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

42 661–42 720 of 61 947

page 712 of 1 033
Environment Setup
by cxcscmu

Procedures for setting up the python environment, installing dependencies, and verifying installations.

164 tokens
Simpo Implementation
by cxcscmu

Guidelines for implementing the SimPO loss function as per the SimPO paper.

358 tokens
DOCX Manipulation
by cxcscmu

Manipulate Word documents using python-docx, including text replacement and handling conditional sections.

289 tokens
JSON Processing
by cxcscmu

Efficiently read and parse JSON files for use in automation tasks.

86 tokens
File Management
by cxcscmu

This skill covers organizing files into subdirectories by subject matter.

109 tokens
Scala Data Modeling
by cxcscmu

Modeling domain entities and transformations using case classes, companion objects, and type-safe hierarchies.

235 tokens
Scala Functional Idioms
by cxcscmu

Idiomatic functional programming in Scala using sealed traits, pattern matching, and Option/Either for robust error handling.

238 tokens
Calendar Scheduler
by cxcscmu

Logic for calculating meeting slots based on constraints and availability.

124 tokens
JSON Parser
by cxcscmu

Parsing JSON input files for structured data extraction.

88 tokens
PDF Analyzer
by cxcscmu

Extracting text and metadata from PDF documents.

107 tokens
D3 Data Binding
by cxcscmu

Efficiently binding data to DOM elements and handling user interactions like hover and click in D3.js.

177 tokens
D3 Force Clustering
by cxcscmu

Creating bubble clusters in D3.js using force simulations.

139 tokens
D3 Table Rendering
by cxcscmu

Creating data-driven HTML tables using D3.js.

181 tokens
Data Analysis
by cxcscmu

This skill covers computing RMSE metrics from observational and simulated water temperature data.

138 tokens
Glm Simulation
by cxcscmu

This skill covers running the General Lake Model (GLM) and modifying its configuration file (glm3.nml).

159 tokens
Data Miner
by cxcscmu

Provides methods to search, parse, and filter local CSV files in /app/data/.

213 tokens
Itinerary Generator
by cxcscmu

Handles the structural requirements and formatting of the 7-day travel itinerary JSON.

165 tokens
Ffmpeg Frame Extraction
by cxcscmu

Use ffmpeg to extract key frames (I-frames) from a video file into a directory.

166 tokens
Image Grayscale Conversion
by cxcscmu

Use ImageMagick to convert an image to grayscale inplace.

91 tokens
Object Counting In Images
by cxcscmu

Detect and count occurrences of template images within a larger target image.

220 tokens
Data Lookup
by cxcscmu

Advanced data retrieval in Excel using INDEX and MATCH.

124 tokens
Excel Analysis
by cxcscmu

Techniques for statistical analysis in Excel including weighted means, percentiles, and rounding.

171 tokens
Python Pillow Diagrams
by cxcscmu

Create clean technical posters and diagrams using the Python Pillow library, including shape drawing, typography placement, and annotation.

793 tokens
Chinese Poetry Qilv
by cxcscmu

Explains the rules, forms, and modern rhyming conventions for composing a seven-character regulated verse (Qi Lu).

432 tokens
CLI File Writing
by cxcscmu

How to write multi-line text files using command line interfaces.

176 tokens
Python Pypdf
by cxcscmu

Guide on using the Python pypdf library to read, write, and fill PDF forms programmatically.

321 tokens
Custom Distance Metrics
by cxcscmu

Custom distance metric implementation for use with clustering algorithms like DBSCAN.

240 tokens
Parallel Processing
by cxcscmu

Parallel processing with joblib to speed up computationally intensive parameter grid searches.

178 tokens
CSV Reporting
by cxcscmu

Output vulnerability reports as a formatted CSV file.

522 tokens
Cvss Extraction
by cxcscmu

Extract CVSS scores from Trivy JSON output.

394 tokens
Trivy Offline Scanning
by cxcscmu

Use Trivy for offline vulnerability scanning of dependency files like package-lock.json.

294 tokens
Geopandas Distance Calculation
by cxcscmu

How to calculate distance between points and other geometries (like lines or polygons) in metric units using GeoPandas.

552 tokens
Geopandas Point In Polygon
by cxcscmu

How to determine which points fall inside a specific polygon using GeoPandas.

436 tokens
JSON Data Processing
by cxcscmu

Provides techniques for parsing and extracting data from JSON files in Python.

114 tokens
Python Text Search
by cxcscmu

Techniques to find specific data points in nested Python dictionaries using recursion.

180 tokens
13f Data Parsing
by cxcscmu

A skill for parsing and analyzing SEC Form 13F TSV files, including COVERPAGE, INFOTABLE, and SUMMARYPAGE, using pandas.

400 tokens
Fuzzy String Matching
by cxcscmu

A skill for finding best string matches in datasets using fuzzy matching libraries like fuzzywuzzy or rapidfuzz.

203 tokens
Jackson Druid Cve
by cxcscmu

Security and Jackson deserialization issues in Apache Druid, focusing on property bypasses.

199 tokens
Github Search API
by cxcscmu

Fetch repository metrics, issues, and pull requests over a specific date range using the GitHub Search API.

535 tokens
Python Datetime Metrics
by cxcscmu

Parse datetime strings and compute time durations/averages for datasets (like PR merge times) in Python.

539 tokens
Huggingface Trl
by cxcscmu

Using Hugging Face TRL library for building custom trainers for Preference Optimization methods like DPO, SimPO, etc.

291 tokens
Simpo Loss
by cxcscmu

Implement the SimPO (Simple Preference Optimization) loss function for LLM alignment. Use this skill whenever implementing SimPO training objectives, reference-free reward optimization, or Bradley-Terry preference loss with target reward margin. Triggers on: SimPO, preference optimization loss, average log probability reward, gamma margin.

718 tokens
Python DOCX Templating
by cxcscmu

A skill for replacing placeholders and handling conditional blocks in python-docx.

470 tokens
Document Text Extraction
by cxcscmu

Extracts text from PDF, DOCX, and PPTX files using Python.

274 tokens
Text Classification Heuristics
by cxcscmu

Classifies text into predefined categories using keyword matching heuristics.

471 tokens
Scala Circe JSON
by cxcscmu

Guide for using Circe in Scala 2.13 for parsing and generating JSON, specifically when translating Python JSON handling.

363 tokens
Scala Functional Builders
by cxcscmu

Guide for creating functional fluent builders in Scala.

363 tokens
Scala Generics Variance
by cxcscmu

Guide for translating Python TypeVars and generics to Scala covariant and contravariant types.

358 tokens
Scala Method Overloading
by cxcscmu

Guide for translating Python @overload and dynamic typing (Any, Union) to Scala method overloading and type matching.

395 tokens
PDF Drawing Extraction
by cxcscmu

Extracts vector graphics, colors, and text from PDF files using PyMuPDF to analyze calendars or visual schedules.

360 tokens
Schedule Constraint Parsing
by cxcscmu

Uses regular expressions to parse dates, time ranges, and durations from natural language text like meeting requests.

452 tokens
D3 Force Bubble
by cxcscmu

Guide for creating clustered bubble charts using D3.js force simulations (v6+), including collision and categorization.

298 tokens
D3 Linked Interactivity
by cxcscmu

Guide for linking D3.js SVG visualizations with DOM elements like HTML tables for bidirectional interactivity (hover, click, highlight).

378 tokens
Glm Calibration
by cxcscmu

Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.

2k tokens
Python Pandas Merge
by cxcscmu

Matching observations with simulated data using exact datetime and rounded depth merges in pandas.

251 tokens
Python Xarray Netcdf
by cxcscmu

Reading and processing NetCDF outputs from models like GLM using Python and xarray.

155 tokens
Data Analysis
by cxcscmu

Using Python and Pandas to analyze large CSV datasets and filter based on specific criteria like budget, location, and amenities.

229 tokens
Route Planning
by cxcscmu

Algorithmic planning of itineraries avoiding specific transport modes and allocating time based on budget constraints.

367 tokens
Image Grayscale
by cxcscmu

Convert images to grayscale in-place.

90 tokens
Video Keyframe Extraction
by cxcscmu

Extract key frames (I-frames) from video files using FFmpeg.

79 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.