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.
Use Excel statistical functions for descriptive analysis including percentiles, weighted calculations, and data summaries.
Use the xlsx skill tool to create, read, modify and analyze Excel spreadsheets with formulas and formatting.
Common operations and patterns for using the xlsx skill tool to manipulate Excel files programmatically.
Anthropic's official brand color palette, typography, and design tokens for use in branded materials.
Creating technical diagrams and exploded-view illustrations using Python Pillow with geometric primitives and text annotations.
Modern Mandarin rhyme groups for classical Chinese poetry composition, mapping finals to rhyme categories.
Rules and structure of Chinese seven-character regulated verse (七言律诗), including tonal patterns, parallelism, and rhyme schemes.
California SC-100 Small Claims Court form field mapping and filling guide.
Fill PDF form fields using pypdf library in Python, including text fields and checkboxes.
Define custom distance/similarity metrics for DBSCAN clustering with sklearn, using weighted Euclidean distances.
Parallel processing with joblib for grid search and batch computations across multiple CPU cores.
Multi-objective optimization with Pareto frontiers for finding trade-off solutions between conflicting objectives.
Extract CVSS scores from vulnerability data sources with proper fallback handling across NVD, GHSA, and RedHat sources.
Use Trivy vulnerability scanner in offline mode to discover security vulnerabilities in dependency files.
Generate structured CSV security audit reports from vulnerability data with proper filtering and formatting.
Loading and processing GeoJSON earthquake and plate boundary data with GeoPandas for spatial analysis.
Using GeoPandas coordinate projections for accurate distance calculations on geospatial data.
Analyzing earthquake data relative to tectonic plate boundaries using PB2002 dataset and GeoPandas.
Techniques for retrieving structured information from enterprise Slack/document JSON data files.
Patterns for analyzing and outputting structured JSON answers from enterprise data queries.
Analyze SEC 13-F filings data including AUM, holdings count, and cross-quarter comparisons using TSV files.
Fuzzy string matching for fund names and stock CUSIPs using thefuzz library.
Apache Druid JavaScript RCE vulnerability (CVE-2021-25646) fix via @JacksonInject hardening and constructor validation.
Preventing Jackson @JacksonInject override attacks where JSON input can replace server-side injected values.
Computing pull request statistics (merge time, top contributors) from gh CLI JSON output using jq.
Using the gh CLI to search and list GitHub issues and pull requests with date filters and label queries.
Using jq to parse, filter, and aggregate JSON data from CLI tools for generating reports.
PyTorch patterns for implementing preference optimization losses (DPO, SimPO, etc.) for LLM training.
SimPO (Simple Preference Optimization) loss computation for LLM alignment without a reference model.
Handle conditional sections in Word templates with IF/END_IF markers, removing or keeping content based on data values.
Manipulate Word .docx files with python-docx, including handling split placeholders across runs and conditional sections.
Extract text from DOCX and PPTX files using python-docx and python-pptx for content analysis.
Classify academic papers and documents into subject categories using keyword-based text analysis.
Extract text from PDF files using Python libraries (PyPDF2, pdfplumber) for content analysis and classification.
Guide for mapping Python collection types and operations to Scala equivalents.
Guide for translating Python functional patterns (map, flatMap, Option, monads) to idiomatic Scala.
Guide for writing idiomatic Scala including naming conventions, error handling, and pattern matching.
Guide for translating Python classes, inheritance, ABC, generics and builder patterns to idiomatic Scala.
Reference for translating Python syntax constructs (enums, dataclasses, type vars, protocols) to Scala equivalents.
Techniques for parsing visual calendar PDFs to extract appointment blocks, free slots, and time boundaries.
Workflow for parsing meeting request emails, matching constraints to calendar availability, and generating reply files.
Load and parse CSV data with D3.js v6 using d3.csv() and d3.autoType for local file serving.
Build interactive HTML data tables with D3.js v6, including row highlighting and click-based selection synced with charts.
Create force-simulation bubble charts with D3.js v6, including sector clustering, collision avoidance, tooltips, and legends.
Calibration strategy for GLM lake temperature simulations, including parameter sensitivity and typical ranges.
Running the General Lake Model (GLM) and understanding its NML configuration file format.
Reading and analyzing GLM NetCDF output with Python netCDF4 and pandas for RMSE evaluation.
Planning multi-city travel itineraries with budget constraints, route optimization, and cuisine diversity.
Filtering accommodations for pet-friendly stays by analyzing house_rules field in accommodation data.
Querying travel planning datasets (cities, restaurants, accommodations, attractions, distances) for itinerary generation.
Extract key frames (I-frames) from video files using FFmpeg for analysis and processing.
Convert images from RGB/BGR to grayscale using OpenCV and save in-place.
Count occurrences of a template object in an image using OpenCV template matching with non-maximum suppression.
Using INDEX/MATCH formulas in Excel for two-condition lookups across sheets.
Excel statistical functions (MIN, MAX, MEDIAN, AVERAGE, PERCENTILE, SUMPRODUCT) with ROUND.
Editing existing Excel files with openpyxl while preserving formatting and adding formulas.
Anthropic official brand color palette, typography standards, and design tokens for consistent brand application.
Techniques for drawing isometric or orthographic exploded-view hardware diagrams programmatically using Pillow, with annotation leader lines and layer separation.
Create technical poster and diagram images using Pillow (PIL), including shapes, text, lines, and layered composition.
How to compose a seven-character regulated verse (七言律诗) in Classical Chinese, including tonal patterns, rhyme schemes, and structural requirements.
Answers built from the skills we actually parsed.