mcpbeat Sign in

Claude Skills

The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.

Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.

61 947
unique skills
out of 79 600 files found on GitHub
17 653
are copies
same content, someone else's repository
1 739
tokens, median
what a typical skill costs you in context
7 890
name collisions
two skills with one name cannot sit side by side

42 421–42 480 of 61 947

page 708 of 1 033
Greedy Bipartite Matching
by cxcscmu

Implement greedy bipartite matching for pairing cluster centroids with expert annotations.

897 tokens
Parallel Grid Search
by cxcscmu

Parallelize hyperparameter grid search using joblib for efficient multi-core execution.

881 tokens
Pareto Frontier Analysis
by cxcscmu

Identify Pareto-optimal solutions from multi-objective optimization results.

745 tokens
Cvss Score Extraction
by cxcscmu

Extract and handle CVSS scores from multiple vulnerability data sources (NVD, GHSA, RedHat) with proper fallback priority.

837 tokens
Package Lock Parsing
by cxcscmu

Parse and extract package information from npm package-lock.json files to identify dependencies and their installed versions.

476 tokens
Security Audit CSV Reporting
by cxcscmu

Generate structured CSV security audit reports from vulnerability data with proper filtering, formatting, and field mapping.

967 tokens
Trivy Vulnerability Scanning
by cxcscmu

Use Trivy vulnerability scanner in offline mode to detect CVEs in npm dependencies and generate structured JSON reports.

750 tokens
Geopandas Projections
by cxcscmu

Use GeoPandas with coordinate projections to perform accurate spatial calculations and transformations.

749 tokens
Plate Tectonics Geospatial
by cxcscmu

Analyze plate tectonics data using GeoPandas, identify points within plates, and calculate distances to boundaries.

1k tokens
Usgs Earthquake Analysis
by cxcscmu

Load, parse, and process USGS earthquake data in GeoJSON or JSON formats.

879 tokens
Enterprise Data Retrieval
by cxcscmu

Retrieve and aggregate information across multiple enterprise data sources

1k tokens
JSON Data Extraction
by cxcscmu

Extract, parse, and query JSON data from large enterprise files efficiently

947 tokens
JSON Result Formatting
by cxcscmu

Format query results to JSON with proper structure and token tracking

1k tokens
Fuzzy Fund Search
by cxcscmu

Fuzzy matching techniques for finding hedge funds by name when exact names are unknown

2k tokens
Portfolio Analysis
by cxcscmu

Analyzing fund portfolios including AUM extraction, holdings counts, and portfolio composition

2k tokens
Sec13f Data Format
by cxcscmu

Understanding SEC 13-F filing data structure, TSV format, and key tables for hedge fund analysis

1k tokens
Druid Javascript Security
by cxcscmu

Securing Apache Druid's JavaScript execution engine against code injection and security bypass attacks.

711 tokens
Git Patch Workflow
by cxcscmu

Creating, managing, and applying unified diff patches with Git for source code modifications.

578 tokens
Jackson Deserialization Validation
by cxcscmu

Securing Jackson JSON deserialization by validating input before processing and preventing unknown properties.

1k tokens
Maven Druid Build
by cxcscmu

Building Apache Druid with Maven, managing memory constraints, and skipping verification checks.

702 tokens
Github CLI Queries
by cxcscmu

Query GitHub repositories for PRs and issues using gh CLI with date filtering and structured output.

661 tokens
Github Metrics Processing
by cxcscmu

Process GitHub API data to calculate PR/issue metrics including merge time averages, author rankings, and bug categorization.

1k tokens
JSON Report Generation
by cxcscmu

Generate and write structured JSON reports with proper formatting and validation.

1k tokens
Fixed Tensor Testing
by cxcscmu

Test ML functions with fixed input tensors for reproducibility.

1k tokens
Nlp Project Setup
by cxcscmu

Set up Python environment for NLP and preference optimization projects.

678 tokens
Pytorch Loss Implementation
by cxcscmu

Implement loss functions in PyTorch with proper tensor operations.

573 tokens
Simpo Loss Function
by cxcscmu

Implement SimPO loss with length-normalized rewards and target margin.

684 tokens
Python DOCX
by cxcscmu

Programmatically read, modify, and create Word documents (.docx) with python-docx library

1k tokens
Template Processing
by cxcscmu

Process templates with placeholder substitution and conditional sections

2k tokens
Content Classification
by cxcscmu

Classify documents by subject using keyword matching and text analysis

861 tokens
Document Organization Pipeline
by cxcscmu

End-to-end pipeline for extracting, classifying, and organizing documents by subject

2k tokens
DOCX PPTX Extraction
by cxcscmu

Extract text from DOCX and PPTX files for content analysis

502 tokens
File Organization
by cxcscmu

Organize files into target directories based on classification results

891 tokens
PDF Text Extraction
by cxcscmu

Extract text content from PDF files for analysis and classification

401 tokens
Scala Adt Enums
by cxcscmu

Translating Python Enums and Protocols to Scala sealed traits and algebraic data types

2k tokens
Scala Circe JSON
by cxcscmu

Working with Circe JSON library in Scala for type-safe JSON processing

2k tokens
Scala Collections Fp
by cxcscmu

Scala collections, iterators, and functional programming patterns for Python developers

2k tokens
Scala Generics
by cxcscmu

Translating Python generic types, variance, and type bounds to Scala 2.13

905 tokens
Scala Option Either
by cxcscmu

Translating Python's None/Optional to Scala's Option, Either, and Try types

2k tokens
Calendar Scheduling Logic
by cxcscmu

Find available time slots in a calendar and schedule meetings while respecting constraints

2k tokens
Datetime Formatting
by cxcscmu

Format dates and times according to specific requirements for meeting confirmations

1k tokens
Meeting Request Parsing
by cxcscmu

Parse meeting request emails from JSON format and extract duration and time constraints

1k tokens
PDF Calendar Parsing
by cxcscmu

Extract calendar events, blocks, and time slots from PDF calendar files using pdfplumber

1k tokens
CSV Data Handling
by cxcscmu

Loading and parsing CSV files with D3.js, data transformation, and handling missing values

1k tokens
D3 Force Simulation
by cxcscmu

D3.js force simulation for creating interactive bubble charts with clustering, collision detection, and physics-based positioning

1k tokens
D3 Fundamentals
by cxcscmu

Essential D3.js v6 concepts including selections, scales, SVG basics, and data binding for building interactive visualizations

774 tokens
D3 Interactive Charts
by cxcscmu

D3.js techniques for tooltips, hover effects, click handlers, and cross-filtering between visualizations

1k tokens
Data Matching
by cxcscmu

Matching observation data to simulation output with exact datetime and depth binning

1k tokens
Fortran Namelist
by cxcscmu

Reading and modifying Fortran namelist configuration files for scientific models

1k tokens
Glm Simulation
by cxcscmu

Running the General Lake Model (GLM) with configuration files and parameter calibration

752 tokens
Model Calibration
by cxcscmu

Calculating RMSE metrics and parameter calibration for lake model validation

1k tokens
Netcdf Processing
by cxcscmu

Reading, processing, and analyzing NetCDF output from lake simulation models

810 tokens
Budget Management
by cxcscmu

Track and manage travel budget across accommodations, meals, and activities

1k tokens
Data Filtering
by cxcscmu

Filter accommodations, restaurants, and attractions by travel requirements

1k tokens
Data Loading
by cxcscmu

Load and parse CSV/TXT files from travel database for itinerary planning

841 tokens
Route Planning
by cxcscmu

Plan multi-city road trip routes using distance matrices and constraints

950 tokens
Ffmpeg Keyframe Extraction
by cxcscmu

Extract key frames (I-frames) from video files using FFmpeg to identify scene changes and important moments.

628 tokens
Opencv Template Matching
by cxcscmu

Use OpenCV for image processing, grayscale conversion, and template matching to detect objects in images.

1k tokens
Python CSV Generation
by cxcscmu

Generate structured CSV files from Python data using the csv module for tabular data export.

826 tokens
Excel Lookup Functions
by cxcscmu

Master Excel lookup functions (VLOOKUP, HLOOKUP, INDEX/MATCH, XLOOKUP) for single and multiple criteria.

913 tokens

Claude Skills — questions

Answers built from the skills we actually parsed.

What is a Claude Skill?
A folder with a SKILL.md file: instructions that teach an agent to do one thing well, optionally with scripts and reference files alongside. The format is open and called Agent Skills — Claude Code, Codex and other agents read the same files. It is not a program you run; it is knowledge the agent loads when the task calls for it.
How is a skill different from an MCP server?
A server gives the agent new abilities — it connects to something and exposes tools. A skill gives the agent knowledge: how to use what it already has. They combine, and often literally: 11 352 of the skills here declare which MCP servers they need to work.
Why are there fewer skills here than in other catalogues?
Because we deduplicate by content. Of 79 600 files found on GitHub, 61 947 are unique — the rest is the same skill copied into someone else's repository, word for word. Catalogues that count files rather than skills show every copy as a separate entry.
What does the token count mean?
A skill is loaded into the model's context when it is used, so its size is a running cost on every request that touches it. We measure the whole folder, not just SKILL.md: one official skill is 377 tokens, another drags 83 files of fonts behind it.
How do I install a skill?
Copy the skill folder into ~/.claude/skills for personal use, or into .claude/skills inside a project. The agent picks it up by the name in the SKILL.md header — which is worth checking: 7 890 skills here share a name with another skill, and two of them cannot sit side by side.