qmd

Hybrid local search over notes, docs, and transcripts.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/research/qmd/SKILL.md

Quality

Content

82%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 a thorough, highly actionable reference with clear workflows and verification, strong command coverage, and good internal navigation. The main gaps are minor trimmable prose and the absence of progressive disclosure into separate bundle files for the longer reference material.

Suggestions

Move the launchd plist, systemd unit, and "How the Search Pipeline Works" internals into separate reference files linked from the main body to improve progressive disclosure and reduce the inline token load.

Tighten explanatory prose like the context-description rationale to one line to lift conciseness toward 5.

Add an explicit validation gate in the Setup Workflow (e.g., "Only proceed to search once `qmd status` reports all collections embedded") to push workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands, tables, and configs rather than padding, and largely avoids explaining concepts Claude already knows; minor prose such as "Context metadata helps the search engine understand what each collection contains" could be trimmed, which fits the efficient-but-slightly-tightenable score-4 anchor.	4 / 5
Actionability	It provides copy-paste-ready commands for every common case (search/vsearch/query/get/multi-get/collection add/context add/embed/status/mcp), complete daemon config files (launchd plist, systemd unit), and concrete MCP YAML, fully matching the score-5 anchor for executable, common-case-covering guidance.	5 / 5
Workflow Clarity	The "Setup Workflow" is a clear 4-step sequence ending in a "Verify" checkpoint (`qmd status`), and Troubleshooting supplies error-recovery feedback loops for the batch embed operation; it is not a 5 because validation is not gated with explicit "only proceed when valid" language between steps.	4 / 5
Progressive Disclosure	Sections are well-organized with clear headers and a Quick Reference table providing easy navigation, and the external GitHub/Changelog references are real and clearly signaled; it is not a 5 because all ~415 lines live in one file with no one-level-deep bundle split for large reference blocks (daemon configs, pipeline internals).	4 / 5
	Total	17 / 20 Passed

Description

61%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 concise and names a clear, distinctive niche with reasonable natural trigger terms, but it lacks an explicit "Use when..." clause, which caps completeness and limits its ability to trigger reliably. Adding concrete trigger phrases would raise both completeness and trigger-term coverage.

Suggestions

Append a "Use when..." clause naming concrete triggers, e.g., "Use when searching notes, docs, knowledge bases, or meeting transcripts locally, or when the user mentions qmd or semantic search."

Add natural synonyms users say ("knowledge base", "meeting notes", "find in my docs") to broaden trigger-term coverage.

List one or two more concrete capabilities (e.g., "hybrid search with semantic reranking") to lift specificity above a single action.

Dimension	Reasoning	Score
Specificity	"Hybrid local search over notes, docs, and transcripts" names a clear domain and one concrete action (hybrid local search), but does not enumerate multiple specific capabilities, matching the score-3 anchor rather than the comprehensive list expected at 4-5.	3 / 5
Completeness	It gives a clear "what" (hybrid local search over notes/docs/transcripts) but no "Use when..." trigger clause, so per the missing-trigger-guidance cap it cannot exceed 3; the "when" is only weakly implied by the content types listed.	3 / 5
Trigger Term Quality	"notes, docs, and transcripts" are natural phrases users would actually say (e.g., "search my notes"), giving good keyword coverage; it is not a 5 because synonyms like "knowledge base" and "meeting notes" are absent.	4 / 5
Distinctiveness Conflict Risk	"Hybrid local search over notes, docs, and transcripts" carves a distinct niche with low conflict risk, though the notes/docs terms create minor overlap with closely related skills like obsidian, keeping it just below a 5.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/research/qmd/SKILL.md
Commit: d92bfa0

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.