stands alone)"Palette renders when image loads""Implement with React useEffect hook"
Implementation-free"Passwords cannot be recovered from stored data""Use bcrypt with 12 salt rounds"

STOP after writing specs — run the audit checklist before proceeding to Phase 4.

Spec Audit Checklist

#CheckPass Criteria
1No implementation detailsZero code, function names, or tech choices
2One Sentence Without 'And' testEach spec covers exactly one topic
3All criteria are Given/When/ThenNo free-form prose criteria
4All criteria are testableEach can be verified by a test
5Edge cases documentedAt least 2 per spec
6Data contracts definedInput and output shapes specified
7Consistent naming<int>-<descriptive-name>.md format

Phase 4: Story Map Organization

Organize specs into a story map for release planning:

CAPABILITY 1    CAPABILITY 2    CAPABILITY 3    CAPABILITY 4
─────────────   ─────────────   ─────────────   ─────────────
basic upload    auto-extract    manual arrange  export PNG
bulk upload     palette gen     templates       export SVG
drag-drop       color names     grid layout     share link
                accessibility   animation       collaborate
  • Horizontal rows = candidate releases
  • Top row = minimum viable release
  • Each row adds capabilities across the board

SLC Release Criteria

For each horizontal slice, evaluate:

CriterionQuestionStandard
SimpleCan it ship fast with narrow scope?Weeks, not months
LovableWill people actually want to use it?Delightful, not just functional
CompleteDoes it fully accomplish a job?End-to-end, not half-done

[HARD-GATE] A release must satisfy ALL three. "Simple but incomplete" is not shippable. "Complete but not lovable" is not shippable.

STOP after story map — get user confirmation on release slicing before finalizing.

Phase 5: Specs Audit Mode

When auditing existing specs (rather than writing new ones):

  1. Read all spec files in specs/
  2. Check each against the Cardinal Rule (no code, no implementation details)
  3. Verify "One Sentence Without 'And'" test
  4. Ensure consistent naming convention
  5. Verify Given/When/Then format for all acceptance criteria
  6. Flag violations and auto-fix where possible

Deploy up to 100 parallel subagents via the Agent tool (with subagent_type="Explore") — one per spec file — for large spec sets.

Anti-Patterns / Common Mistakes

MistakeWhy It Is WrongWhat To Do Instead
Including code snippets in specsLocks implementation approachDescribe behavior, not mechanism
Naming technologies ("use Redis")Prevents better alternativesDescribe capability ("caches results")
Combining topics with "and"Spec too broad, hard to implement/testSplit into separate spec files
Vague acceptance criteria ("works well")Cannot write a test for itSpecific measurable outcome
Missing edge casesBugs in boundary conditionsDocument at least 2 edge cases per spec
Skipping data contractsInput/output ambiguityAlways define shapes and constraints
Writing specs after codeSpecs justify code instead of driving itSpecs come BEFORE implementation
Acceptance criteria that describe UI layoutImplementation detailDescribe what the user can accomplish

Anti-Rationalization Guards

  • [HARD-GATE] Do NOT include ANY implementation details — no code, no tech names, no architecture
  • [HARD-GATE] Do NOT skip the "One Sentence Without 'And'" test — split every compound topic
  • [HARD-GATE] Do NOT accept acceptance criteria that are not in Given/When/Then format
  • [HARD-GATE] Do NOT skip the audit checklist before finalizing specs
  • Do NOT skip edge cases — every spec needs at least 2
  • Do NOT skip data contracts — every spec needs input/output shapes
  • Do NOT write specs after implementation — specs drive code, not the reverse

Integration Points

SkillRelationship
autonomous-loopPlanning mode reads specs to identify implementation gaps
acceptance-testingTests are derived directly from spec acceptance criteria
reverse-engineering-specsGenerates specs from existing code (brownfield)
prd-generationPRD provides high-level requirements; specs detail them
planningPlans reference spec acceptance criteria for task definition
test-driven-developmentRed phase writes tests matching spec acceptance criteria
writing-skillsSkills can be specified using this methodology

Concrete Example: Complete Spec File

# Image Color Extraction

## Job to Be Done
When I upload an image to the design tool, I want to automatically extract
its dominant colors, so I can use those colors in my design palette.

## Acceptance Criteria

### Dominant Color Extraction
- Given an uploaded image in PNG, JPG, or WebP format
- When the extraction process completes
- Then 5-10 dominant colors are returned as hex values
- And colors are ordered by prominence (most dominant first)

### Transparent Image Handling
- Given an uploaded image with transparent regions
- When the extraction process completes
- Then transparent regions are excluded from color analysis
- And at least 3 dominant colors are still returned

### Processing Feedback
- Given an image upload has started
- When extraction is in progress
- Then the user sees a progress indicator
- And extraction completes within 3 seconds for images up to 10MB

## Edge Cases
- Single-color image: returns 1 color (not an error)
- Very large image (>50MB): returns an error with size limit message
- Corrupted image file: returns an error with clear message, no crash
- Animated GIF: extracts colors from the first frame only

## Data Contracts
- Input: Image file (PNG, JPG, WebP), max 50MB
- Output: Array of 1-10 hex color strings, ordered by prominence
- Error output: Error object with code and human-readable message

## Non-Functional Requirements
- Performance: <3s for images up to 10MB, <10s for images up to 50MB
- Accessibility: Color values include WCAG contrast ratio against white/black

Verification Gate

Before claiming specs are complete:

  1. VERIFY the Cardinal Rule — zero implementation details in any spec
  2. VERIFY every spec passes the "One Sentence Without 'And'" test
  3. VERIFY all acceptance criteria use Given/When/Then format
  4. VERIFY every spec has edge cases and data contracts
  5. VERIFY the story map has at least one complete SLC release slice
  6. VERIFY the user has confirmed the spec set

Skill Type

Rigid — The no-implementation-details rule, JTBD structure, Given/When/Then format, and audit checklist must be followed exactly. No elements may be skipped or adapted.

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

34.83%
按下载量换算84

Claude

32.59%
按下载量换算79

Cursor

19.34%
按下载量换算47

Gemini CLI

10.63%
按下载量换算26

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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