qmd

Search markdown knowledge bases, notes, and documentation using QMD. Use when users ask to search notes, find documents, or look up information.

1.49x

Quality

82%

Does it follow best practices?

Impact

97%

1.49x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is qmd in tobi/qmd

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.

An efficient, highly actionable reference for the QMD tool with excellent executable examples and clear query-selection guidance. Its one real weakness is bundle structure: the existing references/mcp-setup.md is orphaned (never referenced from the body) while its content is partly duplicated inline.

Suggestions

Link references/mcp-setup.md from the body (e.g., a "MCP setup" section saying "See references/mcp-setup.md for client configuration and troubleshooting") instead of duplicating install/HTTP details inline.

Move the HTTP API curl example and the detailed "Other MCP Tools" table into references/mcp-setup.md, keeping only a pointer in SKILL.md.

Add a brief fallback step (e.g., "No results? Re-run with lex+vec or check `qmd collection list` / `qmd embed`") to close the workflow loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense: query types, syntax, and examples are conveyed via compact tables and terse bullets ("2-5 terms, no filler words", "First query gets 2x weight in fusion") with zero explanation of concepts Claude already knows. Every section adds tool-specific knowledge.	5 / 5
Actionability	Fully executable throughout: a copy-paste MCP query JSON, concrete CLI invocations ("qmd query $'lex: X\nvec: Y'", "qmd multi-get journals/2026-*.md -l 40"), a working curl example, and real query examples for each search type.	5 / 5
Workflow Clarity	The "Combining Types" table gives clear decision guidance ("Know exact terms → lex only", "Best recall → lex + vec") and the embedded status check is a nice pre-flight, but there is no explicit fallback loop (e.g., what to do on empty results) — though operations are read-only, so the validation cap does not apply.	4 / 5
Progressive Disclosure	Sections are well-organized, but the provided bundle file references/mcp-setup.md is never linked or signaled from the body, and its content (setup, MCP tool parameters, HTTP mode, troubleshooting) is duplicated inline — references present but not clearly signaled and content that should be separate is inline.	3 / 5
	Total	17 / 20 Passed

Description

78%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 description with an explicit "Use when..." clause and natural trigger phrases that clearly answer both what and when. Its main gaps are the single-action framing (search only, omitting retrieval) and one overly broad trigger phrase.

Suggestions

Mention retrieval alongside search (e.g., "Search and retrieve documents from markdown knowledge bases...") to reflect the get/multi_get capabilities.

Tighten the overly broad trigger "look up information" toward markdown-specific phrasing (e.g., "search my notes", "find that doc in my knowledge base") to reduce overlap with general lookup skills.

Dimension	Reasoning	Score
Specificity	"Search markdown knowledge bases, notes, and documentation" names the domain and one concrete action (search), but the skill also retrieves documents (get/multi_get per the body) which the description omits, so coverage is not comprehensive.	3 / 5
Completeness	It clearly answers what ("Search markdown knowledge bases, notes, and documentation using QMD") and when ("Use when users ask to search notes, find documents, or look up information") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"search notes", "find documents", and "look up information" are natural phrases users would say, with good keyword coverage (markdown, notes, documentation), but synonyms like "knowledge base lookup" or file extensions (.md) are missing.	4 / 5
Distinctiveness Conflict Risk	The markdown/QMD niche is mostly distinct from other skills, but the broad trigger "look up information" creates minor overlap risk with general lookup or web-search skills.	4 / 5
	Total	16 / 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: compozy/compozy
Path: .agents/skills/qmd/SKILL.md
Commit: a15f541

Reviewed: 3 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.