Skip to main content
skill CX Codex

memory-metadata-search · basicmachines-co — Claude Code skill: query notes by metadata

A Basic Memory skill that finds notes by frontmatter fields — status, priority, confidence — instead of free text.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add basicmachines-co/basic-memory-skills --skill memory-metadata-search -a claude-code
Open on GitHub

What memory-metadata-search does

Basic Memory keeps structure in YAML frontmatter. Every key you add beyond the standard set (title, type, tags, permalink, schema) is indexed as entity_metadata and can be queried. This skill shows the agent how to build those queries with search_notes.

Filters go into metadata_filters as a JSON dictionary. Supported conditions: equality, list membership with $in, comparisons $gt, $gte, $lt, $lte, inclusive ranges with $between, and nested keys via dot notation such as {"schema.version": "2"}. Several keys combine with AND. Shortcuts exist for tags and status. A text query is optional — you can narrow one with filters or skip it entirely.

Operators need the $ prefix. Drop it and the filter is read as an exact-match key, returning nothing without an error: {"confidence": {"gte": 0.7}} fails where $gte works. Keys follow [A-Za-z0-9_-]+, an operator dict holds exactly one operator, and $between takes only [min, max].

What it helps with

  • pull every note with status: draft
  • list specs whose priority is high or critical
  • select notes above a confidence threshold
  • narrow a text search with a frontmatter field
  • filter notes by a nested schema field

Example prompts for the agent

  • Find notes with status: in-progress and type spec
  • Show notes where confidence is above 0.7
  • Find notes tagged security with status draft

How to install memory-metadata-search

1Skills CLI (Vercel)

npx skills add basicmachines-co/basic-memory-skills --skill memory-metadata-search -a claude-code

2Manually: put the files in place

~/.claude/skills/memory-metadata-search/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/memory-metadata-search/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about memory-metadata-search

How do I install memory-metadata-search in Claude Code?

Run npx skills add basicmachines-co/basic-memory-skills --skill memory-metadata-search -a claude-code. The skill lands at ~/.claude/skills/memory-metadata-search/SKILL.md.

What does memory-metadata-search do?

It teaches the agent to query Basic Memory notes by frontmatter fields: equality, ranges, list membership, nested keys. Everything runs through search_notes with metadata_filters.

How is metadata search different from text search?

Text search looks at note content, metadata search matches a known field value. You can combine them — a text query plus a status or priority filter.

Similar skills

All skills for Agent setup: memory, context, orchestration →

memory-metadata-search by other authors comes first.

From the same set6

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor