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.
Use Trivy vulnerability scanner in offline mode to discover security vulnerabilities in dependency files. This skill covers setting up offline scanning, executing Trivy against package lock files, and generating JSON vulnerability reports without requiring internet access.
Generate structured CSV security audit reports from vulnerability data with proper filtering and formatting. This skill covers CSV schema design for security reports, using Python csv.DictWriter, severity-based filtering, and field mapping from JSON to tabular format.
Using map projections to calculate real-world distances in meters or kilometers accurately.
Techniques for loading and initial processing of GeoJSON and coordinate-based datasets using GeoPandas.
Methods for filtering GeoDataFrames based on spatial relationships like containment and intersection.
Skill to extract information from the structured JSON data, including Slack messages and document metadata.
Skill to estimate the number of consumed tokens for the task.
Compare holdings between two quarters or find top holders of a specific stock.
Extract AUM, holdings count, and detailed holding information for a specific fund.
Search for fund accession numbers and stock CUSIPs using fuzzy matching.
Security considerations for Jackson JSON deserialization, specifically regarding `@JacksonInject` and unintended property overrides.
Best practices for securing JavaScript execution in Java applications using ScriptEngines like Rhino or Nashorn.
Retrieve pull request and issue data from GitHub repositories using the gh CLI with specific filters and JSON output for downstream processing.
Process JSON data from GitHub CLI using jq to calculate metrics like average merge times, counts, and top contributors.
Verifies model components like loss functions using unit tests and saves the results as NumPy archives.
Manages NLP environments, handling library dependencies like PyTorch, Transformers, and custom local packages.
Implements the Simple Preference Optimization (SimPO) loss function in PyTorch, focusing on length-normalized log probabilities and target reward margins.
Efficiently organizes large numbers of files into directories.
Logic for categorizing documents into subjects based on keyword matching.
Extracts text from DOCX and PPTX documents for content analysis.
Extracts text from PDF documents for content analysis.
Mapping Python's functional tools to idiomatic Scala equivalents, including lambdas and collection methods.
Mapping standard and common libraries from Python to Scala, including datetime, decimal, and JSON.
Translating Python classes, inheritance, and generic variance to Scala equivalents.
Basic syntax and type mapping from Python to Scala, including primitive types and common control structures.
Parse duration and time constraints from email text.
Extract text and identifying colored regions (e.g., rectangles) from a PDF using pdfplumber.
Algorithm to find earliest available meeting slots given constraints and existing appointments.
Loading CSV data, formatting currency/large numbers, and implementing tooltips in D3.
Techniques for creating clustered bubble charts using D3 force simulations (v6).
Building dynamic tables with D3 and implementing bidirectional interactions with SVG elements.
A skill to process GLM NetCDF output and calculate specific RMSE metrics by merging with field observations.
A skill to edit GLM's namelist file (glm3.nml) by safely updating parameter values within specific blocks.
A skill to execute the GLM binary and manage its simulation output.
Filter CSV data (restaurants, accommodations, attractions) based on criteria like city, cuisine, budget, and pet-friendliness.
Create a JSON structure for a 7-day travel plan.
Use a distance matrix CSV to find travel time and distance between cities for self-driving trips.
Techniques for image preprocessing and template matching to count objects in images.
Tools and techniques for extracting keyframes and processing video files using FFmpeg.
Covers advanced Excel lookup functions including VLOOKUP, INDEX/MATCH, and XLOOKUP for multi-dimensional data retrieval.
Covers descriptive statistics (mean, median, percentiles) and weighted averages using Excel formulas.
Guidelines for applying strict brand color palettes and minimalist technical design standards to generated imagery.
Standardized structure for branding metadata in engineering documentation.
Guidelines and structures for composing classical Chinese poetry, specifically seven-character regulated verse (Qi-Yan Lu-Shi).
Provides guidelines for filling out PDF forms using programming tools.
Greedy matching of centroid points to expert annotations based on standard Euclidean distance.
Implements DBSCAN with a weighted Euclidean distance metric.
Multi-objective optimization with Pareto frontiers. Use when optimizing multiple conflicting objectives simultaneously, finding trade-off solutions, or computing Pareto-optimal points.
Creating structured CSV reports for security findings.
Performing offline security audits on package-lock.json files using Trivy.
Provides foundational techniques for loading, projecting, and manipulating geospatial datasets using GeoPandas.
Provides techniques for performing spatial operations like joins, contains, and distance calculations to identify relations between geographic features.
Provides strategies for traversing and filtering hierarchical JSON datasets stored in flat files.
Provides utility functions for reading, manipulating, and writing JSON data structures efficiently in Python.
Techniques for parsing TSV/JSON files for financial reporting data (13F).
Logical patterns for comparing 13F holdings across quarters to determine net change.
Security practices and vulnerability patching for Apache Druid, focusing on JavaScript sandbox configuration.
Techniques for applying security fixes to Java projects using git, diffs, and Maven.
Skills for querying GitHub API data using the `gh` CLI, specifically for extracting PR and issue metrics.
Skills for processing JSON data in the CLI, primarily using `jq`.
Claude Skills — questions
Answers built from the skills we actually parsed.