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

92%

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

85%

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, clearly sequenced, and well-organized, with concrete MCP/CLI syntax and validation in the index-resolution script. Its main weakness is conciseness: the Commands and When-to-Search sections overlap and the MCP-preference rule is repeated, which could be consolidated.

Suggestions

Consolidate the overlap between 'Commands' and 'When to Search': keep Commands as the syntax reference and have When-to-Search reference operation types (e.g., 'hybrid query') instead of restating full MCP argument shapes.

State the MCP-preference rule once in 'Tool Surfaces — Preference Order' and avoid restating 'prefer MCP' in the Commands, When-to-Search, and section intros.

Consider moving the multi-line index-name resolution Node script into a referenced helper file to slim the SKILL.md body while keeping the inline validation guidance.

Dimension	Reasoning	Score
Conciseness	The body is operational and free of concept-padding, but the 'Commands' and 'When to Search' sections overlap (both restate the full MCP call syntax per operation) and the MCP-preference rule is restated several times, so it could be tightened — matching the score-2 anchor rather than the every-token-earns-its-place score-3 anchor.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: exact MCP argument shapes ('searches=[{type:"lex", query:"..."}]'), full CLI commands ('qmd --index <name> query "..." --json -n 10'), and an explicit bootstrap command, matching the score-3 anchor for fully executable code/commands.	3 / 3
Workflow Clarity	The pick-highest-surface-and-stop decision flow is clearly sequenced, and the index-name resolution script has an explicit validation checkpoint ('process.exit(1)' on an invalid pin); no destructive batch operations lack feedback loops, satisfying the score-3 anchor.	3 / 3
Progressive Disclosure	A single, well-organized SKILL.md with clear section headers, an in-page anchor link, and one-level-deep references to external vault files (vault-manifest.json, .scripts/qmd-bootstrap.ts); no bundle files are needed, matching the score-3 anchor for clear overview with well-signaled navigation.	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.

The description is strong across all dimensions, clearly stating what the skill does, when to trigger it, and its distinct niche. It is somewhat verbose — the full MCP/CLI/Grep preference order with tool names is operational detail that largely duplicates the body — but this does not reduce its specificity, trigger coverage, completeness, or distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and specific tools ('Search the vault using QMD semantic search', 'mcp__qmd__query', 'qmd --index <name> ...', 'Grep/Glob'), matching the score-3 anchor for multiple specific concrete actions rather than just a domain plus some actions.	3 / 3
Completeness	Explicitly answers both what ('Search the vault using QMD semantic search') and when ('Use PROACTIVELY before reading files', 'Trigger proactively for...'), matching the score-3 anchor with explicit triggers rather than implied timing.	3 / 3
Trigger Term Quality	Natural trigger terms users would say are well covered ('past decisions, incidents, people, meetings, architecture, patterns'), satisfying the score-3 anchor for good coverage rather than only some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	Has a clear QMD/vault-search niche and explicitly subordinates Grep/Glob as a last-resort fallback, making conflict with other skills unlikely; voice is imperative/third-person with no first/second-person framing penalty.	3 / 3
	Total	12 / 12 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: aa16349

Reviewed: about 15 hours 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.