mcp-patterns

Model Context Protocol (MCP) server patterns for building integrations with Claude Code. Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool.

2.15x

Quality

—

Does it follow best practices?

Impact

97%

2.15x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

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 with a complete executable server example and clean configuration snippets, and it is well-organized. Its main weaknesses are duplicated reference listings, an implicit rather than explicit build workflow, and reference pointers to bundle files that are not present.

Suggestions

Remove one of the two reference listings (Quick Reference table or Additional Resources) or merge them so each reference file appears once, tightening conciseness.

Add an explicit build-and-test sequence (e.g. 1. implement handlers, 2. run local validation, 3. add to Claude Desktop config, 4. verify the tool appears) with a validation checkpoint to raise workflow clarity.

Create the referenced ./references/*.md files (tool-patterns, resource-patterns, auth-patterns, state-patterns, testing-patterns) so the signaled progressive-disclosure navigation resolves to real content.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with no concept padding, but the opening line restates the frontmatter description and the five reference files are listed twice (once in the Quick Reference table and again in Additional Resources), so it could be tightened; not every token earns its place.	2 / 3
Actionability	A complete, executable Python MCP server (imports, decorators, tool handlers, stdio main loop) plus copy-paste-ready Claude Desktop JSON config (basic and uv variants) and a concrete project layout match the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	Sections imply an order (server -> layout -> config) and the Common Issues table offers implicit troubleshooting, but there is no explicit step sequence with validation checkpoints or a build-test-debug feedback loop, so it sits between the listed-but-gaps anchor and the explicit-checkpoint anchor.	2 / 3
Progressive Disclosure	The body is well-sectioned and the five reference paths are clearly signaled one level deep, matching score-3 organization; however the referenced bundle files (./references/*.md) do not actually exist in the bundle, so the signaled navigation leads to dead ends and cannot earn a 3.	2 / 3
	Total	9 / 12 Passed

Description

90%

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 clearly defines its MCP-server niche, uses third-person voice, and provides explicit trigger terms answering both what and when. Its only weakness is that the capability statement stays somewhat abstract rather than listing concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and a general action ("MCP server patterns for building integrations with Claude Code") but does not enumerate multiple concrete actions like 'build tool handlers', 'expose resources', or 'configure transports'; it is above the vague anchor but short of the multi-action score-3 example.	2 / 3
Completeness	It states what the skill does ("MCP server patterns for building integrations") and gives explicit when-guidance ("Triggers on: ..."), satisfying both halves and avoiding the missing-trigger cap of 2.	3 / 3
Trigger Term Quality	Explicit "Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool" gives good coverage of natural terms a user would say when needing this skill, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	MCP server development is a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	11 / 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: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 days 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.