qmd

Search local markdown knowledge bases, notes, docs, and wikis with QMD. Use when users ask to find notes, retrieve documents, inspect a wiki, answer from indexed markdown, or set up QMD access.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality, actionable skill body with executable commands across all common QMD operations, a clearly sequenced core workflow with safety gating, and well-structured progressive disclosure via a real referenced file. Minor conciseness gains are available from deduplicating the query-expansion guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational with executable command blocks and no padding about basics, but the 'write query fields yourself / don't lean on expansion' guidance repeats across sections and some option explanations (e.g. --full-path) could be trimmed, keeping it at anchor 4 rather than 5.	4 / 5
Actionability	It provides copy-paste-ready commands across the common cases — qmd search/query/get/multi-get with real flags, the :from:count suffix, JSON filter AST, and an MCP payload — matching the anchor 5 fully-executable criterion.	5 / 5
Workflow Clarity	The search→retrieve→cite workflow is explicitly sequenced with a typical-loop example, index mutation is gated behind explicit user intent, and qmd doctor serves as an error-recovery loop, but the main workflow lacks a fully explicit validate→fix→retry checklist, fitting anchor 4.	4 / 5
Progressive Disclosure	The body is clearly sectioned with headers and offloads MCP setup to a verified one-level-deep reference (references/mcp-setup.md), keeping the overview inline and navigation easy, matching anchor 5.	5 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that clearly answers both what QMD does and when to use it, with natural trigger phrases and a distinct niche. Minor room to add file-extension synonyms and broaden the action vocabulary for a perfect score.

Dimension	Reasoning	Score
Specificity	Names the domain (local markdown KBs, notes, docs, wikis) and several concrete actions (search, find notes, retrieve documents, inspect a wiki), with only minor coverage gaps — not a comprehensive action list, so it sits at anchor 4 rather than 5.	4 / 5
Completeness	It explicitly states both what the skill does ('Search local markdown knowledge bases... with QMD') and when to use it ('Use when users ask to find notes, retrieve documents, inspect a wiki, answer from indexed markdown, or set up QMD access'), matching the anchor 5 example.	5 / 5
Trigger Term Quality	Natural user phrasing is well represented ('find notes', 'retrieve documents', 'inspect a wiki', 'set up QMD access') with good synonym coverage, though it misses file-extension variants like '.md' that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	QMD's local-indexed-markdown niche and tool-specific triggers make it mostly distinct with only minor overlap risk against generic note-search skills, fitting anchor 4 rather than the fully-niche anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: tobi/qmd
Path: skills/qmd/SKILL.md
Commit: 04e4dbd

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.