mcp-setup
Configure popular MCP servers for enhanced agent capabilities
36
32%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/mcp-setup/SKILL.mdQuality
Discovery
22%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 too vague and lacks both concrete actions and explicit trigger guidance. It names the domain (MCP servers) but fails to specify what configuration steps are performed, which servers are supported, or when Claude should select this skill. The phrase 'enhanced agent capabilities' is meaningless fluff that adds no discriminative value.
Suggestions
List specific concrete actions such as 'generate configuration files, set up authentication, install dependencies for MCP servers like filesystem, GitHub, Slack'.
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to set up, configure, or connect an MCP server, or mentions MCP tools, tool servers, or server configuration.'
Replace 'enhanced agent capabilities' with specific outcomes like 'enabling tool use through MCP protocol connections' to improve specificity and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description is vague — 'configure popular MCP servers' names a domain but doesn't list any concrete actions (e.g., install, authenticate, set up config files). 'Enhanced agent capabilities' is abstract fluff with no specifics. | 1 / 3 |
Completeness | The 'what' is weak (just 'configure' with no detail on what configuration entails), and there is no 'when' clause or explicit trigger guidance at all. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | 'MCP servers' is a relevant keyword a user might say, but the description lacks common variations or natural trigger terms like 'MCP setup', 'tool server', specific server names, or 'connect to MCP'. 'Configure' is somewhat natural but coverage is thin. | 2 / 3 |
Distinctiveness Conflict Risk | 'MCP servers' is a somewhat specific domain that narrows the scope, but 'configure' and 'enhanced agent capabilities' are generic enough that it could overlap with general setup/configuration skills or other MCP-related skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, concrete CLI commands for configuring MCP servers, which is its primary strength. However, it is excessively verbose—spelling out literal dialogue scripts, repeating server descriptions across sections, and including a massive completion message template. The monolithic structure with no progressive disclosure and the lack of per-server error recovery in the workflow are notable weaknesses.
Suggestions
Cut the literal AskUserQuestion dialogue scripts to brief bullet lists of menu options; Claude can construct conversational prompts on its own.
Move the completion message template, common issues, and custom server section into separate referenced files to improve progressive disclosure.
Add an explicit per-server validation step after each `claude mcp add` command (e.g., check exit code, run `claude mcp list` to confirm it appeared, retry or report on failure).
Remove redundant descriptions of what each server does—list them once in a compact table rather than repeating in menus, usage tips, and troubleshooting.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant verbosity throughout. The completion message template is extremely long and could be a brief note. The multi-step menu flow with full question/option text spelled out is overly prescriptive—Claude knows how to present menus. Explaining what each MCP server does repeatedly (in menus, usage tips, and troubleshooting) wastes tokens. The 'ask for API key' prompts are written out as literal dialogue scripts Claude doesn't need. | 1 / 3 |
Actionability | All CLI commands are concrete, copy-paste ready, and cover each server variant (stdio, http, with/without env vars). The custom server section provides complete command templates with placeholders. Configuration examples for company-context including the jsonc config are specific and executable. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (choose → gather info → add servers → verify → show completion), and verification via `claude mcp list` is included. However, there's no explicit validation/feedback loop after adding each server—no 'if the add command fails, do X' recovery step. For a multi-server batch configuration, missing per-server error handling caps this at 2. | 2 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no references to supporting documents. The custom server section, company-context convention, common issues, and the lengthy completion message template could all be split into separate files. With no bundle files provided and no external references, all content is inlined creating a very long document. | 1 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
679b418
- 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.