Agent Skills › harumiWeb/exstruct › adr-indexer

adr-indexer

GitHub

用于在架构决策记录（ADR）新增、更新或变更时，扫描源文件并同步更新README、索引和决策地图等元数据制品，确保衍生文档与源文件状态一致。

.agents/skills/adr-indexer/SKILL.md harumiWeb/exstruct

Trigger Scenarios

ADR文件被添加、更新或重新分类需要刷新面向人类和AI代理的ADR映射

Install

npx skills add harumiWeb/exstruct --skill adr-indexer -g -y

More Options

Non-standard path

npx skills add https://github.com/harumiWeb/exstruct/tree/main/.agents/skills/adr-indexer -g -y

Use without installing

npx skills use harumiWeb/exstruct@adr-indexer

指定 Agent (Claude Code)

npx skills add harumiWeb/exstruct --skill adr-indexer -a claude-code -g -y

安装 repo 全部 skill

npx skills add harumiWeb/exstruct --all -g -y

预览 repo 内 skill

npx skills add harumiWeb/exstruct --list

SKILL.md

Frontmatter

{
    "name": "adr-indexer",
    "description": "Maintain ExStruct ADR index artifacts by scanning ADR files and synchronizing README, index.yaml, and decision-map.md metadata. Use when ADRs are added, updated, superseded, or reclassified and the repository needs a refreshed ADR map for humans and AI agents."
}

ADR Indexer

Refresh the derived ADR map after the source ADRs change.

Read

dev-docs/agents/adr-governance.md
dev-docs/agents/adr-workflow.md
dev-docs/specs/adr-index.md
All ADR files under dev-docs/adr/
Existing dev-docs/adr/README.md, dev-docs/adr/index.yaml, dev-docs/adr/decision-map.md

Workflow

Scan the ADR files and collect normalized metadata:
- id
- title
- status
- primary_domain
- domains
- supersedes
- superseded_by
- related_specs
Compare the normalized metadata with README.md, index.yaml, and decision-map.md.
Update the derived artifacts so that status, primary domain, domain grouping, and supersede relationships match the ADR source files.
Report any ambiguity that cannot be derived from the ADR text alone.