qmd

Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcp__qmd__query, mcp__qmd__get, mcp__qmd__multi_get, mcp__qmd__status — if they appear in your tool menu, use them first; (2) CLI `qmd --index <name> ...` as fallback; (3) Grep/Glob only when QMD is not installed. Trigger proactively for past decisions, incidents, people, meetings, architecture, patterns, or any vault content — and after creating/editing notes to check for duplicates and related content.

Quality

81%

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

71%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.

The body is highly actionable with concrete MCP and CLI examples and a clear surface-preference workflow, but it leans verbose in places and keeps all detail inline rather than offloading reference material to bundled files.

Suggestions

Tighten the inline Node slug-resolution block or move it to a script in ./scripts/ so the main body stays lean.

Add an explicit validation checkpoint after bulk changes (e.g. run a status/count query to confirm the index is populated) to strengthen the workflow feedback loop.

Split the Commands catalog or index-name resolution into a reference file under ./references/ and link to it from SKILL.md for cleaner progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete tool listings, but the inline Node slug-resolution script and repeated restating of the preference order add length that could be tightened or moved to a reference.	3 / 5
Actionability	Fully executable guidance throughout — concrete MCP call signatures, exact CLI commands with arguments, and a copy-paste bootstrap command covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced preference order and a bootstrap flow with an idempotency note, but bulk-change and index-management steps lack an explicit validate/verify checkpoint to confirm the index is usable before relying on it.	4 / 5
Progressive Disclosure	Well-organized into headed sections, but everything lives inline in SKILL.md with no external reference files — the slug-resolution script and command catalog could be split out for a vault-scoped skill of this length.	3 / 5
	Total	15 / 20 Passed

Description

91%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.

The description is specific, trigger-rich, and explicitly covers both what the skill does and when to use it, with strong distinctiveness. It is dense rather than padded, though the long MCP tool enumeration makes it somewhat heavy for a description field.

Dimension	Reasoning	Score
Specificity	Lists several concrete surfaces and actions — the four MCP tools by name, the CLI with subcommands, and Grep/Glob — with minor gaps in coverage (it names interfaces rather than the full set of operations like embed/update).	4 / 5
Completeness	Explicitly answers both 'what' (QMD semantic search across three surfaces with a preference order) and 'when' ('Use PROACTIVELY before reading files' plus a concrete trigger list), with clear trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural triggers including 'past decisions, incidents, people, meetings, architecture, patterns' plus duplicate/related-content checks, covering both conceptual and concrete phrasings users would say.	5 / 5
Distinctiveness Conflict Risk	Has a clear niche — vault semantic search via QMD-specific tool names and CLI — with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: breferrari/obsidian-mind
Path: .claude/skills/qmd/SKILL.md
Commit: b84464b

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.