ai-plugins AGENTS.md

ai-plugins

AI-assistant plugins for openEHR — official plugin marketplace of the openEHR Foundation.

Repository Purpose

This repo contains AI-assistant plugins that support openEHR work — packaged as a dual Claude Code and Cursor plugin marketplace; the skill content (SKILL.md, an open cross-tool format) is the canonical artifact, and each assistant gets a thin manifest layer (.claude-plugin/, .cursor-plugin/) around the same skills, so further assistants can be added the same way. It is not a specification repository — it provides AI-assisted tooling for authors working in specifications-XX repos.

Structure

ai-plugins/
├── .claude-plugin/marketplace.json    # Claude Code marketplace manifest
├── .cursor-plugin/marketplace.json    # Cursor marketplace manifest
├── docs/                              # Contributor and user documentation
└── plugins/<plugin-name>/             # One directory per plugin
    ├── .claude-plugin/plugin.json     # Claude Code plugin manifest
    ├── .cursor-plugin/plugin.json     # Cursor plugin manifest
    ├── README.md                      # Plugin purpose, install, and component inventory
    ├── skills/<skill-name>/           # Knowledge/workflow skills (model- or user-invoked)
    │   ├── SKILL.md                   # Skill definition (YAML frontmatter + body)
    │   └── references/                # Optional supplementary content
    ├── agents/<agent>.md              # Autonomous subagents (context-isolated, multi-file)
    └── commands/<command>.md          # User-invoked action commands (disable-model-invocation)

Current plugins: openehr-specs — 7 skills (spec authoring, review, governance, content patterns, amendment records, ITS-REST, BMM class generation), 3 subagents (spec-reviewer, xref-auditor, identifier-grounding), and 3 commands (amend, regen-classes, publish).

Key Conventions

• Plugin names: openehr-<domain> (mandatory prefix — flat global namespace); skill names: terse activity nouns with no prefix (auto-namespaced as <plugin>:<skill>).
• Component choice follows the nature of the work: skills = knowledge/workflows (model- or user-invoked); commands (commands/) = user-initiated actions, marked disable-model-invocation: true so they don't compete with knowledge-skill triggering; subagents (agents/) = context-heavy, multi-file, or adversarial work that would otherwise pollute the main context. Commands/agents reference their sibling knowledge skill rather than duplicating it.
• Skill description frontmatter is lean (~50–75 words): one what+scope sentence → a few representative triggers → short "Not for …" anti-triggers routing to the right sibling/plugin.
• Keep each SKILL.md body a lean overview (quick-reference + pointers); push bulky detail (tables, templates, format specs) into references/ so it loads only on demand.
• Versions must stay in sync across both plugin manifests (.claude-plugin/ and .cursor-plugin/), both marketplace entries, and the release tag ({name}--v{version}).
• Never invent identifiers, paths, class names, or conventions — ground everything in published openEHR specifications. To verify, read the spec's Markdown twin: take any specifications.openehr.org/...page.html URL and swap .html → .md.
• Do not duplicate community tooling (e.g. CKM/clinical modeling is covered by Cadasto's plugins); this repo covers ground the Foundation owns.