mcp-setup

Configure popular MCP servers for enhanced agent capabilities

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-sequenced with a real verification checkpoint, but it is a long single-file monolith with duplicated troubleshooting and no progressive disclosure via reference files. Splitting peripheral detail out of SKILL.md would tighten the core flow.

Suggestions

Deduplicate troubleshooting: keep a single "Common Issues" section and have the Step 5 completion message point to it rather than restating the same guidance.

Move the per-server configuration blocks and/or the completion-message template into a reference file (e.g. references/SERVERS.md) and link to it from the main flow, improving progressive disclosure and conciseness.

Trim the Overview/Step 1 intro overlap with the frontmatter description to tighten the opening.

Dimension	Reasoning	Score
Conciseness	The body is procedural and avoids over-explaining concepts Claude already knows, but troubleshooting guidance is duplicated in both the Step 5 completion message and the "Common Issues" section, and the completion-message template is lengthy.	2 / 3
Actionability	It provides copy-paste-ready `claude mcp add` commands for each named server, specific AskUserQuestion text and options, and parameterized templates for custom stdio/http servers with clearly marked placeholders.	3 / 3
Workflow Clarity	A clear five-step sequence (choose → gather → add → verify → complete) includes an explicit verification checkpoint (Step 4, `claude mcp list`) and an error-recovery feedback loop in the Common Issues section.	3 / 3
Progressive Disclosure	Sections are well-organized, but the 245-line body is monolithic with all content inline and no external references; per-server configs, the completion template, and troubleshooting could be split into reference files.	2 / 3
	Total	10 / 12 Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is clear about its domain and core action but stops there: it lacks explicit trigger guidance, lists only one concrete action, and pads with the vague phrase "enhanced agent capabilities." Adding a "Use when..." clause would raise its highest-weighted dimension.

Suggestions

Add an explicit trigger clause, e.g. "Use when setting up or adding MCP servers/tools to Claude Code, or when the user asks to extend Claude with external integrations like web search, file access, or GitHub."

Replace "for enhanced agent capabilities" with concrete capabilities (e.g. "web search, filesystem access, and GitHub integration") to improve specificity and natural trigger terms.

Include common user phrasings such as "add MCP tools", "set up MCP", or "Model Context Protocol" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain and one action ("Configure popular MCP servers") but lists only a single action rather than multiple specific ones, and "for enhanced agent capabilities" is vague fluff.	2 / 3
Completeness	It states what the skill does (configure MCP servers) but provides no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 2.	2 / 3
Trigger Term Quality	"Configure" and "MCP servers" are relevant keywords a user might say, but "enhanced agent capabilities" is not natural user speech and common variations ("add MCP tools", "set up MCP", "Model Context Protocol") are absent.	2 / 3
Distinctiveness Conflict Risk	"MCP servers" is a recognizable niche, but without explicit distinct triggers it could overlap with other configuration or MCP-related skills.	2 / 3
	Total	8 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Commit: 6c59219

Reviewed: about 8 hours ago

Table of Contents

Discovery Implementation Validation

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.