qmd
Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.
75
72%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./src/skills/bundled/qmd/SKILL.mdQuality
Discovery
67%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 functional and well-structured with a clear 'Use when' clause, which is its strongest aspect. However, it lacks specificity in concrete actions and could benefit from more natural trigger terms and distinctive language to differentiate it from other search or document retrieval skills.
Suggestions
Add more specific concrete actions such as 'index markdown files', 'perform semantic and keyword search', 'rank results by relevance', or 'search across folders'.
Expand trigger terms with natural variations users might say, such as 'look up notes', 'knowledge base', 'vault search', 'find in docs', '.md files', or 'semantic search'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (markdown notes/docs) and the general action (hybrid search), but doesn't list specific concrete actions like 'index files', 'rank by relevance', 'filter by tags', etc. It's more of a single capability statement than a list of specific actions. | 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 an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes some natural keywords like 'searching notes', 'finding related content', 'retrieving documents', and 'indexed collections', but misses common variations users might say such as 'look up', 'knowledge base', 'vault', 'find in notes', 'semantic search', or specific file types like '.md'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'local hybrid search' and 'indexed collections' provides some distinctiveness, but 'searching notes' and 'finding related content' are fairly broad and could overlap with file search tools, grep-based skills, or general document retrieval skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with clear executable commands and a well-structured decision tree for search mode selection. Its main weakness is moderate verbosity—some sections repeat performance information, and a few explanatory passages don't add value for Claude. The content could benefit from splitting detailed reference material (cron setup, model cache details) into separate files.
Suggestions
Remove or condense the 'When to use (trigger phrases)' section and the 'Relationship to Clawdbot memory search' section—these explain things Claude can infer from context.
Consolidate the duplicated performance information between 'Default behavior', 'Search modes', and 'Performance notes' into a single concise section or table.
Move detailed cron scheduling examples and model/cache configuration into a separate reference file to keep the main skill leaner.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary sections like 'When to use (trigger phrases)' which Claude can infer, the 'What it indexes' section has filler ('In our testing, "messy" Markdown is fine'), and the 'Relationship to Clawdbot memory search' section explains concepts Claude could figure out. The performance notes are somewhat repetitive across sections. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready commands for installation, setup, searching, retrieval, and maintenance. Commands include concrete flags and options with clear explanations. The cron examples are specific and complete. | 3 / 3 |
Workflow Clarity | The setup workflow is clearly sequenced (install → add collection → embed). The default behavior section provides a clear decision tree (start with BM25 → fall back to vsearch → avoid query). Maintenance workflows are explicit with update/embed steps. The search mode escalation path serves as a validation/fallback loop. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers, but everything is in a single file that runs fairly long. The performance notes, models/cache info, and cron scheduling details could be split into separate reference files. No external references are provided for advanced configuration or troubleshooting. | 2 / 3 |
Total | 10 / 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 | |
- Repository
- alsk1992/CloddsBot
- Commit
e71a5f6
- Reviewed
Table of Contents
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.