Mira Annotation Review
Review MIRA annotations in Markdown documents for semantic correctness, Markdown...
Install
npx skills add stencila/stencila --skill mira-annotation-review -g -a claude-code -y- Repository
- stencila/stencila914
- Category
- Writing
- Updated
- 3d ago
- License
- Apache-2.0
- Context cost
- Mediumabout 3,000 tokens
- Runs scripts
- No, instructions only
What it does
Review MIRA annotations in Markdown documents for semantic correctness, Markdown dialect validity, preservation, and relation integrity. Use for md, smd, qmd, and myst files containing research objects such as claims, evidence, questions, protocols, requests, typed claims, ids, and relations. Produces actionable findings without modifying files by default.
Overview
Review MIRA annotations in Markdown documents without changing the files unless the user explicitly asks for edits. Check that annotated research objects and relations are semantically grounded in the source text, valid for the document's Markdown dialect, internally consistent, and preservative of the original document structure and meaning.
This skill is for annotation quality assurance, not for general prose editing or adding new annotations. Prefer concrete, actionable findings over broad advice.
Required Inputs
| Input | Required | Description |
|---|---|---|
| Target Markdown content or file path | Required | The annotated Markdown text or one or more .md, .smd, .qmd, or .myst files to review |
| Markdown flavor or file extension | Optional | One of Stencila Markdown, Quarto Markdown, MyST Markdown, or plain Markdown; infer from path and syntax when absent |
| Review scope | Optional | Entire document, selected sections, specific annotation ids, or a particular concern such as relation integrity |
| MIRA vocabulary or project conventions | Optional | Any project-specific allowed object types, relation names, id style, or dialect conventions |
| Desired output detail | Optional | Summary only, full finding table, line-referenced findings, or prioritized remediation plan |
When used standalone, these inputs come from the user or the agent's prompt. When used within a workflow, the workflow's stage prompt will specify how to obtain them.
