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.
82
77%
Does it follow best practices?
Impact
86%
3.18xAverage score across 3 eval scenarios
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 skill description that clearly identifies its specialized domain (MCP servers) and provides explicit trigger conditions. The description effectively covers both what the skill does and when to use it, with good trigger term coverage. The main weakness is that the capability verbs (manage, discover, analyze) could be more concrete about specific actions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (MCP servers) and lists several actions (discover, analyze, execute tools/prompts/resources), but the actions are somewhat generic and could be more concrete about what 'manage' and 'analyze' specifically entail. | 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). | 3 / 3 |
Trigger Term Quality | Includes good coverage of natural terms: 'MCP servers', 'MCP integrations', 'capability discovery', 'tool filtering', 'programmatic execution', 'context bloat', 'server configuration', 'tool execution errors' - these are terms users working with MCP would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | MCP servers is a very specific niche with distinct terminology (MCP integrations, context bloat, server configuration). Unlikely to conflict with other skills due to the specialized domain. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid actionable guidance with executable commands for MCP management. However, it suffers from repetition (showing bun/bunx alternatives multiple times, duplicating quick start info), lacks validation/error handling workflows, and could benefit from better content organization with external references for detailed patterns.
Suggestions
Remove duplicate command examples (bun vs bunx shown identically) - pick one as primary and note alternative once
Add validation steps after tool execution (e.g., 'Verify output: check for error field in response')
Add error handling guidance: what to do when Gemini CLI fails, when tool execution returns errors
Move detailed patterns (Pattern 1-4) to a separate PATTERNS.md file and link from overview
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Contains some unnecessary repetition (bun vs bunx alternatives shown multiple times, Method 1/2/3 duplicates Quick Start info). The 'When to Use This Skill' and 'Key Benefits' sections explain things Claude could infer, but overall structure is reasonable. | 2 / 3 |
Actionability | Provides concrete, executable bash commands throughout. Commands are copy-paste ready with specific tool names, flags, and argument formats. The CLI examples are complete and actionable. | 3 / 3 |
Workflow Clarity | Execution priority is clearly sequenced (Gemini CLI → Direct Scripts → Subagent), but lacks validation checkpoints. No error handling guidance for when commands fail, no verification steps after tool execution, and no feedback loops for debugging failed MCP operations. | 2 / 3 |
Progressive Disclosure | References external files (assets/tools.json, .claude/.mcp.json) appropriately, but the skill itself is somewhat monolithic. Multiple patterns and methods are inline when they could be split into separate reference files. The mcp-manager agent is mentioned but not linked. | 2 / 3 |
Total | 9 / 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 | |
- Repository
- secondsky/claude-skills
- Commit
90d6bd7
- 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.