Manages Claude Code skills from plugin marketplaces using the local-skills CLI. Use when the user wants to add, update, remove, list, or inspect skills from a marketplace, or when managing the project's .claude/skills/ directory with version-tracked skills. Triggers on "install a skill", "add skill from marketplace", "update skills", "list available skills", "remove skill", or "local-skills".
96
96%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 well-crafted skill description that excels across all dimensions. It provides specific actions, natural trigger terms users would actually say, explicit 'Use when' guidance, and a distinctive niche that won't conflict with other skills. The description follows best practices by using third person voice and being comprehensive without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'add, update, remove, list, or inspect skills from a marketplace' and 'managing the project's .claude/skills/ directory with version-tracked skills'. Clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Manages Claude Code skills from plugin marketplaces using the local-skills CLI') and when ('Use when the user wants to add, update, remove, list, or inspect skills...') with explicit trigger phrases listed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'install a skill', 'add skill from marketplace', 'update skills', 'list available skills', 'remove skill', 'local-skills'. These match natural user language patterns. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific niche: 'local-skills CLI', 'plugin marketplaces', '.claude/skills/ directory'. The combination of skill management + marketplace + specific CLI tool creates a clear, non-conflicting identity. | 3 / 3 |
Total | 12 / 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 managing Claude Code skills via the local-skills CLI. The content is well-structured with excellent command examples and workflow guidance. Minor improvement could be made by splitting detailed reference content into separate files for better progressive disclosure.
Suggestions
Consider moving the detailed command reference (add, ls, info, update, remove) to a separate COMMANDS.md file, keeping only quick examples in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only necessary information without explaining concepts Claude already knows. Tables and code examples are used effectively to convey information densely. | 3 / 3 |
Actionability | Provides fully executable commands with concrete examples covering multiple use cases. The specifier format table and command examples are copy-paste ready with clear variations. | 3 / 3 |
Workflow Clarity | The 'Workflow Guidance' section provides clear numbered sequences for common tasks with explicit validation steps (verify installation, check current state) and conditional handling for edge cases like local modifications. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in a single file. For a skill of this length (~120 lines), some content like the detailed 'How It Works' section or command reference could be split into separate files. | 2 / 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.
c10c616
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.