Menu
Use when validating markdown links or Mermaid diagrams.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | md-validation |
| type | reference |
| description | Use when validating markdown links or Mermaid diagrams. |
Meridian's markdown validation commands work on any markdown file or directory.
meridian kg check [path]: broken-link gate. Exit 0 clean, 1 broken
links. Run before committing doc changes.meridian kg graph [path]: link topology visualization. Use to understand
doc structure and find orphan pages.meridian kg [path]: quick stats (file count, link count, broken count).Context aliases work as path: kb, strategy, work resolve to their
context directories (e.g. meridian kg check kb, meridian kg graph strategy).
meridian mermaid check [path]: Mermaid diagram validation (syntax +
style warnings). Run after diagram edits.meridian kg [path]: quick sanity checkmeridian kg check [path]: catch broken linksmeridian mermaid check [path]: validate diagramsUse meridian kg --help and meridian mermaid --help for full flag coverage.
See resources/mermaid-authoring.md for diagram authoring rules (quoting,
line breaks, reserved words, themes).
See resources/command-reference.md for detailed flags and warning categories.
Use when grilling should be grounded primarily in project artifacts. Loads `/grill`, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs.
Load for large human-facing outputs: reports, docs, multi-section explanations, artifacts. Choose the right form for each beat (prose, diagram, table, mockup) and put the answer first, depth behind it. If the medium allows, use progressive disclosure.
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Anchor work in a work item: artifacts on disk, not in context.
Investigate and engage concurrently: don't block on evidence before surfacing your read.
Use when exploring or changing the codebase: read AGENTS.md first, use .context/CONTEXT.md for detail, keep intent docs succinct.