Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.
88
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates both purpose and usage triggers. Its main weakness is the lack of specific concrete actions beyond 'search' and some potential overlap with other document/search skills. The technical term 'hybrid search' may not resonate with users who don't know what that means.
Suggestions
Add specific concrete actions like 'performs full-text and semantic search', 'finds similar documents', or 'searches by keywords and meaning'
Include file type triggers like '.md files' or 'markdown files' to strengthen distinctiveness from general document search skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (markdown notes/docs) and general action (hybrid search), but lacks specific concrete actions like 'full-text search', 'semantic similarity matching', or 'filter by tags'. The phrase 'local hybrid search' is somewhat technical without explaining what it does. | 2 / 3 |
Completeness | Clearly answers both what ('Local hybrid search for markdown notes and docs') and when ('Use when searching notes, finding related content, or retrieving documents from indexed collections') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'searching notes', 'finding related content', 'retrieving documents', 'indexed collections'. These are phrases users would naturally use when looking for this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | While 'markdown notes' and 'indexed collections' provide some specificity, terms like 'searching notes' and 'finding related content' could overlap with general file search or knowledge base skills. The 'hybrid search' term helps but isn't a user-facing trigger. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that provides clear, actionable guidance for using qmd search. The content efficiently communicates when to use each search mode, provides executable examples throughout, and includes practical maintenance guidance including cron schedules. The only weakness is that all content is inline rather than using progressive disclosure for advanced features.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of concepts Claude already knows. Each section provides only necessary information without padding or verbose descriptions of what markdown or search engines are. | 3 / 3 |
Actionability | Provides fully executable commands throughout with copy-paste ready examples for installation, setup, search modes, retrieval, and maintenance. The cron examples are complete and specific. | 3 / 3 |
Workflow Clarity | Clear sequencing for setup (add collection → add context → embed), explicit guidance on which search mode to use when, and maintenance workflows with specific commands. The decision tree for search modes (BM25 first, vsearch as fallback, avoid query) is well-defined. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in a single file. For a tool with this many features (search modes, retrieval, maintenance, cron setup), some content like detailed options or advanced usage could be split into referenced files. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 | 8 / 11 Passed | |
2a8c94e
Table of Contents
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.