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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

A well-organized, highly actionable skill body with a clear workflow and appropriate offloading of MCP setup to a single one-level-deep reference. Its main weakness is repetition of the query-expansion guidance, which inflates length without adding new information.

Suggestions

Consolidate the 'do not lean on query expansion / write intent:lex:vec:hyde yourself' guidance into one authoritative section and reference it from the others instead of restating it in 'How search works', 'Pick the right search mode', and 'Pitfalls'.

Trim the repeated 'do not pipe through sed/head/tail' explanation — state the rule with one example in 'Retrieve sources' and shorten the Pitfalls restatement to a one-line pointer.

Consider moving the detailed 'Pick the right search mode' query-field reference into a reference file so the top of SKILL.md stays a lean quick-start, since the body is long for a single-purpose search skill.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and command-driven, but the 'do not lean on query expansion' guidance is restated at least four times (How search works, Pick the right search mode, and twice in Pitfalls), and the overall length could be tightened without losing clarity.	2 / 3
Actionability	Provides many copy-paste-ready, fully executable `qmd` commands with concrete flags, suffixes, and JSON examples rather than pseudocode or vague direction.	3 / 3
Workflow Clarity	States an explicit 3-step retrieval workflow, includes a fallback when model/GPU commands fail, guards index mutation ('Only mutate indexes when the user asked'), and offers diagnostics via `qmd doctor`.	3 / 3
Progressive Disclosure	Keeps operational guidance inline in SKILL.md while splitting the bulkier MCP-client configuration into a clearly signaled, one-level-deep reference (references/mcp-setup.md), which exists as a real file.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, third-person description that states concrete capabilities and an explicit, well-covered trigger clause for when to use the skill. It avoids vague fluff and over-claims while remaining concise.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Search local markdown knowledge bases, notes, docs, wikis, and transcripts' plus 'find notes, retrieve documents, inspect a wiki, answer from indexed markdown, or set up QMD access'), matching the top anchor rather than the partial 'names some actions' level.	3 / 3
Completeness	Explicitly answers both what ('Search local markdown knowledge bases...') and when ('Use when users ask to find notes, retrieve documents...'), with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Uses natural phrases a user would actually say ('find notes', 'retrieve documents', 'inspect a wiki', 'set up QMD') with good coverage, not jargon or a single narrow term.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (QMD over local markdown knowledge bases) with distinct triggers and third-person voice, making overlap with other skills unlikely.	3 / 3
	Total	12 / 12 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
Commit: e428df7

Reviewed: 6 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.