Co-Pilot / 辅助式
更新于 a month ago

specweave

Aanton-abyzov
0.0k
anton-abyzov/specweave
86
Agent 评分

💡 摘要

SpecWeave通过永久文档和无缝集成自动化AI驱动的编码任务。

🎯 适合人群

寻求自动化的软件开发人员需要文档的项目经理使用GitHub/JIRA进行项目管理的团队希望实现CI/CD集成的DevOps工程师探索编码工具的AI研究人员

🤖 AI 吐槽:就像有一个永不休息的私人助理,但确实需要Node.js才能运行。

安全分析中风险

自述文件暗示了潜在的风险,例如依赖性漏洞和与外部工具同步的网络访问。为了减轻风险,确保定期更新依赖项并使用安全配置。

SpecWeave

The Enterprise Layer for AI Coding.

Permanent memory, GitHub/JIRA sync, quality gates, autonomous execution. Ship features while you sleep.

NPM Version License: MIT Test & Validate Discord YouTube

npm install -g specweave # Requires Node.js 20.12.0+

Quick Demo

/sw:increment "User authentication" /sw:auto # Ship while you sleep

What happens:

  • AI creates spec + plan + tasks
  • Executes autonomously for hours
  • Tests, fixes failures, syncs to GitHub/JIRA
  • You review finished work
[08:23:41] [Planning]      Analyzing T-003: Implement refresh token rotation
[08:24:12] [Implementing]  Writing src/auth/token-manager.ts
[08:25:33] [Testing]       Running tests... FAILED
[08:25:47] [Fixing]        Adjusting implementation...
[08:26:15] [Testing]       Re-running... PASSED
[08:26:22] [Done]          T-003 complete. Moving to T-004...

Why SpecWeave?

Every AI coding tool loses context when the chat ends. SpecWeave creates permanent documentation:

.specweave/increments/0001-oauth/
├── spec.md    <- WHAT: User stories, acceptance criteria
├── plan.md    <- HOW: Architecture decisions, tech choices
└── tasks.md   <- DO: Implementation tasks with tests

After 6 months: Search "OAuth" → find exact decisions, who approved, why it was built that way.


Key Differentiators

Lazy Plugin Loading (99% Token Savings)

SpecWeave loads plugins on-demand based on your prompt keywords:

| Scenario | Without Lazy Loading | With Lazy Loading | |----------|---------------------|-------------------| | Non-SpecWeave work | ~60k tokens | ~500 tokens | | SpecWeave work | ~60k tokens | ~60k (when needed) |

Say "React frontend" → frontend plugin loads. Say "Kubernetes deploy" → k8s plugin loads. No manual configuration.

Self-Improving Skills

SpecWeave learns from corrections. When you fix something, it captures the learning:

## Skill Memories <!-- Auto-captured by SpecWeave reflect --> - Always use `vi.hoisted()` for ESM mocking in Vitest 4.x+ - Prefer native `fs` over fs-extra in new code

Next time, it won't make the same mistake.

Structured Documentation (No Root Bloat)

Everything stays organized in .specweave/:

.specweave/
├── increments/####-name/     # Feature specs + tasks
├── docs/internal/            # Living documentation
│   ├── architecture/adr/     # Architecture Decision Records
│   └── specs/                # Feature specifications
└── config.json               # Project configuration

Your project root stays clean. No scattered markdown files.

15+ AI Agents Working Together

| Agent | Role | |-------|------| | PM | Requirements, user stories, acceptance criteria | | Architect | System design, ADRs, tech decisions | | QA Lead | Test strategy, quality gates | | Security | OWASP review, vulnerability scanning | | DevOps | CI/CD, infrastructure, deployment |

Agents auto-activate based on context. Mention "security" → security expertise loads.


Install

Prerequisites

Node.js 20.12.0+ required (recommend Node.js 22 LTS).

node --version # Check version

Getting SyntaxError: Unexpected token 'with'? Your Node.js is too old. Upgrade instructions →

New Project

npm install -g specweave mkdir my-app && cd my-app specweave init .

Then describe what you want in Claude Code:

"Build a calculator app with React"

Existing Project

npm install -g specweave cd your-project specweave init .

Then:

/sw:increment "Add dark mode" # Create spec + plan + tasks /sw:auto # Ship while you sleep

Core Commands

| Command | Purpose | |---------|---------| | /sw:increment "feature" | Create spec + plan + tasks | | /sw:auto | Autonomous execution (hours) | | /sw:do | Execute one task at a time | | /sw:done 0001 | Close with quality validation | | /sw:sync-progress | Push to GitHub/JIRA/ADO | | /sw:next | Auto-close + suggest next |

53 total commands →


External Integrations

| Platform | Capabilities | |----------|--------------| | GitHub | Issues, PRs, milestones, bidirectional sync | | JIRA | Epics, stories, status sync | | Azure DevOps | Work items, area paths |

Automatic sync: When you close an increment (/sw:done), external tools update immediately. Task progress syncs at session end.

/sw:sync-progress # Manual: Push updates to ALL tools /sw-github:sync 0001 # Manual: Sync specific increment to GitHub /sw-jira:sync 0001 # Manual: Sync specific increment to JIRA

Works On Everything

| Scenario | What Happens | |----------|-------------| | 10-year legacy codebase | Brownfield analysis detects doc gaps | | Weekend MVP | Full spec-driven development | | 50-team enterprise | Multi-project sync to JIRA/ADO |


CLI Commands

| Command | Purpose | |---------|---------| | specweave init . | Initialize project | | specweave update | Full update: CLI + plugins + instructions |

Troubleshooting

Run specweave update - this fixes 98% of issues (updates CLI, plugins, and instructions).


Requirements

  • Node.js 20.12.0+ (recommend 22 LTS)
  • Any AI coding tool (Claude Code recommended)
  • Git repository

Built With SpecWeave

This framework builds itself. Every feature, bug fix, and release is spec-driven.

Deploy Frequency Features

Browse our increments →


Documentation

spec-weave.com - Full documentation, guides, and examples.


Community

Discord | YouTube | GitHub Issues


License

MIT - github.com/anton-abyzov/specweave

五维分析
清晰度9/10
创新性9/10
实用性9/10
完整性8/10
可维护性8/10
优缺点分析

优点

  • 有效地自动化编码任务
  • 创建永久文档
  • 与流行工具无缝集成
  • 从用户修正中学习

缺点

  • 需要特定的Node.js版本
  • 新用户可能需要学习曲线
  • 对外部工具的依赖以实现全部功能

相关技能

goodvibes-plugin

A
toolCo-Pilot / 辅助式
84/ 100

“看起来很能打,但别让配置把人劝退。”

omni-dev-fusion

A
toolCo-Pilot / 辅助式
82/ 100

“看起来很能打,但别让配置把人劝退。”

miyabi-claude-plugins

A
toolCo-Pilot / 辅助式
82/ 100

“这个插件套件就像一把瑞士军刀,如果瑞士军队由过于优秀的 AI 组成。”

免责声明:本内容来源于 GitHub 开源项目,仅供展示和评分分析使用。

版权归原作者所有 anton-abyzov.