canvascoding/canvas-notebook / seed_skills/qmd
qmd
VerifiedSearch the Canvas Notebook workspace with qmd. Use when the user asks to find files, search workspace content, or locate related notes/documents. Default to mode=search (BM25), use vsearch (vector) only as fallback, avoid query (hybrid) by default as it is expensive. Triggers: find files, search workspace, locate notes, Finde, suche, workspace search, content search, qmd.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.2 KB |
| agents/canvas.yaml | config | 185 B |
SKILL.md
View on GitHub---
name: qmd
description: "Search the Canvas Notebook workspace with qmd. Use when the user asks to find files, search workspace content, or locate related notes/documents. Default to mode=search (BM25), use vsearch (vector) only as fallback, avoid query (hybrid) by default as it is expensive. Triggers: find files, search workspace, locate notes, Finde, suche, workspace search, content search, qmd."
compatibility: Requires Bun >= 1.0.0 and SQLite3
allowed-tools: Bash(qmd:*)
metadata:
version: "1.0"
author: canvas-studios
---
# Workspace Search (qmd)
Local workspace search for Canvas Notebook. Searches direct text files via `workspace-text` and derived document text such as DOCX extracts via `workspace-derived`.
## When to Use
Use this skill when the user requests:
- "Search my notes"
- "Find related documents"
- "Search my workspace"
- "Search for ... in my workspace"
- "Where is ..."
- "Finde ..."
## Default Behavior
- Use the PI tool contract: `qmd({ query, mode, limit, collection })`
- Prefer `mode=search` (BM25) - fast and safe as the default
- Use `mode=vsearch` only if keyword search fails and semantic similarity is needed
- Avoid `mode=query` unless it was explicitly enabled for this runtime or the user explicitly asks for the expensive path
## Parameters
- **query** (required): Search query
- **mode**: Search mode (search, vsearch, query). Default: search
- **collection**: Collection to search. Default: workspace-text + workspace-derived
- **limit**: Maximum number of results. Default: 10
## Search Modes
- `qmd search` (default): Fast keyword search (BM25)
- `qmd vsearch` (last resort): Semantic similarity (vector). Often slow due to local LLM before lookup.
- `qmd query` (mostly skip): Hybrid search + LLM reranking. Often slower than vsearch.
## Examples
Standard search:
`qmd({ query: "my search term", mode: "search" })`
Specific collection:
`qmd({ query: "search term", collection: "workspace-text" })`
More results:
`qmd({ query: "search term", limit: 10 })`
Semantic search (slower):
`qmd({ query: "conceptually similar content", mode: "vsearch" })`
## Requirements
- Bun >= 1.0.0 (automatically installed)
- SQLite3 (available in container)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |