Provides comprehensive best practices and guidelines for Next.js development, including app router usage and caching strategies.
Offers best practices for developing React hooks, building reusable components, and adhering to Vercel's recommended React patterns.
Delivers Vercel's recommended React best practices and guidelines for deploying and optimizing applications on the Vercel platform.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Skillroute MCP show me the code review guidelines"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Skillroute MCP is a Model Context Protocol (MCP) server that provides AI agents with access to a structured library of engineering skills, best practices, and playbooks.
This MCP server currently provides the following skills and best practice guidelines:
agent-development: Guidelines for developing AI agents.
agents-sdk: Documentation and rules for using the agents SDK.
ai-elements: Best practices for AI UI elements.
building-components: Standards for building reusable components.
code-reviewer: Guidelines and instructions for automated code review.
command-development: Rules for developing CLI commands and tools.
frontend-design: General frontend design rules and principles.
hook-development: Best practices for developing React hooks.
next-best-practices: Comprehensive Next.js best practices and app router guidelines.
next-cache-components: Guidelines for caching in Next.js.
skill-development: Instructions on how to write and structure skills.
vercel-react-best-practices: Vercel's recommended React best practices.
web-design-guidelines: General web design and aesthetic guidelines.
web-perf: Web performance optimization rules.
Related MCP server: Engineering Standards MCP Server
First, clone the project to your local machine:
git clone https://github.com/vaibhavgupta5/SkillRoute-MCP.git
cd SkillRoute-MCPInstall dependencies and compile the TypeScript code:
npm install
npm run buildThis will generate the compiled JavaScript in the dist/ directory.
For the MCP configuration, you will need the absolute path to the compiled index.js file.
For example, if you cloned the repository into C:\Projects\skillroutemcp, your path will be C:/Projects/skillroutemcp/dist/index.js (make sure to use forward slashes or escaped backslashes in JSON).
In the configurations below, replace [ABSOLUTE_PATH_TO_DIST_INDEX_JS] with your actual absolute path.
To use this MCP server in Claude Desktop, add the following to your claude_desktop_config.json file (typically located at %APPDATA%\\Claude\\claude_desktop_config.json on Windows or ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"skillroute": {
"command": "node",
"args": ["[ABSOLUTE_PATH_TO_DIST_INDEX_JS]"]
}
}
}Restart Claude Desktop after updating the configuration.
To use this MCP server in VS Code with extensions that support MCP, you can add it to their respective MCP settings configuration file:
{
"mcpServers": {
"skillroute": {
"command": "node",
"args": ["[ABSOLUTE_PATH_TO_DIST_INDEX_JS]"]
}
}
}To use this MCP server in Antigravity, you need to register it in your Antigravity MCP configuration.
Open your Antigravity Settings and edit the mcp.json file (or navigate to the MCP Server configuration section). Add the server using the following structure:
{
"mcpServers": {
"skillroute": {
"command": "node",
"args": ["[ABSOLUTE_PATH_TO_DIST_INDEX_JS]"]
}
}
}Alternatively, if adding via the Antigravity settings UI:
Command: node
Arguments: ["[ABSOLUTE_PATH_TO_DIST_INDEX_JS]"]
Reload the Antigravity workspace for the changes to take effect.
Fetches specific engineering guidelines, rules, and best practices for a given framework/technology.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Optional relative path to a specific rule or markdown file within the skill (e.g., 'rules/async-parallel.md' or 'file-conventions.md') | |
| technology | Yes | The name of the framework or skill folder (e.g., vercel-react-best-practices, next-best-practices) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. The description only states the basic fetch action and does not mention that the operation is read-only, idempotent, or any side effects. It lacks information about error handling, authentication needs, or what happens if the technology is not found.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that gets to the point. It is concise and front-loaded, but could include additional brief details without being overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description is too brief. It does not explain what the output looks like, how to use parameters effectively, or any contextual behavior. For a tool with two parameters, more guidance is needed for an agent to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds minimal extra meaning beyond the schema, such as mentioning 'specific rule or markdown file' for the path parameter, but this is already present in the schema description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'Fetches' and resource 'engineering guidelines, rules, and best practices' for a specific framework/technology. It also implicitly distinguishes from the sibling tool 'list_skills' by focusing on a single skill's content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this tool is for retrieving details of a specific skill, contrasting with 'list_skills' which would list available skills. However, it does not explicitly state when to use this tool instead of alternatives or provide any usage exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Lists all available engineering skills and playbooks.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It only states that the tool 'lists' skills and playbooks, implying a read-only operation, but does not disclose any behavioral traits such as permissions, side effects, or output format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that efficiently conveys the tool's purpose with no unnecessary words. It is front-loaded and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks completeness for a simple list tool: it does not describe the return value format or any other contextual details. Since there is no output schema, the description should explain what is returned, but it does not.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline score is 4 based on the rubric. The description, though minimal, does not need to add parameter meaning since the schema already covers all parameters (none).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the verb 'lists' and specifies the resource as 'all available engineering skills and playbooks,' clearly distinguishing this tool from the sibling 'get_framework_skill' which retrieves a single skill.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The sibling tool 'get_framework_skill' is not mentioned, and there is no explicit instruction about when to list vs fetch a single skill.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_framework_skilllist_skillsScored across 2 tools
The two tools have clearly distinct purposes: listing all available skills versus fetching details for a specific framework. There is no overlap or ambiguity an agent could encounter.
Both tool names follow a consistent verb_noun pattern (list_skills, get_framework_skill) using snake_case. The naming clearly indicates the action and target resource.
With only 2 tools, the set feels minimal but not inappropriate for a narrow domain like reference documentation. It is on the low end but earns its place.
The surface covers the basic operations for a skills reference: listing all available and retrieving one by framework. A gap might be the absence of search or filtering, but for a simple lookup tool it is largely complete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Your team's shipping standards, org map and delivery metrics, inside your coding agent.
One place to build, share, and govern the skills and tools your AI agents use at work.
Git-backed platform for skills, tools, and context for AI agents
Curated knowledge API for AI agents - skill packs, semantic search, validated patterns.
