jobe-skills/ebook-library
Use when the user asks about a Calibre ebook library or book collection: find books, search metadata or full text in EPUB/AZW3 files, or locate book paths via Calibre databases.
98
98%
Does it follow best practices?
Impact
99%
1.80xAverage score across 4 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly defines its scope, includes natural trigger terms, and explicitly states both when to use and when not to use the skill. The inclusion of negative boundaries (what it does NOT do) is particularly effective for disambiguation. Minor note: it uses second person ('Use this skill when the user asks') which is slightly informal but still functional for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: search/browse a Calibre ebook library, find books by title/author/topic, locate file paths, and search inside EPUB/AZW3 text for quotes or passages. Also explicitly lists what it does NOT do. | 3 / 3 |
Completeness | Clearly answers both 'what' (find books by title/author/topic, locate file paths, search inside EPUB/AZW3 text) and 'when' ('when the user asks to search or browse a Calibre ebook library'). Also includes explicit negative triggers for when NOT to use it. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'search', 'browse', 'Calibre', 'ebook library', 'title', 'author', 'topic', 'file paths', 'EPUB', 'AZW3', 'quotes', 'passages'. These cover a good range of natural user language. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche: Calibre ebook library searching specifically. The explicit exclusions (conversion, metadata editing, downloads, recommendations, non-Calibre sources) further reduce conflict risk with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-organized skill that provides clear, actionable guidance for searching a Calibre library. Its main strengths are the concrete executable commands, explicit validation checkpoints, and well-defined fallback workflows. The only notable weakness is mild verbosity—some sections (result handling, quick response rules) overlap, and a few lines could be consolidated without losing clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but there's some redundancy between sections (e.g., result handling repeats what's already covered in quick response rules, and the orchestration fallback rules could be tighter). The decision tree and common commands sections are well-structured but the overall document could be trimmed by ~20%. | 2 / 3 |
Actionability | Every task maps to a concrete, copy-paste-ready bash command with specific flags and arguments. The JSON output examples for find_books.py and error responses give Claude clear expectations of what to parse and return. | 3 / 3 |
Workflow Clarity | The library discovery and validation section provides a clear numbered sequence with explicit validation checkpoints (test -r checks, stop-and-report on failure). The orchestration section provides well-defined fallback/retry loops for error recovery, and the decision tree clearly routes different user intents to specific tools. | 3 / 3 |
Progressive Disclosure | The skill is well-structured with clear sections progressing from discovery → decision tree → common commands → fallback rules → boundaries. It appropriately references `references/scripts.md` for detailed script arguments and output formats, keeping the main file at overview level with one-level-deep navigation. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents