CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-server-patterns

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API. Use when building or debugging an MCP server — tools, resources, prompts, validation, or transport choice.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

61%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 is well-structured and domain-appropriate, but its core guidance stops short of executable tool/resource registration code and lacks an explicit build-and-verify workflow. Tightening the repeated documentation caveats would improve token efficiency.

Suggestions

Add one complete, copy-pasteable example of registering a tool with a Zod input schema and handler, so the central action is executable rather than described as prose alternatives.

Provide a short sequenced workflow with a validation checkpoint (e.g., install → construct server → register tool/resource → choose transport → connect → verify via a test client).

Consolidate the repeated 'check Context7 or official MCP docs' disclaimers into a single note near the top instead of restating it in every section.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence, but the 'check Context7 or official MCP docs' caveat is repeated verbatim five+ times and the SDK-version hedging could be consolidated into one note.

4 / 5

Actionability

Install and McpServer construction are executable, but the central action — registering tools/resources/prompts — is described in prose alternatives ('server.tool(name, description, schema, handler)' vs 'server.tool({...}, handler)' vs 'registerTool()') with no complete, copy-pasteable registration example.

3 / 5

Workflow Clarity

Sections imply a rough order (concepts → stdio → HTTP → examples → best practices) but there is no explicit sequenced build workflow and no validation/testing checkpoint to confirm a server registers and connects correctly.

3 / 5

Progressive Disclosure

Well-organized into clearly signaled sections with one-level external references (capability-surface-selection.md, MCP docs); no bundle files exist to split further, and nothing is nested or buried.

4 / 5

Total

14

/

20

Passed

Description

100%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.

A strong, well-formed description that concretely states what the skill does and gives explicit, natural trigger phrases for when to use it. Voice is correctly third person and it stays concise without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'Build MCP servers', 'tools, resources, prompts, Zod validation, stdio vs Streamable HTTP' — giving comprehensive coverage of the MCP server domain rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both what ('Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP') and when ('Use when building or debugging an MCP server — ...'), matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say — 'building or debugging an MCP server', 'tools, resources, prompts, validation, or transport choice' — with good synonym coverage across the domain.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (MCP server construction with the Node/TypeScript SDK) with distinct triggers, making overlap with unrelated skills minimal.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
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.