Content
78%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-organized, mostly lean skill body that gives concrete, executable MCP tool guidance across three operations with clear sections. Adding one example call per tool and trimming the redundant 'When to Use' section would push it higher.
Suggestions
Add a short example invocation for each tool (e.g., `search_prompts(query="code review", limit=5)`) to make guidance copy-paste ready.
Trim or remove the 'When to Use This Skill' section since its content duplicates the frontmatter description.
Note expected error or empty-result handling for `search_prompts` and `get_prompt` so Claude knows what to do when nothing is found.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and free of padding about what prompts are, but the 'When to Use This Skill' section restates the frontmatter description and the 'Present results showing' list could be slightly tightened. | 4 / 5 |
Actionability | Concrete tool names with typed parameters and defaults (query, limit, type, category, tag, id, outputType, outputFormat) are executable, but no example invocations with actual values are shown — a minor gap. | 4 / 5 |
Workflow Clarity | Each operation (search, get, improve) is sequenced with clear parameter steps and presentation guidance; operations are read-mostly so validation checkpoints are not required, though no error-handling guidance is given. | 4 / 5 |
Progressive Disclosure | A compact, single-file skill with no need for external references, organized into clearly labeled sections (When to Use, Available Tools, How to…, Guidelines) — well-organized structure fits the simple-skill exception. | 5 / 5 |
Total | 17 / 20 Passed |