$ loading_
Search Markdown knowledge bases, notes, and docs to quickly find needed information.
This appears to be a prompt-only search skill with no required secrets and no declared remote endpoints, so overall risk is low. The main caution is supply-chain quality: the referenced open-source source is niche, has no declared license, and has unknown maintenance status.
The material explicitly states that no secrets or environment variables are required. No token, API key, or account credential handling is described, and no credential abuse path is evident.
No remote endpoint is declared, and the README describes it as a local markdown search engine. There is no evidence that user queries or document contents are sent to external services.
The system classifies this as prompt-only, and the reviewed material itself contains no executable logic. While the README mentions a local `qmd` CLI and shell examples, that appears to be companion-tool documentation rather than evidence of additional code-execution privileges in the skill itself.
Its stated purpose is to search local markdown knowledge bases, notes, and documentation, with document retrieval by path or glob. That normally implies read access to local document collections. No overbroad access beyond the stated purpose is shown, but if connected to a real tool, the search scope should be confined to expected collections.
On the positive side, there is a public GitHub repository and it is marked as open-source, which gives some auditability. However, the repo has 0 stars, unknown maintenance status, and no declared license, so maturity and maintenance signals are weak; dependencies and version pinning should be reviewed carefully. The README also includes an inline shell snippet; while it looks like a status-check example, it is another reason not to treat documentation text as executable instructions.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "qmd" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/nix-openclaw-tools/main/tools/qmd/skills/qmd/SKILL.md 2. Save it as ~/.claude/skills/qmd/SKILL.md 3. Reload skills and tell me it's ready
Search my Markdown notes for "Q3 budget review," find the related meeting notes, and summarize the key decisions and action items.
A list of relevant notes plus a summary of decisions, owners, and follow-up tasks.
Search the project documentation for "authentication middleware," tell me which files mention it, and extract the most relevant explanations.
Document paths that match, along with relevant excerpts or a concise summary.
Search the knowledge base for information about the "employee reimbursement process," turn it into clear steps, and cite the source documents.
A structured process guide with citations to the corresponding source documents.
Local search engine for markdown content.
!qmd status 2>/dev/null || echo "qmd CLI not found on this runtime PATH"
query{
"searches": [
{ "type": "lex", "query": "CAP theorem consistency" },
{ "type": "vec", "query": "tradeoff between consistency and availability" }
],
"collections": ["docs"],
"limit": 10
}
| Type | Method | Input |
|---|---|---|
lex | BM25 | Keywords — exact terms, names, code |
vec | Vector | Question — natural language |
hyde | Vector | Answer — hypothetical result (50-100 words) |
lex (keyword)
"connection pool" (quoted)performance -sports (minus prefix)handleError asyncvec (semantic)
"how does the rate limiter handle burst traffic""in the payment service, how are refunds processed"hyde (hypothetical document)
expand (auto-expand)
expand: question on its own lineexpand: with other typed lines — it's either a standalone expand query or a full query documentWhen a query term is ambiguous, add intent to steer results:
{
"searches": [
{ "type": "lex", "query": "performance" }
],
"intent": "web page load times and Core Web Vitals"
}
Intent affects expansion, reranking, chunk selection, and snippet extraction. It does not search on its own — it's a steering signal that disambiguates queries like "performance" (web-perf vs team health vs fitness).
| Goal | Approach |
|---|---|
| Know exact terms | lex only |
| Don't know vocabulary | Use a single-line query (implicit expand:) or vec |
| Best recall | lex + vec |
| Complex topic | lex + vec + hyde |
| Ambiguous query | Add intent to any combination above |
First query gets 2x weight in fusion — put your best guess first.
| Syntax | Meaning | Example |
|---|---|---|
term | Prefix match | perf matches "performance" |
"phrase" | Exact phrase | "rate limiter" |
-term | Exclude | performance -sports |
Note: -term only works in lex queries, not vec/hyde.
{ "collections": ["docs"] } // Single
{ "collections": ["docs", "notes"] } // Multiple (OR)
Omit to search all collections.
| Tool | Use |
|---|---|
get | Retrieve doc by path or #docid |
multi_get | Retrieve multiple by glob/list |
status | Collections and health |
qmd query "question" # Auto-expand + rerank
qmd query $'lex: X\nvec: Y' # Structured
qmd query $'expand: question' # Explicit expand
qmd query --json --explain "q" # Show score traces (RRF + rerank blend)
qmd search "keywords" # BM25 only (no LLM)
qmd get "#abc123" # By docid
qmd multi-get "journals/2026-*.md" -l 40 # Batch pull snippets by glob
qmd multi-get notes/foo.md,notes/bar.md # Comma-separated list, preserves order
curl -X POST http://localhost:8181/query \
-H "Content-Type: application/json" \
-d '{"searches": [{"type": "lex", "query": "test"}]}'
qmd collection add ~/notes --name notes
qmd embed
Watch file changes and automatically rebuild across any language or build system.
Mirror Discord history into SQLite for offline search, analysis, and reporting.
Search places, details, and reviews via Google Places with human or JSON output.
Search local WhatsApp Desktop chats, messages, and media metadata read-only.
Debug Node.js apps with inspect, breakpoints, heap, and CPU profiling.
Audit and harden OpenClaw hosts for security and operational health.
Let AI manage local Markdown notes as persistent memory across sessions.
Search, validate, and cross-reference structured Markdown knowledge vaults for AI workflows.
Search, browse, and trace backlinks in a published Markdown notes vault.
Search MDN docs for web APIs, syntax, and compatibility details.
Search local Markdown notes and manage tags, todos, and wiki links.
Ask questions over documents and get answers with exact source citations.