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

adr-generator地址生成器

Agent Skill

adr-generator 用于查找、检索和筛选相关信息,适合在 OpenClaw 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

1,599

周安装

68

GitHub Stars

公开资料未说明

下载量

560
OpenClaw

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

MIT-0

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:adr-generator(地址生成器)
来源仓库:https://github.com/charlie-morrison/adr-generator
安装命令:
openclaw skills install adr-generator
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install adr-generator

简介

adr-generator 用于信息检索与筛选,适合在 OpenClaw 中分析技术决策。

  • 它生成架构决策记录,记录上下文、替代方案和后果。
  • 通过 clawhub 安装后,可结合来源仓库和 README 验证使用场景。
  • 安装前需确认权限范围、维护状态及是否涉及代码读取或文件写入。
  • 建议参考原始文档了解输入格式和输出结构。

SKILL.md

name
adr-generator
description
Architecture Decision Record generator — analyze codebases and document technical decisions with context, alternatives, and consequences. Use when asked to document architecture decisions, create ADRs, or explain why technical choices were made.

Architecture Decision Record Generator

Analyze a codebase or conversation to produce Architecture Decision Records (ADRs) — structured documents that capture the WHY behind technical choices so future developers understand the reasoning.

Use when: "document this decision", "create an ADR", "why did we choose X", "record our architecture decision", or when a significant technical choice is being made.

What is an ADR?

A short document capturing one significant architectural decision: the context, the decision itself, the alternatives considered, and the consequences. ADRs form a decision log that prevents the same debates from recurring and helps new team members understand the codebase.

When to Create an ADR

  • Choosing a framework, database, or major library
  • Defining API contracts or data schemas
  • Setting team conventions (testing strategy, branching model, deployment process)
  • Making a trade-off (performance vs maintainability, monolith vs microservices)
  • Adopting or dropping a tool
  • Any decision someone might later ask "why did we do it this way?"

Analysis Steps

1. Identify the Decision

From conversation or code review, extract:

  • What was decided
  • When (date or PR/commit reference)
  • Who was involved (if known)

2. Reconstruct Context

# Check git history for related changes
git log --oneline --all --grep="<keyword>" | head -20

# Find when a dependency was added
git log --all --diff-filter=A -- package.json | head -5
git log -p --all -S '<package-name>' -- package.json | head -40

# Look for prior discussion in docs
grep -ri "decision\|chose\|alternative\|trade-off\|migrate" docs/ README.md CONTRIBUTING.md 2>/dev/null

# Check for existing ADRs
find . -type f -name "*.md" -path "*/adr/*" -o -name "*decision*" 2>/dev/null
ls docs/adr/ docs/decisions/ doc/architecture/ 2>/dev/null

3. Analyze Alternatives

For framework/library decisions:

# What else was evaluated? Check for traces
grep -ri "considered\|vs\|compared\|evaluated\|alternative" docs/ 2>/dev/null
git log --all --oneline | grep -i "try\|experiment\|spike\|poc\|prototype" | head -10

# Check if multiple solutions were tried
git log --all --oneline --diff-filter=D -- '**/package.json' | head -10

4. Assess Consequences

Read the current implementation to understand what the decision enabled or constrained:

# How deeply is the choice embedded?
grep -rc "<framework-import>" --include="*.{ts,js,py,go}" . 2>/dev/null | sort -t: -k2 -rn | head -10

# Are there workarounds that suggest regret?
grep -ri "hack\|workaround\|todo\|fixme\|technical debt" --include="*.{ts,js,py,go}" . 2>/dev/null | head -20

ADR Template

Use the Michael Nygard format (industry standard):

# ADR-{NNN}: {Title — short, noun-phrase}

**Date:** YYYY-MM-DD
**Status:** Proposed | Accepted | Deprecated | Superseded by ADR-XXX
**Deciders:** [names or roles]

## Context

What is the issue that we're seeing that is motivating this decision or change?
Describe the forces at play: technical constraints, business requirements, team capabilities, timeline pressure.

## Decision

State the decision clearly in full sentences.
"We will use PostgreSQL as our primary database."
"We will adopt a monorepo structure using Turborepo."

## Alternatives Considered

### Alternative A: [name]
- **Pros:** ...
- **Cons:** ...
- **Why not:** ...

### Alternative B: [name]
- **Pros:** ...
- **Cons:** ...
- **Why not:** ...

## Consequences

### Positive
- What becomes easier or possible because of this decision

### Negative
- What becomes harder, more expensive, or is now ruled out
- What technical debt does this introduce

### Risks
- What could go wrong
- Under what conditions would we reconsider this decision

## References

- Links to relevant PRs, issues, benchmarks, or external resources

File Organization

Standard locations (create if none exist):

docs/adr/
  0001-use-postgresql.md
  0002-adopt-monorepo.md
  0003-api-versioning-strategy.md
  README.md          # index of all ADRs with one-line summaries

Index format for README.md:

# Architecture Decision Records

| # | Decision | Status | Date |
|---|----------|--------|------|
| 1 | [Use PostgreSQL](0001-use-postgresql.md) | Accepted | 2026-01-15 |
| 2 | [Adopt monorepo](0002-adopt-monorepo.md) | Accepted | 2026-02-01 |

Tips

  • Keep ADRs short — 1-2 pages max. If it's longer, the decision is too big (split it).
  • Write ADRs at decision time, not after. Retrospective ADRs lose the "alternatives considered" context.
  • ADRs are immutable once accepted. If a decision changes, create a new ADR that supersedes the old one.
  • Number them sequentially. Never reuse numbers.
  • Store them in the repo, next to the code they govern.
  • Review ADRs in PRs — they deserve the same scrutiny as code.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

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

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

OpenClaw

71.48%
按下载量换算400

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

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。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