CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-apps-builder

**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) - Debugging MCP server issues or errors - Reviewing MCP server code for quality, security, or performance - Answering questions about MCP development or mcp-use patterns - Making ANY changes to server.tool(), server.resource(), server.prompt(), or widgets This skill contains critical architecture decisions, security patterns, and common pitfalls. Always consult the relevant reference files BEFORE implementing MCP features.

60

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./generative_ui_agents/ai-mcp-app-builder/apps/mcp-use-server/.agent/skills/mcp-apps-builder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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.

A well-architected progressive-disclosure skill: the body is a lean navigation hub with concrete examples and a decision tree, deferring depth to a complete set of real reference files. Its main weakness is workflow clarity around destructive/production operations, which lack explicit validation checkpoints.

Suggestions

Add explicit validation checkpoints to the deployment and scaffolding workflows (e.g. 'Verify the build passes / inspector boots before considering the server ready'), with a validate→fix→retry loop.

Trim repeated emphatic framing ('MANDATORY', 'MUST', 'ALWAYS') where a single clear directive would convey the same instruction more concisely.

Include one concrete inline example of returning an error() vs throwing, since error handling is named as a common mistake but only illustrated abstractly.

DimensionReasoningScore

Conciseness

The body is mostly an efficient navigation guide with decision trees, a concise response-helpers table, and one minimal server example; it avoids re-teaching basic MCP concepts, though the bolded 'MANDATORY'/'MUST'/'ALWAYS' emphasis and repeated 'When:'/'Covers:' annotations add minor padding.

4 / 5

Actionability

Provides concrete executable guidance: the scaffolding command (`npx create-mcp-use-app`), a complete minimal server code sample, a typed widget-metadata code block, and a response-helpers table with concrete examples; minor gaps remain because most detailed implementation guidance is deferred to references rather than shown inline.

4 / 5

Workflow Clarity

The 'FIRST: New Project or Existing Project?' detection logic and the Decision Tree give a clear sequence, but workflows touching destructive/production operations (deployment, scaffolding over existing projects) lack explicit validation or verify-then-proceed checkpoints, and there are no validate→fix→retry feedback loops.

3 / 5

Progressive Disclosure

Excellent structure: the SKILL.md is a lean navigation guide pointing to clearly signaled, one-level-deep reference files, all 18 referenced paths resolve to real files, organized under Foundations / Authentication / Server / Widgets / Patterns with explicit 'When' and 'Covers' cues for easy discovery.

5 / 5

Total

16

/

20

Passed

Description

71%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, mandatory-styled description that clearly states both what the skill covers (mcp-use best practices, architecture, security patterns, pitfalls) and when to use it (six enumerated MCP server work scenarios). Trigger phrasing leans on framework jargon rather than natural user language, which slightly limits trigger-term quality.

Suggestions

Add natural-language user triggers a person would actually say, e.g. 'Use when the user asks to build, extend, or debug an MCP server' alongside the framework jargon.

Name deployment explicitly in the trigger list since it is a covered capability, to round out coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Creating new MCP servers', 'Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets)', 'Debugging MCP server issues', 'Reviewing MCP server code'), with only minor gaps in coverage such as deployment being implied rather than named.

4 / 5

Completeness

Clearly answers 'what' ('mcp-use framework best practices and patterns', 'critical architecture decisions, security patterns, and common pitfalls') and 'when' (the 'READ THIS FIRST before any MCP server work, including:' list of six triggers); the 'when' is explicit but framed as mandatory rather than as natural user trigger phrases, so it stops just short of a 5.

4 / 5

Trigger Term Quality

Contains relevant terms like 'MCP server', 'tools, resources, prompts, widgets', and 'mcp-use patterns', but lacks natural synonyms a user might actually say (e.g. 'build an MCP server', 'add a tool to my MCP server') and file extensions are absent.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (mcp-use framework / MCP servers) with distinct triggers tied to server.tool(), server.resource(), server.prompt(), and widgets, making conflict with unrelated skills minimal.

5 / 5

Total

16

/

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

relative_links

Relative link issues: 19 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 19 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
Shubhamsaboo/awesome-llm-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.