Skip to main content
Glama
Bbeierle12

Skills Manager MCP Server

by Bbeierle12
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

Skills Manager

A visual web interface for managing Claude MCP Skills with Claude Code CLI integration.

Project Overview

This project provides a browser-based UI for managing skills in an MCP (Model Context Protocol) server. Skills are markdown-based instruction sets that Claude can load on-demand to gain specialized knowledge.

Related MCP server: agent-skill-loader

Architecture

┌─────────────────────────────────────────────────────────────────┐
│                        Skills Manager                           │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│   ┌──────────────────┐         ┌──────────────────────────┐    │
│   │  Claude Desktop  │         │     Browser UI           │    │
│   │  (MCP Client)    │         │  skills-manager.html     │    │
│   └────────┬─────────┘         └────────────┬─────────────┘    │
│            │                                │                   │
│            │ stdio/MCP                      │ HTTP REST         │
│            │                                │                   │
│   ┌────────▼─────────┐         ┌────────────▼─────────────┐    │
│   │   server.py      │         │  skills_manager_api.py   │    │
│   │   (MCP Server)   │         │  (Flask API :5050)       │    │
│   └────────┬─────────┘         └────────────┬─────────────┘    │
│            │                                │                   │
│            └────────────┬───────────────────┘                   │
│                         │                                       │
│                         ▼                                       │
│                  ┌──────────────┐                               │
│                  │   skills/    │                               │
│                  │  (folder)    │                               │
│                  └──────────────┘                               │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

File Structure

skills-mcp/
├── server.py                 # MCP server (FastMCP) - connects to Claude Desktop
├── skills_manager_api.py     # Flask HTTP API server (port 5050)
├── skills_manager_app.py     # Standalone all-in-one app (for .exe build)
├── skills-manager.html       # Web UI (single-file, Tailwind + Lucide)
├── requirements.txt          # Python dependencies
├── build.bat                 # Windows build script for .exe
├── skills/                   # Skills directory
│   ├── my-skill/
│   │   ├── SKILL.md          # Main skill content
│   │   ├── _meta.json        # Metadata (tags, description)
│   │   ├── scripts/          # Optional helper scripts
│   │   └── references/       # Optional reference docs
│   └── another-skill/
│       └── ...
└── dist/                     # Built executable + assets
    ├── SkillsManager.exe
    ├── skills-manager.html
    └── README.md

Setup

Prerequisites

  • Python 3.10+

  • Node.js (optional, for Claude Code CLI)

  • Claude Code CLI (optional, for AI features)

Installation

cd skills-mcp
pip install -r requirements.txt

Running the API Server

python skills_manager_api.py

Opens at: http://localhost:5050

Running the MCP Server (for Claude Desktop)

The MCP server runs automatically when Claude Desktop starts (configured in claude_desktop_config.json).

Manual test:

python server.py

Daily Skills Catalogue Audit

The repo ships an automated review system that grades every skill daily and surfaces improvement opportunities. See reports/ for the latest output.

What it does

  • Pass 1 (deterministic, every run): structural defects — missing files, description drift between _meta.json and SKILL.md frontmatter, broken references, unknown depends_on targets, oversized SKILL.md files, thin asset-less skills, duplicate sub-skill triggers, stale reviews.

  • Pass 2 (one skill per run): content audit of the skill whose last_reviewed_at is oldest. Runs a deterministic rubric (description distinctness vs. tag-cluster siblings, library version mentions, asset richness, cross-references), proposes a relevance_tier (A/B/C/D), and optionally calls the Claude CLI for an LLM-assisted rubric.

  • Pass 3 (weekly): catalogue-level review — sibling description overlap, router necessity, tag-cluster drift vs. last week's snapshot, source distribution.

Running locally

# Add the audit metadata fields once (idempotent):
python scripts/backfill_audit_meta.py

# Daily run (writes reports/YYYY-MM-DD.md):
python scripts/run_daily_audit.py

# With weekly Pass 3 + the LLM rubric:
python scripts/run_daily_audit.py --weekly --use-llm

The GitHub Actions workflow .github/workflows/skills-audit.yml runs the daily audit at 06:30 UTC and commits the resulting report. The Monday run also performs Pass 3.

Metadata fields added to _meta.json

Field

Type

Meaning

last_reviewed_at

ISO date or null

When Pass 2 last audited this skill

review_score

int 0–100 or null

Composite of distinctness + asset richness + freshness + cross-references

relevance_tier

"A" / "B" / "C" / "D" / null

A = irreplaceable, B = trim & keep, C = redundant with base-model output, D = obsolete

The Skills Manager UI shows these as a filter dropdown and a per-card badge.

Development

Key Files to Edit

File

Purpose

skills-manager.html

Frontend UI (vanilla JS, Tailwind CSS, Lucide icons)

skills_manager_api.py

Backend REST API (Flask)

server.py

MCP server for Claude Desktop integration

skills_manager_app.py

Standalone app (combines API + launcher for .exe)

API Endpoints

Method

Endpoint

Description

GET

/api/skills

List all skills

GET

/api/skills/<name>

Get skill details

POST

/api/skills

Create new skill

PUT

/api/skills/<name>

Update skill

DELETE

/api/skills/<name>

Delete skill

POST

/api/import/folder

Import skill from folder path

POST

/api/import/json

Import files via JSON

GET

/api/browse?path=

Browse filesystem

GET

/api/claude/status

Check Claude CLI availability

POST

/api/claude/run

Run Claude with prompt

POST

/api/claude/generate-skill

Generate skill with AI

Frontend Structure

The UI is a single HTML file with embedded CSS and JavaScript:

  • Modals: Import, Folder Browser, File Upload, Generate, View, Claude Console

  • State: skills[], selectedFolderPath, browsePathCache{}, etc.

  • Key Functions:

    • browsePath(path) - Navigate filesystem

    • importSelectedFolder() - Copy folder to skills/

    • uploadFiles() - Upload files as new skill

    • generateSkill() - AI skill generation

    • runConsoleCommand() - Execute Claude prompts

Building the Executable

# Windows
build.bat

# Or manually
pip install pyinstaller
python -m PyInstaller --onefile --name "SkillsManager" --console ^
    --add-data "skills-manager.html;." skills_manager_app.py

Output: dist/SkillsManager.exe

Skill Format

SKILL.md Structure

---
name: skill-name
description: When Claude should use this skill
---

# Skill Name

## Overview
What this skill helps with.

## When to Use
- Trigger condition 1
- Trigger condition 2

## Quick Start
\`\`\`code
Example usage
\`\`\`

## Best Practices
- Practice 1
- Practice 2

## Examples
Practical examples here.

_meta.json Structure

{
  "name": "skill-name",
  "description": "One-line description",
  "tags": ["tag1", "tag2"],
  "sub_skills": [],
  "source": "imported"
}

Claude Desktop Configuration

Location: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "skills": {
      "command": "python",
      "args": ["C:/Users/<YOUR_USERNAME>/skills-mcp/server.py"]
    }
  }
}

MCP Tools (for Claude)

The MCP server exposes these tools to Claude:

Tool

Description

list_skills()

List all available skills

get_skill(name)

Load a skill's SKILL.md content

search_skills(query)

Search skills by metadata

search_content(query)

Full-text search across all skills

get_skills_batch([...])

Load multiple skills at once

reload_index()

Refresh skill index

validate_skills()

Check skill integrity

Known Issues / TODO

  • Folder browser doesn't show drive letters on initial load (starts at root drives)

  • No confirmation before overwriting existing skills

  • File upload doesn't preserve folder structure from drag-drop

  • Claude Console output doesn't syntax highlight

  • No skill versioning or backup

Tech Stack

  • Backend: Python 3.11, Flask, Flask-CORS, FastMCP

  • Frontend: Vanilla JS, Tailwind CSS (CDN), Lucide Icons (CDN)

  • Build: PyInstaller

  • Protocol: MCP (Model Context Protocol)

This server cannot be installed

A
license - permissive license
-
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Bbeierle12/Skill-MCP-Claude'

If you have feedback or need assistance with the MCP directory API, please join our Discord server