Back to Skills

Mcp Management

Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, capability discovery, tool filtering, programmatic execution, or encountering context bloat, server configuration, tool execution errors.

By secondsky
21030Updated 5 days agoTypeScriptMIT

Skill Content

# MCP Management

Skill for managing and interacting with Model Context Protocol (MCP) servers.

## Overview

MCP is an open protocol enabling AI agents to connect to external tools and data sources. This skill provides scripts and utilities to discover, analyze, and execute MCP capabilities from configured servers without polluting the main context window.

**Key Benefits**:
- Progressive disclosure of MCP capabilities (load only what's needed)
- Intelligent tool/prompt/resource selection based on task requirements
- Multi-server management from single config file
- Context-efficient: subagents handle MCP discovery and execution
- Persistent tool catalog: automatically saves discovered tools to JSON for fast reference

## When to Use This Skill

Use this skill when:
1. **Discovering MCP Capabilities**: Need to list available tools/prompts/resources from configured servers
2. **Task-Based Tool Selection**: Analyzing which MCP tools are relevant for a specific task
3. **Executing MCP Tools**: Calling MCP tools programmatically with proper parameter handling
4. **MCP Integration**: Building or debugging MCP client implementations
5. **Context Management**: Avoiding context pollution by delegating MCP operations to subagents

## Core Capabilities

### 1. Configuration Management

MCP servers configured in `.claude/.mcp.json`.

**Gemini CLI Integration** (recommended): Create symlink to `.gemini/settings.json`:
```bash
mkdir -p .gemini && ln -sf .claude/.mcp.json .gemini/settings.json
```

### 2. Capability Discovery

```bash
# Preferred: Using bun (faster)
bunx tsx scripts/cli.ts list-tools  # Saves to assets/tools.json
bunx tsx scripts/cli.ts list-prompts
bunx tsx scripts/cli.ts list-resources

# Alternative: Using bunx
bunx tsx scripts/cli.ts list-tools
bunx tsx scripts/cli.ts list-prompts
bunx tsx scripts/cli.ts list-resources
```

Aggregates capabilities from multiple servers with server identification.

### 3. Intelligent Tool Analysis

LLM analyzes `assets/tools.json` directly - better than keyword matching algorithms.

### 4. Tool Execution

**Primary: Gemini CLI** (if available)
```bash
gemini -y -m gemini-2.5-flash -p "Take a screenshot of https://example.com"
```

**Secondary: Direct Scripts**
```bash
# Preferred: Using bun
bunx tsx scripts/cli.ts call-tool memory create_entities '{"entities":[...]}'

# Alternative: Using bunx
bunx tsx scripts/cli.ts call-tool memory create_entities '{"entities":[...]}'
```

**Fallback: mcp-manager Subagent**

## Implementation Patterns

### Pattern 1: Gemini CLI Auto-Execution (Primary)

Use Gemini CLI for automatic tool discovery and execution.

**Quick Example**:
```bash
gemini -y -m gemini-2.5-flash -p "Take a screenshot of https://example.com"
```

**Benefits**: Automatic tool discovery, natural language execution, faster than subagent orchestration.

### Pattern 2: Subagent-Based Execution (Fallback)

Use `mcp-manager` agent when Gemini CLI unavailable. Subagent discovers tools, selects relevant ones, executes tasks, reports back.

**Benefit**: Main context stays clean, only relevant tool definitions loaded when needed.

### Pattern 3: LLM-Driven Tool Selection

LLM reads `assets/tools.json`, intelligently selects relevant tools using context understanding, synonyms, and intent recognition.

### Pattern 4: Multi-Server Orchestration

Coordinate tools across multiple servers. Each tool knows its source server for proper routing.

## Quick Start

**Method 1: Gemini CLI** (recommended)
```bash
bun install -g gemini-cli  # or: bun add -g gemini-cli
mkdir -p .gemini && ln -sf .claude/.mcp.json .gemini/settings.json
gemini -y -m gemini-2.5-flash -p "Take a screenshot of https://example.com"
```

**Method 2: Scripts**
```bash
cd .claude/skills/mcp-management/scripts
bun install  # or: bun install
bunx tsx cli.ts list-tools  # Saves to assets/tools.json
bunx tsx cli.ts call-tool memory create_entities '{"entities":[...]}'
```

**Method 3: mcp-manager Subagent**

Dispatch subagent to handle MCP operations, keeping main context clean.

## Secure Installation

When installing MCP server packages, follow supply chain security best practices:

- **Block post-install scripts** — `npm config set ignore-scripts true` (or Bun: disabled by default)
- **Cooldown period** — Wait 7 days for new package versions to be vetted by the community
- **Audit before installing** — Run `socket package score npm <pkg>` or use `socket npm install <pkg>` to check packages

Load the `dependency-upgrade` skill for full security configuration including Socket CLI integration, cooldown setup, lockfile validation, and CI enforcement.

## Integration Strategy

### Execution Priority

1. **Gemini CLI** (Primary): Fast, automatic, intelligent tool selection
   - Check: `command -v gemini`
   - Execute: `gemini -y -m gemini-2.5-flash -p "<task>"`
   - Best for: All tasks when available

2. **Direct CLI Scripts** (Secondary): Manual tool specification
   - Use when: Need specific tool/server control
   - Execute: `bunx tsx scripts/cli.ts call-tool <server> <tool> <args>`

3. **mcp-manager Subagent** (Fallback): Context-efficient delegation
   - Use when: Gemini unavailable or failed
   - Keeps main context clean

### Integration with Agents

The `mcp-manager` agent uses this skill to:
- Check Gemini CLI availability first
- Execute via `gemini` command if available
- Fallback to direct script execution
- Discover MCP capabilities without loading into main context
- Report results back to main agent

This keeps main agent context clean and enables efficient MCP integration.

How to use

  1. Copy the skill content above
  2. Create a .claude/skills/claude-skills-mcp-management directory in your project (or ~/.claude/skills/claude-skills-mcp-management to use it in every project)
  3. Save the content as .claude/skills/claude-skills-mcp-management/SKILL.md
  4. Claude Code loads it automatically when the task matches, or run /claude-skills-mcp-management to invoke it directly

Claude Code Skills Collection

142 production-ready skills for Claude Code CLI

Version 3.6.3 | Last Updated: 2026-08-06

<div align="center">

šŸ”Œ Platform / Harness Support

These plugins ship as Claude Code marketplace plugins (.claude-plugin/ manifests) and Codex CLI plugins (.codex-plugin/ manifests). Other harnesses consume the same skills via skills.sh — the cross-harness bridge.

HarnessMarketplace supportHow to install
Claude Codeāœ… Native (federated)/plugin marketplace add secondsky/claude-skills, then /plugin install <name>@claude-skills
ZCodeāœ… Native (reads .claude-plugin/ manifests)Add this repo as a marketplace in the ZCode GUI
Codex CLIāœ… Native (federated)codex plugin marketplace add secondsky/claude-skills, then /plugins in the Codex TUI
Cursorāš ļø Adaptation neededCursor has an official marketplace, but expects .cursor-plugin/plugin.json (UI "Add to Cursor") this repo does not generate yet. Use skills.sh.
opencodeāŒ No marketplacenpm plugins only (opencode.json plugin[]). Use skills.sh or vendor manually.
Gemini CLIāŒ No marketplacegemini extensions install <url> only. Use skills.sh or vendor manually.
</div>

A curated collection of battle-tested skills for building modern web applications with Cloudflare, AI integrations, React, Tailwind, and more.


Quick Start

Marketplace Installation (Recommended)

# Add the marketplace
/plugin marketplace add https://github.com/secondsky/claude-skills

# Install individual skills as needed
/plugin install cloudflare-d1@claude-skills
/plugin install tailwind-v4-shadcn@claude-skills
/plugin install gemini-cli@claude-skills

See MARKETPLACE.md for complete catalog of all 142 skills.

Codex CLI Installation

This repo generates .codex-plugin/ manifests and a .agents/plugins/marketplace.json for all 142 plugins, so Codex CLI can install them natively:

# Add the marketplace (from GitHub)
codex plugin marketplace add secondsky/claude-skills

# Browse and install plugins in the Codex TUI
#   /plugins          # opens the plugin browser
#   Space             # enable/disable a plugin

Skills are auto-discovered from each plugin's skills/ directory — the same SKILL.md files Claude Code uses. Claude-specific slash commands and subagents are not carried into Codex (use Codex's /import command for that).


Installing with skills.sh

skills.sh is an open agent-skills registry and npx skills CLI (maintained by Vercel) that auto-detects your coding agent — Claude Code, Cursor, Codex, Copilot, Cline, opencode, and 70+ others — and installs each skill into the correct directory for that harness. It is the universal cross-harness path for harnesses without a marketplace (opencode, Gemini CLI) or where this repo's manifest format isn't generated yet (Cursor).

# Install one skill (auto-detects your agent)
npx skills add secondsky/claude-skills --skill cloudflare-d1

# Install several specific skills
npx skills add secondsky/claude-skills --skill cloudflare-d1 --skill tailwind-v4-shadcn

# Try a skill once without installing (pipes its prompt to your agent)
npx skills use secondsky/claude-skills@cloudflare-d1 | claude

# Target a specific agent explicitly
npx skills add secondsky/claude-skills --skill cloudflare-d1 --agent codex

# List what's installed, search, update, remove
npx skills ls -g
npx skills find cloudflare
npx skills update cloudflare-d1
npx skills remove cloudflare-d1

Bulk install note: npx skills add secondsky/claude-skills --all installs every discovered skill at once, but discovery walks skills.sh's standard container directories (skills/, .claude/skills/, …). This repo nests skills under plugins/<name>/skills/<skill>/, so --all may not pick up everything in one pass — install the skills you need by name with --skill, or run npx skills add secondsky/claude-skills -l to list what it finds.

Security scanning caveat

skills.sh runs every published skill through three scanners (Gen Agent Trust Hub, Socket, Snyk) plus an LLM-based meta-analyzer, and publishes the results at skills.sh/audits. The LLM analysis stage has been publicly shown (Trail of Bits, June 2026) to both miss genuinely malicious skills and flag unfamiliar version pins (e.g. newest dependency versions) as suspicious false positives. Treat skills.sh warnings as advisory, not authoritative — and verify against this repo's own version pins before acting on a warning.


Repository Structure

This repository contains 142 production-tested skills for Claude Code, each focused on a specific technology or capability.

Individual Skills: Each skill is a standalone unit with:

  • SKILL.md - Core knowledge and guidance
  • Templates - Working code examples
  • References - Extended documentation
  • Scripts - Helper utilities

Installation Options:

  1. Marketplace (recommended) - Install individual skills via /plugin install <name>@claude-skills
  2. Cross-harness - Install into any supported agent with npx skills add secondsky/claude-skills --skill <name> (see Installing with skills.sh)

Available Skills (142 Individual Skills)

Each skill is individually installable. Install only the skills you need.

Full Catalog: See MARKETPLACE.md for detailed listings.

Categories

CategorySkillsExamples
tooling24turborepo, plan-interview, code-review
frontend26nuxt-v4, nuxt-v5, tailwind-v4-shadcn, tanstack-query, nuxt-studio, maz-ui, threejs
cloudflare21cloudflare-d1, cloudflare-workers-ai, cloudflare-agents
api16api-design-principles, graphql-implementation
ai7gemini-cli, ml-model-training, tanstack-ai
web10hono-routing, firecrawl-scraper, web-performance
security6csrf-protection, xss-prevention, cybersecurity
mobile5react-native-app, react-native-skills
woocommerce4woocommerce-backend-dev
testing4vitest-testing, playwright-testing
design4design-review, design-system-creation
auth4better-auth
architecture3microservices-patterns, architecture-patterns
data2recommendation-engine, recommendation-system
cms2hugo, wordpress-plugin-core
database1drizzle-orm-d1
seo2seo-optimizer, seo-keyword-cluster-builder
documentation1technical-specification

How It Works

Auto-Discovery

Claude Code automatically checks ~/.claude/skills/ for relevant skills before planning tasks:

User: "Set up a Cloudflare Worker with D1 database"
           ↓
Claude: [Checks skills automatically]
           ↓
Claude: "Found cloudflare-d1 skills.
         These prevent 12 documented errors. Use them?"
           ↓
User: "Yes"
           ↓
Result: Production-ready setup, zero errors, ~65% token savings

Note: Due to token limits, not all skills may be visible at once. See āš ļø Important: Token Limits below.

Skill Structure

Each plugin is a directory under plugins/<plugin-name>/ containing one or more skills:

plugins/[plugin-name]/
ā”œā”€ā”€ .claude-plugin/
│   └── plugin.json       # Plugin manifest (marketplace metadata)
ā”œā”€ā”€ README.md
ā”œā”€ā”€ skills/
│   └── [skill-name]/
│       ā”œā”€ā”€ SKILL.md          # Core knowledge and guidance
│       ā”œā”€ā”€ templates/        # Ready-to-copy templates
│       ā”œā”€ā”€ scripts/          # Helper utilities
│       └── references/       # Extended documentation
└── (optional) agents/, commands/, hooks/

Recent Additions

July 2026

Offensive Security (new category):

  • cybersecurity — Unified OSS-only cybersecurity skill with progressive disclosure. Fuses 7 community skills (mukul975 business-logic/XSS/host-header/forced-browsing/open-redirect, rysweet/amplihack cybersecurity-analyst, Aradotso security-detections-mcp) ported to fully open-source tooling (OWASP ZAP, Dalfox, ffuf, Nuclei, mitmproxy, interact.sh, Semgrep, Sigma). Covers threat modeling (STRIDE/PASTA/VAST, MITRE ATT&CK), web-vuln testing, SAST, code audit, AI/LLM-app security, and detection engineering. Live-target testing is gated behind an authorization disclaimer; static analysis, code review, and threat modeling are always available. Cross-references the 5 existing defensive security plugins (csrf-protection, xss-prevention, vulnerability-scanning, security-headers-configuration, defense-in-depth-validation) for remediation. Integrates 20 Aradotso dev-security skills across 5 grouped reference docs.

May 2026

Supply Chain Security (cross-cutting):

  • dependency-upgrade expanded with Socket CLI integration — proactive malicious package detection, typosquatting alerts, and CI/CD security gates. New 418-line reference guide, 2 GitHub Actions templates, and expanded supply chain security comparison (3 tools)
  • 31 skills now include "Secure Installation" guidance — contextually-tailored security sections across all high-risk skill categories (scaffolding, MCP/agent SDKs, multi-provider installs, Docker, CI/CD). Covers 8 Bun skills, 5 Nuxt skills, 6 Cloudflare skills, 4 AI/agent skills, and 8 frontend/tooling skills
  • Supply chain security is now a first-class cross-cutting concern woven into the skill collection — not a standalone topic

February - April 2026

Full-Stack Frameworks:

  • nuxt-v5 (v1.0.0) - Full Nuxt 5 support with 4 skills (core, data, server, production), 3 diagnostic agents, and interactive setup wizard
  • threejs (v1.0.0) - 3D web graphics: scenes, geometries, shaders, animations, post-processing

Infrastructure:

  • JSON schema validation - Automated plugin.json validation with CI support
  • GitHub issue templates - Skill-specific issue templates for bug reports, feature requests, and submissions

Plugin Enhancements:

  • mutation-testing - Added Bun native runner support
  • dependency-upgrade - Added supply chain security content

December 2025 - January 2026

Frontend Expansion:

  • nuxt-studio (v1.0.0) - Visual CMS for Nuxt Content with live preview, OAuth auth, and R2 storage integration
  • maz-ui (v1.0.0) - 50+ Vue/Nuxt components with theming, i18n, form generation, and 14 composables

Developer Workflow:

  • plan-interview (v2.0.0) - Adaptive interview-driven spec generation with autonomous quality review
  • turborepo (v2.8.0) - Updated to official Vercel skill with enhanced monorepo build optimization

Mobile Development:

  • react-native-skills (v1.0.0) - React Native & Expo best practices with performance optimization patterns

Enhanced Authentication:

  • better-auth (v2.2.0) - Expanded to 18 framework integrations with 30+ authentication plugins

āš ļø Important: Token Limits

Skill Visibility Constraint

Claude Code has a 15,000 character limit for the total size of skill descriptions in the system prompt. This limit also applies to commands and agents.

What this means:

  • Not all 142 skills may be visible in Claude's context at once
  • Skills are loaded based on relevance and available token budget
  • You can verify how many skills Claude currently sees by asking: "How many skills do you see in your system prompt?"

Checking Visible Skills

To verify which skills are currently loaded:

# Ask Claude Code directly
"Check what skills/plugins you see in your system prompt"

Claude will report something like: "85 of 142 skills visible due to token limits"

Workaround: Increase Token Budget

You can double the headroom for s

…

View source on GitHub