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

42 781–42 840 of 61 947

page 714 of 1 033
Run2 Advanced Template Matching
by cxcscmu

Advanced OpenCV template matching with dynamic threshold tuning, robust NMS filtering, and multi-scale detection for object counting in images.

2k tokens
Run2 CSV Validation Export
by cxcscmu

Generate and validate CSV files with data integrity checks, verification, and comprehensive error handling for reliable data export.

2k tokens
Run2 Ffmpeg Robust Extraction
by cxcscmu

Robust FFmpeg video frame extraction with error handling, alternative methods, and comprehensive frame selection strategies.

938 tokens
Run2 Image Processing Verification
by cxcscmu

Robust image processing with format conversion, in-place modification, and comprehensive verification of image properties.

2k tokens
Run2 Excel Percentages
by cxcscmu

Calculating and formatting percentages in Excel with proper rounding and display

765 tokens
Run2 Excel Statistics Aggregates
by cxcscmu

Excel statistical functions for datasets including MIN, MAX, MEDIAN, AVERAGE, QUARTILE, and SUMPRODUCT

975 tokens
Run2 Multi Condition Lookups
by cxcscmu

Implementing two-condition lookups in Excel using INDEX/MATCH with proper sheet references

785 tokens
Run2 Openpyxl Cross Sheet
by cxcscmu

Using openpyxl to edit Excel workbooks with cross-sheet formulas while preserving all formatting

1k tokens
Run2 Anthropic Brand
by cxcscmu

Anthropic official brand colors, typography tokens, and design guidelines extracted from anthropic.com CSS.

486 tokens
Run2 Exploded View Layout
by cxcscmu

Improved layout strategy for technical exploded-view diagrams with better spacing and visual balance.

481 tokens
Run2 Pillow Technical Poster
by cxcscmu

Pillow techniques for technical posters including 3D layers, annotations, and balanced layouts.

449 tokens
Run2 Mandarin Rhyming
by cxcscmu

Detailed guide to modern Mandarin rhyming and tone classification for classical Chinese poetry, including common pitfalls.

436 tokens
Run2 Peace Poem Composition
by cxcscmu

Guide for composing a classical Chinese poem on the theme of peace, covering thematic structure and literary devices.

394 tokens
Run2 Seven Char Regulated Verse
by cxcscmu

Comprehensive rules, tonal patterns, and verification checklist for composing a seven-character regulated verse (七言律诗).

711 tokens
Run2 Ca Small Claims
by cxcscmu

Comprehensive field mapping for California SC-100 Small Claims Court form with field IDs and filling guidance.

1k tokens
Run2 PDF Form Filling
by cxcscmu

Complete workflow for filling fillable PDF forms using Claude Code PDF skill scripts with pypdf.

688 tokens
Run2 Dbscan Custom Metric
by cxcscmu

DBSCAN with custom weighted Euclidean distance metric for spatial clustering of annotations.

236 tokens
Run2 Parallel Grid Search
by cxcscmu

Parallel DBSCAN hyperparameter grid search with joblib for Mars cloud clustering.

233 tokens
Run2 Pareto Optimization
by cxcscmu

Identifying Pareto-optimal solutions for multi-objective optimization (maximize F1, minimize delta).

248 tokens
Run2 CSV Reporting
by cxcscmu

Generate structured CSV security audit reports from Trivy JSON vulnerability data with deduplication, proper quoting, and field mapping.

575 tokens
Run2 Cvss Score
by cxcscmu

Extract CVSS v3 scores from Trivy vulnerability data with source priority fallback (NVD > GHSA > RedHat) and handle missing data gracefully.

331 tokens
Run2 Trivy Offline
by cxcscmu

Use Trivy vulnerability scanner in offline mode to discover security vulnerabilities in dependency files, covering setup, execution, and JSON output parsing.

559 tokens
Run2 Antimeridian Handling
by cxcscmu

Handling the antimeridian (180/-180 longitude) in geospatial analysis with GeoPandas and Shapely.

315 tokens
Run2 Geopandas Geospatial Distance
by cxcscmu

Accurate geospatial distance calculations using GeoPandas with appropriate map projections for global-scale analysis.

418 tokens
Run2 Plate Boundary Analysis
by cxcscmu

Finding earthquakes within tectonic plates and computing distances to plate boundaries using PB2002 data.

493 tokens
Run2 Enterprise Data Retrieval
by cxcscmu

Comprehensive guide for retrieving structured information from enterprise JSON data files containing Slack messages, documents, meetings, and metadata.

573 tokens
Run2 Slack Analysis
by cxcscmu

Advanced patterns for analyzing Slack conversations to extract reviewers, competitor insights, and shared resources from enterprise product channels.

411 tokens
Run2 13f Data Analysis
by cxcscmu

Comprehensive guide for analyzing SEC 13-F quarterly filings data (TSV format) including fund lookup, AUM, holdings comparison, and stock investor analysis.

764 tokens
Run2 Druid Cve 2021 25646
by cxcscmu

Complete fix for Apache Druid CVE-2021-25646 JavaScript RCE via @JacksonInject override in all 7 affected components.

651 tokens
Run2 Jackson Inject Security
by cxcscmu

Preventing Jackson @JacksonInject bypass via empty JSON keys by using OptBoolean.FALSE to reject user-supplied input for injected parameters.

601 tokens
Run2 Data Analysis
by cxcscmu

Using jq to compute statistics from GitHub API JSON responses including counts, averages, grouping, and label filtering.

367 tokens
Run2 Gh REST API
by cxcscmu

Using the GitHub REST Search API to query PRs and issues with date filtering, pagination, and field extraction.

355 tokens
Run2 Pytorch Preference Optimization
by cxcscmu

Environment setup and testing patterns for SimPO preference optimization with PyTorch.

309 tokens
Run2 Simpo Loss
by cxcscmu

Complete SimPO loss implementation with exact formula derivation from the paper.

547 tokens
Run2 Python DOCX Split Placeholders
by cxcscmu

Robust python-docx template filling that handles split runs, conditional sections, nested tables, headers, and footers.

838 tokens
Run2 Document Text Extraction
by cxcscmu

Extract text from PDF, PPTX, and DOCX files for content classification, with error handling and fallback strategies.

557 tokens
Run2 Keyword Classification
by cxcscmu

Classify academic papers into subject categories using weighted keyword matching with regex word boundaries and case-insensitive search.

689 tokens
Run2 Scala Circe JSON
by cxcscmu

Using circe for JSON tokenization in Scala, including printing, cursor navigation, and path-based access.

222 tokens
Run2 Scala Idiomatic Patterns
by cxcscmu

Idiomatic Scala patterns for translating Python code including enums, case classes, and naming conventions.

303 tokens
Run2 Scala Immutable Builder
by cxcscmu

Implementing the builder pattern in Scala using immutable case classes or private constructors with copy.

269 tokens
Run2 Scala Option Handling
by cxcscmu

Handling absence and nullability in Scala using Option, with patterns for translating Python None handling.

245 tokens
Run2 Scala Variance
by cxcscmu

Expressing variance annotations in Scala generics when translating from Python TypeVar covariant/contravariant types.

240 tokens
Run2 Meeting Scheduling
by cxcscmu

Schedule meetings into calendar free slots considering time constraints, timezone conversion, and blue-block overrides.

299 tokens
Run2 PDF Calendar Parsing
by cxcscmu

Extract calendar events from PDF by mapping colored rectangles to a 15-min grid using PyMuPDF.

420 tokens
Run2 Timezone Conversion
by cxcscmu

Convert between US time zones for scheduling, defaulting unspecified zones to calendar timezone.

337 tokens
Run2 D3 Force Bubble
by cxcscmu

D3.js v6 force-directed bubble chart with sector clustering, collision avoidance, size mapping, and cross-component interaction.

418 tokens
Run2 D3 Interactive Table
by cxcscmu

D3.js data table with exact column headers, formatted market cap, and bidirectional highlight with bubble chart.

252 tokens
Run2 Glm Calibration Strategy
by cxcscmu

Two-phase grid search calibration for GLM parameters with parameter sensitivity analysis and regex-based nml editing.

635 tokens
Run2 Glm Lake Modeling
by cxcscmu

Complete guide to setting up, running, and configuring the General Lake Model (GLM) for 1D lake temperature simulation.

748 tokens
Run2 Netcdf Obs Matching
by cxcscmu

Extracting GLM NetCDF output and computing exact RMSE metrics via datetime+depth merge against field observations.

863 tokens
Run2 Budget Validation
by cxcscmu

Validate travel budget calculations including accommodation nights, meal costs, and constraint compliance.

291 tokens
Run2 Itinerary Planning
by cxcscmu

Plan multi-city driving itineraries with proper day allocation, cuisine variety, and format compliance.

375 tokens
Run2 Travel Data Extraction
by cxcscmu

Extract and validate travel data from CSV/TXT databases ensuring city-specific matching and constraint compliance.

417 tokens
Run2 Ffmpeg Keyframes
by cxcscmu

Extract I-frame keyframes from video files using FFmpeg, with output verification and naming conventions.

200 tokens
Run2 Opencv Grayscale
by cxcscmu

Convert images to grayscale in-place using OpenCV, including both keyframes and template images.

241 tokens
Run2 Template Matching Tuning
by cxcscmu

Tune OpenCV template matching parameters (threshold and dedup distance) for accurate object counting in pixel-art games.

535 tokens
Run2 Excel Index Match
by cxcscmu

INDEX&MATCH for two-condition lookups in Excel, with correct absolute/mixed references for fill-down/fill-right

424 tokens
Run2 Excel Weighted Mean
by cxcscmu

GDP-weighted mean and descriptive statistics for net exports as % of GDP in Excel

369 tokens
Run2 Anthropic Brand Tokens
by cxcscmu

Precise Anthropic brand color tokens and typography guidelines for design artifacts, with matplotlib-specific notes.

708 tokens
Run2 Exploded View Drawing
by cxcscmu

Production-ready technique for technical exploded-view hardware diagrams in matplotlib, with layer details, annotations, and title blocks.

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.