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

42 721–42 780 of 61 947

page 713 of 1 033
Python Openpyxl
by cxcscmu

Using openpyxl to read, write, and modify Excel files while preserving formatting and using formulas.

169 tokens
Run2 Advanced Pil Techniques
by cxcscmu

Advanced PIL/Pillow techniques for depth effects, sophisticated shapes, and professional visual design

970 tokens
Run2 Brand Color Strategy
by cxcscmu

Strategic color application following Anthropic brand standards for professional technical materials

914 tokens
Run2 Professional Technical Layout
by cxcscmu

Professional technical diagram layout with grid systems, visual hierarchy, and spatial organization

1k tokens
Run2 Composition Technique
by cxcscmu

Advanced techniques for composing seven-character regulated verse with thematic coherence

369 tokens
Run2 Tonal Patterns
by cxcscmu

Detailed tonal pattern requirements for seven-character regulated verse in modern Mandarin

331 tokens
Run2 Verification Checklist
by cxcscmu

Comprehensive checklist to verify a completed seven-character regulated verse meets all requirements

485 tokens
Run2 PDF Skill Form Filling
by cxcscmu

Fill PDF forms using the PDF skill's form-filling scripts and workflow

986 tokens
Run2 Sc100 Form Mapping
by cxcscmu

SC-100 California Small Claims form field ID mappings and data entry guidelines

3k tokens
Run2 Clustering Metrics
by cxcscmu

Compute and aggregate F1 score and delta from clustering evaluation across images

2k tokens
Run2 Custom Distance Metrics
by cxcscmu

Implement weighted Euclidean distance metric for DBSCAN with shape parameter

1k tokens
Run2 Greedy Matching
by cxcscmu

Greedy one-to-one matching of cluster centroids to expert points with maximum distance constraint

2k tokens
Run2 Parallel Grid Search
by cxcscmu

Efficient parallel hyperparameter grid search using joblib with 847 combinations

2k tokens
Run2 Pareto Frontier
by cxcscmu

Find Pareto-optimal solutions balancing multiple conflicting objectives with rigorous verification

2k tokens
Run2 CSV Report Generation Advanced
by cxcscmu

Advanced CSV security report generation with validation, normalization, and comprehensive error handling

3k tokens
Run2 Cvss Scoring Strategy
by cxcscmu

Strategic CVSS score extraction with multi-source lookup, fallback handling, and NVD/GHSA integration

2k tokens
Run2 npm Vulnerability Scanning Enhanced
by cxcscmu

Enhanced npm vulnerability scanning with Trivy supporting multiple severity levels and complete metadata extraction

1k tokens
Multipart Geometry Handling
by cxcscmu

Work with MultiPolygon and MultiLineString geometries from real plate boundary datasets.

955 tokens
Optimal Projection Selection
by cxcscmu

Select appropriate projected CRS based on geographic region for accurate distance calculations.

732 tokens
Spatial Analysis Validation
by cxcscmu

Validate spatial analysis results to ensure correctness of point-in-polygon and distance calculations.

1k tokens
Advanced Slack Mining
by cxcscmu

Mine Slack data for embedded URLs, mentioned products, competitive intelligence, and cross-referencing with external data sources.

3k tokens
Document Metadata Extraction
by cxcscmu

Extract author, reviewer, and feedback information from structured documents and their associated discussions.

2k tokens
Multi Source Data Correlation
by cxcscmu

Correlate and merge data from multiple sources (documents, Slack, meetings, URLs) to answer enterprise questions.

2k tokens
Run2 Cross Fund Analysis
by cxcscmu

Find which funds hold a specific stock and rank them by holding value

2k tokens
Run2 Fund Analysis
by cxcscmu

Analyze individual fund holdings, AUM, and portfolio composition from 13-F data

1k tokens
Run2 Quarter Comparison
by cxcscmu

Compare holdings across quarters to identify increased/decreased investments

2k tokens
Run2 Sec13f Data Loader
by cxcscmu

Load and parse SEC 13-F TSV files with proper data type handling and validation

1k tokens
Run2 Druid Javascript Deserialization Security
by cxcscmu

Securing Apache Druid JavaScript filters against unknown property injection attacks

1k tokens
Run2 Jackson Security Patching
by cxcscmu

Creating and applying security patches for Jackson deserialization vulnerabilities in Java

1k tokens
Run2 Maven Security Build
by cxcscmu

Building Apache Druid with Maven while maintaining security patch integrity and skipping unnecessary checks

2k tokens
Run2 Data Aggregation
by cxcscmu

Aggregate and validate GitHub API data for metrics calculation with comprehensive error handling.

894 tokens
Run2 Github REST API
by cxcscmu

Query GitHub REST API with pagination and date filtering for repository data (PRs, issues).

627 tokens
Run2 JSON Validation
by cxcscmu

Validate, format, and write JSON output with schema enforcement and error handling.

1k tokens
Run2 Simpo Loss Detailed Implementation
by cxcscmu

Complete SimPO loss implementation with length-normalized rewards and target margin

973 tokens
Run2 Simpo Testing And Verification
by cxcscmu

Testing SimPO loss function with fixed tensors and output verification

1k tokens
Run2 Simpo Trainer Initialization
by cxcscmu

Proper initialization of SimPOTrainer with model loading and args setup

851 tokens
Run2 Placeholder Replacement
by cxcscmu

Robust pattern-based template processing with conditionals, data validation, and comprehensive placeholder replacement.

1k tokens
Run2 Python DOCX Basics
by cxcscmu

Working with Word documents (DOCX) using python-docx library with proper text replacement strategies.

809 tokens
Run2 Content Classification Enhanced
by cxcscmu

Improved keyword-based classification with confidence scoring, compound term detection, and refinement patterns

1k tokens
Run2 File Organization Robust
by cxcscmu

Robust file organization with verification, cleanup, and comprehensive logging

1k tokens
Run2 Multi Format Extraction
by cxcscmu

Unified multi-format extraction for PDF, DOCX, and PPTX with consistent output and quality metrics

881 tokens
Run2 PDF Extraction
by cxcscmu

Robust PDF text extraction with fallback strategies and error handling for academic papers and documents

696 tokens
Scala Immutable Builder
by cxcscmu

Building immutable configurations with fluent method chaining in Scala

559 tokens
Scala Java Time Handling
by cxcscmu

Working with Java's LocalDate and LocalDateTime in Scala for temporal tokenization

379 tokens
Scala Pattern Matching Dispatch
by cxcscmu

Type-safe dispatch using Scala pattern matching for polymorphic operations

431 tokens
Scala String Processing
by cxcscmu

String manipulation, formatting, and regex patterns in Scala

432 tokens
Run2 PDF Visual Extraction
by cxcscmu

Extract calendar event times by analyzing visual block positions relative to hour markers

1k tokens
Run2 Request Parsing Advanced
by cxcscmu

Parse meeting requests with timezone handling and constraint detection

1k tokens
Run2 Time Formatting
by cxcscmu

Format dates and times with strict adherence to required formats

1k tokens
Run2 CSV Robust Loading
by cxcscmu

Robust CSV loading and type coercion patterns for D3.js applications with multiple data sources

2k tokens
Run2 D3 Bubble Clusters
by cxcscmu

Production-ready D3.js bubble chart clustering with optimized force simulation and labeling

1k tokens
Run2 D3 Sync Interaction
by cxcscmu

Two-way synchronized selection between D3 visualization and HTML table with tooltips and scroll management

2k tokens
Run2 Market Cap Formatting
by cxcscmu

Production-ready market cap formatting with consistent decimals, edge case handling, and pre-computation

2k tokens
Run2 Glm Error Diagnosis
by cxcscmu

Diagnosing temperature profile mismatches and simulation errors in GLM outputs

2k tokens
Run2 Netcdf Glm Matching
by cxcscmu

Advanced matching of time-varying GLM simulation depths with observation data

2k tokens
Run2 Nml Calibration Workflow
by cxcscmu

Complete NML-based GLM calibration workflow with validation and verification

2k tokens
Run2 Parameter Optimization Strategy
by cxcscmu

Systematic parameter search strategies for GLM calibration with multiple metrics

1k tokens
Run2 Complete Itinerary Solution
by cxcscmu

End-to-end solution for building multi-city travel itineraries with pet-friendly accommodations and diverse cuisine constraints.

1k tokens
Run2 Data Filtering Validation
by cxcscmu

Advanced filtering and validation of travel datasets with strict cuisine matching, budget constraints, and data quality checks.

1k tokens
Run2 Itinerary Optimization
by cxcscmu

Optimized itinerary building with cuisine distribution, cost tracking, and multi-city routing for pet-friendly travel.

1k 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.