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

71%

Does it follow best practices?

Impact

97%

2.15x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/mcp-patterns/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

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

The body delivers executable code and compact, well-organized reference tables that respect token budget. Its main weaknesses are the absence of an explicit validated workflow and references to bundle files that are not actually shipped.

Suggestions

Add an explicit numbered workflow with a validation checkpoint, e.g. build the server -> configure Claude Desktop -> validate with the MCP inspector before declaring done

Ship the referenced ./references/tool-patterns.md, resource-patterns.md, auth-patterns.md, state-patterns.md, and testing-patterns.md files, or remove the references if they are not bundled, so navigation is not broken

Drop the redundant opening line that repeats the frontmatter description to tighten conciseness

Dimension	Reasoning	Score
Conciseness	The body is largely lean code, compact tables, and links with no concept over-explanation, but the opening line repeats the frontmatter description and the 'With uv (Recommended)' label is mild padding that could be trimmed, so it is efficient rather than maximally lean.	4 / 5
Actionability	The inline Python server example is complete and copy-paste ready and the Claude Desktop JSON configs are executable, but the remaining patterns (validation, auth, state, testing) are deferred to references rather than shown inline, leaving minor coverage gaps in the body itself.	4 / 5
Workflow Clarity	There is an implicit build-then-configure flow (server code, project layout, Desktop config) plus a Common Issues troubleshooting table, but no explicit numbered sequence and no validation checkpoint such as running the MCP inspector before declaring the server ready.	3 / 5
Progressive Disclosure	The overview is well structured with clearly signaled one-level-deep references in the Quick Reference and Additional Resources tables, but the referenced ./references/*.md files do not exist in the bundle, so the disclosure is broken rather than navigable.	3 / 5
	Total	14 / 20 Passed

Description

78%Weight 40%Scale 1-5

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 cleanly answers both what and when with an explicit trigger clause and good domain keyword coverage. It is held back from the top band by a generic action verb and one overlap-prone trigger term.

Suggestions

Replace the generic 'building integrations' with concrete actions, e.g. 'register MCP tools, expose resources, and configure Claude Desktop'

Swap the generic 'tool handler' trigger for more specific phrasing like 'mcp tool handler' or 'register mcp tool' to reduce overlap with general tooling skills

Add a synonym such as 'claude integration' or 'stdio server' to broaden natural trigger coverage

Dimension	Reasoning	Score
Specificity	It names the domain clearly ('MCP server patterns') and one action ('building integrations with Claude Code') but does not enumerate concrete actions like register tools, expose resources, or handle auth, so it sits at the domain-plus-action anchor rather than comprehensive coverage.	3 / 5
Completeness	It explicitly states what the skill does ('MCP server patterns for building integrations with Claude Code') and when to use it via a concrete 'Triggers on:' clause, matching the anchor that requires both a clear what and explicit when with trigger phrases.	5 / 5
Trigger Term Quality	'Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool' gives good keyword coverage of terms developers naturally use, though it lacks synonyms like 'claude integration' or 'stdio server' that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	MCP servers are a clear niche with mostly distinct triggers, but the generic 'tool handler' term carries minor overlap risk with general tooling skills, keeping it just below the minimal-conflict anchor.	4 / 5
	Total	16 / 20 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
Path: data/skills-md/0xdarkmatter/claude-mods/mcp-patterns/SKILL.md
Commit: 2f57aec

Reviewed: about 22 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.