mcp-builder

Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

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

The content is lean, fully actionable, and well-structured, with executable commands and a validated workflow that includes failure-path testing. It is a strong, token-efficient skill body with no clear weaknesses.

Dimension	Reasoning	Score
Conciseness	The body uses lean bullets and compact command blocks without explaining what MCP is or how libraries work; every line earns its place and assumes Claude's competence.	3 / 3
Actionability	It provides copy-paste-ready "deepseek mcp" commands and concrete, typed design rules rather than vague direction, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The six-step workflow has an explicit validation step ("deepseek mcp validate, then deepseek mcp tools") and a failure-path feedback loop ("Test one happy path and one failure path"), meeting the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Under 50 lines with no external references needed, it relies on well-organized sections (Design Rules, DeepSeek Setup, Workflow), which the simple-skills note allows to score 3.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 specific and distinctive, naming concrete actions and transport types for a well-bounded niche. Its main gaps are the missing "MCP" abbreviation that users naturally say and the absence of an explicit "Use when..." trigger clause.

Suggestions

Add an explicit "Use when..." trigger clause, e.g. "Use when the user asks to create, configure, or debug an MCP server."

Include the natural abbreviation "MCP" alongside the spelled-out "Model Context Protocol" so the description matches terms users actually type.

Clarify what "codewhale" refers to (a platform? a CLI?) so the trigger context is unambiguous.

Dimension	Reasoning	Score
Specificity	"Design, build, configure, or debug" lists four concrete actions plus the "stdio and HTTP/SSE transports" detail, matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	The "what" is explicit, but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	It names "Model Context Protocol servers" and transport keywords, but omits the natural abbreviation "MCP" that users actually type, so it has relevant keywords while missing the common variation.	2 / 3
Distinctiveness Conflict Risk	Building MCP servers for a named platform with specific transports is a clear niche with distinct triggers, unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Hmbown/CodeWhale
Path: crates/tui/assets/skills/mcp-builder/SKILL.md
Commit: bc17240

Reviewed: about 15 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.