mcp-management
Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, capability discovery, tool filtering, programmatic execution, or encountering context bloat, server configuration, tool execution errors.
69
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/mcp-management/skills/mcp-management/SKILL.mdQuality
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 solid description that clearly identifies its niche (MCP server management) and provides explicit trigger guidance with a 'Use for' clause covering multiple relevant scenarios. The trigger terms are well-chosen and distinctive. The main weakness is that the capability descriptions could be slightly more concrete — 'manage' and 'analyze' are somewhat vague compared to more specific action verbs.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (MCP servers) and lists some actions (discover, analyze, execute tools/prompts/resources), but the actions are somewhat generic and not fully concrete — 'manage' and 'analyze' are vague, and the list of capabilities could be more detailed. | 2 / 3 |
Completeness | Clearly answers both what ('Manage MCP servers - discover, analyze, execute tools/prompts/resources') and when ('Use for MCP integrations, capability discovery, tool filtering, programmatic execution, or encountering context bloat, server configuration, tool execution errors'). The 'Use for' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users working with MCP would say: 'MCP servers', 'MCP integrations', 'capability discovery', 'tool filtering', 'programmatic execution', 'context bloat', 'server configuration', 'tool execution errors'. Good coverage of the problem space. | 3 / 3 |
Distinctiveness Conflict Risk | MCP server management is a very specific niche. The trigger terms like 'MCP integrations', 'context bloat', 'server configuration' are highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill covers a broad set of MCP management capabilities but suffers from significant redundancy - the same Gemini CLI command appears three times, and 'bun' vs 'bunx' alternatives show identical commands. The content would benefit greatly from deduplication and tighter organization. Key gaps include missing error handling/validation workflows and incomplete concrete examples for the subagent pattern.
Suggestions
Eliminate redundancy: the Gemini CLI screenshot example appears 3 times and the 'bun vs bunx' alternatives show identical commands - consolidate into a single Quick Start section
Add error handling and validation steps: what happens when `list-tools` fails, when a server is unreachable, or when tool execution returns an error? Include concrete recovery steps
Provide a concrete example for the mcp-manager subagent pattern instead of just saying 'Dispatch subagent to handle MCP operations'
Remove the 'When to Use This Skill' and 'Key Benefits' sections - these explain things Claude can infer from the skill content itself, saving ~20 lines of context
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant verbosity and redundancy throughout. The 'Preferred: Using bun' and 'Alternative: Using bunx' sections show identical commands. The 'When to Use This Skill' section explains obvious use cases. 'Key Benefits' lists things Claude can infer. Multiple patterns repeat the same Gemini CLI example. The Quick Start section largely duplicates earlier content. | 1 / 3 |
Actionability | Provides some concrete commands (gemini CLI, bunx tsx scripts), but many sections are vague ('Dispatch subagent to handle MCP operations'), the mcp-manager subagent pattern is never shown concretely, and tool execution examples lack complete parameter examples. The 'bun' vs 'bunx' alternatives appear identical, creating confusion. | 2 / 3 |
Workflow Clarity | The execution priority (Gemini CLI → Direct Scripts → Subagent) provides a clear decision sequence, and the Quick Start gives ordered steps. However, there are no validation checkpoints - no guidance on what to do if tool discovery fails, if servers are misconfigured, or if execution returns errors. No feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | References assets/tools.json and .claude/.mcp.json as external files, and mentions an mcp-manager subagent. However, the skill itself is a monolithic wall of text with significant inline content that could be split out (e.g., implementation patterns, integration strategy). No clear links to separate reference files for detailed API docs or examples. | 2 / 3 |
Total | 7 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- secondsky/claude-skills
- Commit
88da5ff
- 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.