askill
qmd-setup

qmd-setupSafety 95Repository

Set up @tobilu/qmd semantic search for mnemonic memories. Registers collections, builds indexes, and generates embeddings. Run this once per machine.

5 stars
1.2k downloads
Updated 2/18/2026

Package Files

Loading files...
SKILL.md

QMD Setup Skill

Bootstrap @tobilu/qmd for semantic search over mnemonic memories.

Prerequisites

  • Node.js >= 22node --version
  • qmd CLInpm i -g @tobilu/qmd

Automated Setup

Run the setup script:

bash tools/qmd-setup.sh

The script will:

  1. Check prerequisites (Node.js >= 22, qmd installed)
  2. Resolve MNEMONIC_ROOT from ~/.config/mnemonic/config.json
  3. Discover memory roots dynamically:
    • {MNEMONIC_ROOT}/{org}/ → collection mnemonic-{org}
    • {MNEMONIC_ROOT}/default/ → collection mnemonic-default
    • .claude/mnemonic/ → collection mnemonic-project
  4. Run qmd update (index) + qmd embed (embeddings)
  5. Validate with qmd status and a test search

Note: First qmd embed downloads ~2 GB of GGUF models.

Manual Setup

If you prefer to set up manually:

MNEMONIC_ROOT is resolved from ~/.config/mnemonic/config.json (defaults to ~/.local/share/mnemonic). Adjust the paths below to match your config:

# 1. Register collections (replace paths with your MNEMONIC_ROOT)
qmd collection add "${MNEMONIC_ROOT:-$HOME/.local/share/mnemonic}/zircote/" --name mnemonic-zircote
qmd collection add "${MNEMONIC_ROOT:-$HOME/.local/share/mnemonic}/default/" --name mnemonic-default
qmd collection add "$(git rev-parse --show-toplevel)/.claude/mnemonic/" --name mnemonic-project  # if exists

# 2. Build index
qmd update

# 3. Generate embeddings (downloads models on first run)
qmd embed

# 4. Validate
qmd status
qmd search "test" -n 3

After Setup

Use search commands:

CommandTypeRequires
qmd search "query"BM25 keywordqmd update
qmd vsearch "query"Semantic vectorqmd embed
qmd query "query"Hybrid (BM25 + vector)Both

Scope to a specific collection:

qmd search "auth" -c mnemonic-zircote    # org memories only
qmd search "auth" -c mnemonic-project    # this repo only
qmd search "auth"                        # all collections

Re-indexing

After adding new memories, re-index with /mnemonic:qmd-reindex or:

qmd update && qmd embed

Indexing is not automatic — run after captures or bulk imports.

Install

Download ZIP
Requires askill CLI v1.0+

AI Quality Score

91/100Analyzed 2/24/2026

High-quality technical skill for setting up @tobilu/qmd semantic search. Provides clear prerequisites, automated and manual setup paths, usage commands with tables, and re-indexing instructions. Well-structured with good clarity. Located in dedicated skills folder with relevant tags. Scores high on all dimensions except minor deduction for no troubleshooting section. Reusable across machines.

95
95
85
85
90

Metadata

Licenseunknown
Version-
Updated2/18/2026
Publisherzircote

Tags

ci-cdllmsecuritytesting