CtrlK
BlogDocsLog inGet started
Tessl Logo

create-mcp-app

This skill should be used when the user asks to "create an MCP App", "add a UI to an MCP tool", "build an interactive MCP View", "scaffold an MCP App", or needs guidance on MCP Apps SDK patterns, UI-resource registration, MCP App lifecycle, or host integration. Provides comprehensive guidance for building MCP Apps with interactive UIs.

72

Quality

87%

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

75%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 content is well-structured, executable, and uses progressive disclosure effectively by offloading detail to a cloned SDK repo via clear tables. Its main weakness is the absence of an explicit validation feedback loop in the build/test workflow.

Suggestions

Add an explicit validate→fix→retry loop after building (e.g., 'If basic-host fails to load the app, check the console errors, fix the registration/CSP config, and rebuild') to strengthen workflow_clarity.

Tighten the 'Core Concept: Tool + Resource' section to a one-line definition plus the data-flow line, trimming the explanatory framing.

For Advanced Patterns, add a single short inline code snippet for the highest-value pattern (e.g., polling or streaming input) rather than only pointing to docs/patterns.md.

DimensionReasoningScore

Conciseness

The body is dense and task-oriented with tables and code blocks rather than prose; a small amount of conceptual framing (the Tool+Resource core concept) is necessary context for a niche SDK but could be marginally tighter, so it sits just below the lean/efficient anchor.

4 / 5

Actionability

Provides concrete, executable guidance (git clone, npm install commands, handler-registration TypeScript, sendLog and testing commands); the Advanced Patterns section is pointer-only rather than code, leaving minor gaps.

4 / 5

Workflow Clarity

A clear sequence exists (clone repo → register tool/resource → register handlers before connect → build → test with basic-host) with checkpoints like 'Register ALL handlers BEFORE app.connect()' and a testing section, though an explicit validate→fix→retry feedback loop is only weakly present.

4 / 5

Progressive Disclosure

SKILL.md is an overview pointing to well-signaled, one-level-deep references (template/API tables mapping files in the cloned /tmp/mcp-ext-apps repo, docs/patterns.md); no local bundle files exist, and organization is good with minor gaps in signaling some reference paths.

4 / 5

Total

16

/

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.

The description is third-person, specific, and explicitly pairs trigger conditions with the skill's purpose, covering both 'what' and 'when' comprehensively. It is a strong, low-conflict description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('create an MCP App', 'add a UI to an MCP tool', 'build an interactive MCP View', 'scaffold an MCP App') plus specific SDK concerns (UI-resource registration, lifecycle, host integration), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers 'when' ('This skill should be used when the user asks to...') and 'what' ('Provides comprehensive guidance for building MCP Apps with interactive UIs') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say ('create an MCP App', 'scaffold an MCP App', 'add a UI to an MCP tool', 'build an interactive MCP View') with synonymous variations, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (MCP Apps with interactive UIs) with distinct, specific triggers that are unlikely to fire for unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
modelcontextprotocol/ext-apps
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.