Clean up old cached plugin versions to free disk space. Use when the user says "clean cache", "cleanup plugins", "prune old versions", "free disk space", "plugin cache", "clear old plugins", or asks about plugin cache size.
76
95%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 well-crafted skill description with an explicit 'Use when' clause and strong trigger term coverage. Its main weakness is that the 'what' portion is somewhat thin — it describes only one action (cleaning up) rather than listing multiple specific capabilities. Overall it would perform well in skill selection scenarios.
Suggestions
Add more specific concrete actions to the capability description, e.g., 'Lists cached plugin versions, removes outdated entries, reports freed disk space' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (cached plugin versions, disk space) and one action (clean up), but doesn't list multiple specific concrete actions like listing cache contents, showing cache size, selecting specific versions to remove, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (clean up old cached plugin versions to free disk space) and 'when' (explicit 'Use when' clause with multiple trigger phrases covering various ways a user might request this). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'clean cache', 'cleanup plugins', 'prune old versions', 'free disk space', 'plugin cache', 'clear old plugins', and 'plugin cache size' — these are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche — plugin cache cleanup is a distinct task unlikely to conflict with other skills. The trigger terms are narrowly scoped to plugin caching and version pruning. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that is concise, fully actionable, and has a well-structured workflow with proper safety gates for a destructive operation. The dry-run → confirm → delete pattern with explicit tool usage for confirmation is exactly the right approach. No meaningful improvements needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every sentence serves a purpose. No unnecessary explanations of what caching is or how plugins work. The brief context line about Claude Code keeping every version is the minimum needed to justify the skill's existence. | 3 / 3 |
Actionability | Provides exact executable commands with proper variable references (`${CLAUDE_SKILL_DIR}`), specific flags (`--dry-run`, `--delete`), and clear tool usage (`AskUserQuestion`). Copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with an explicit dry-run validation step before any destructive action, a confirmation gate using a specific tool, and an early-exit condition (cache already clean). This is a textbook feedback loop for a destructive operation. | 3 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized with a clear header and numbered workflow. No external references are needed, and the structure is clean and easy to navigate. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
dd10cc1
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.