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. 79 566 files from 1 758 authors, of which 61 913 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.

61 913
unique skills
out of 79 566 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
7 886
name collisions
two skills with one name cannot sit side by side

43 441–43 500 of 61 913

page 725 of 1 032
Geopandas Plate Tectonics
by cxcscmu

> How to load, filter, and work with tectonic plate boundary and polygon data using GeoPandas. Use this skill whenever the user mentions plate boundaries, tectonic plates, PB2002 data, or needs to identify which tectonic plate a point belongs to, or extract boundaries for a specific plate like Pacific (PA), African (AF), North American (NA), etc.

777 tokens
JSON QA
by cxcscmu

Answer questions from JSON enterprise data and write results to answer.json. Use this skill when the user asks multiple questions about enterprise data and needs answers stored in a JSON file with token counts. Handles the output format requirements for answer.json.

285 tokens
Fund Comparison
by cxcscmu

Compare hedge fund holdings between two quarters to identify changes in investment positions. Use this skill when analyzing Q-over-Q changes in fund portfolios, finding top increased/decreased positions, or tracking specific fund activity across reporting periods. Triggers on questions about "change from Q2 to Q3", "increased investment", "top buys/sells", or any cross-quarter 13F comparison.

914 tokens
Sec 13f Analysis
by cxcscmu

Analyze SEC 13F filings data from TSV files. Use this skill whenever the user asks about hedge fund holdings, AUM (Assets Under Management), stock positions, fund managers, or any analysis of 13F filings data. Triggers on questions about fund portfolios, investment positions, quarterly comparisons, or SEC filing data stored in COVERPAGE.tsv, INFOTABLE.tsv, SUMMARYPAGE.tsv files.

1k tokens
Druid Javascript Rce Patch
by cxcscmu

How to patch Apache Druid JavaScript RCE vulnerabilities (CVE-2021-25646 and similar). Use this skill whenever patching Druid JavaScript filter/aggregator security bypass vulnerabilities, when the @JacksonInject config can be overridden via JSON, or when handling arbitrary code execution via JavaScript in Druid sampler/query endpoints.

800 tokens
Druid Maven Build
by cxcscmu

How to build Apache Druid with Maven, including how to skip OOM-prone modules, skip code quality checks for patched files, and build only specific modules. Use this skill when building Druid from source, when rebuilding after applying security patches, or when Maven build fails due to memory or code quality check issues.

501 tokens
Jackson Inject Security
by cxcscmu

Security considerations for Jackson @JacksonInject annotation in Java applications. How to prevent JSON input from overriding server-injected values. Use this skill whenever reviewing code that uses @JacksonInject, when an attacker could supply JSON to override configuration objects, or when fixing deserialization vulnerabilities related to injectable values.

672 tokens
Gh Issue Analysis
by cxcscmu

> total counts, bug report identification by label substring matching, and resolved bug counts. Use this skill whenever the user asks about issue metrics, bug counts, triage stats, or community health reports for a GitHub repo.

772 tokens
Gh Pr Analysis
by cxcscmu

> How to fetch and analyze pull request data from a GitHub repository for a contributors. Use this skill whenever the user wants PR metrics, pull request summaries, contributor leaderboards, or community pulse reports.

780 tokens
Github Repo Stats
by cxcscmu

> How to gather GitHub repository statistics (PRs, issues, contributors) using the GitHub REST API via curl and Python. Use this skill whenever the user asks for a community pulse, activity summary, monthly report, or repository metrics for any GitHub repo — even if they don't explicitly mention the API.

1k tokens
Nlp Preference Optimization
by cxcscmu

Set up and run NLP preference optimization experiments (DPO, SimPO, CPO). Use this skill when configuring trainer environments, installing dependencies (torch, trl, transformers, peft), or running preference optimization unit tests. Triggers on: DPO, SimPO, preference optimization, trl trainer, RLHF, alignment training.

333 tokens
Offer Letter DOCX
by cxcscmu

> Fill Word offer letter templates with employee data, replacing {{PLACEHOLDER}} tokens and handling {{IF_CONDITION}}...{{END_IF_CONDITION}} conditional blocks. Use this skill whenever the user asks to generate, fill, or produce an offer letter from a .docx template and a JSON data file, or whenever you need to merge HR data into a Word document template with placeholders and optional sections (e.g. relocation package, signing bonus).

1k tokens
PDF File Organizer
by cxcscmu

Organizes PDF, PPTX, and DOCX academic files into subject folders by extracting and analyzing their title/abstract text. Use this skill whenever the user needs to sort or categorize a batch of research papers or documents into topic-based folders (e.g., LLM, quantum computing, biology, physics, music). Handles arXiv papers and other academic documents automatically.

884 tokens
Python Scala Builder Pattern
by cxcscmu

Guide for translating Python fluent builder patterns and mutable accumulator objects to idiomatic immutable Scala builders with companion objects. Use this skill when converting Python classes with method chaining (returning self), mutable state accumulation, or factory/build() methods to Scala.

1k tokens
Python Scala Functional Generics
by cxcscmu

Guide for translating Python generic containers (covariant/contravariant), functor/monad simulations, and JSON handling to idiomatic Scala. Use this skill when converting Python Generic[T_co], Generic[T_contra], TokenFunctor, TokenMonad, or json.dumps/json.loads patterns to Scala variance annotations, proper functional types, and Circe JSON.

2k tokens
Python Scala Sealed Traits
by cxcscmu

Guide for translating Python Enum, Protocol, and abstract class hierarchies to Scala sealed trait hierarchies. Use this skill whenever converting Python Enum classes, runtime-checkable Protocol types, abstract base classes (ABC), or Union type aliases to idiomatic Scala sealed traits, case objects, and type classes.

973 tokens
Calendar Scheduling
by cxcscmu

Parse a visual calendar PDF to extract existing appointments and find earliest available meeting slots. Handles blue (low-priority/flexible) blocks as overwritable free time. Use when given a calendar image/PDF and meeting requests that need to be scheduled without conflicts.

415 tokens
Email Reply Generator
by cxcscmu

Generate formatted meeting reply emails and save them as .txt files, then log results to results.json. Use when you need to respond to meeting scheduling requests with proposed time slots.

402 tokens
Timezone Conversion
by cxcscmu

Convert meeting availability times between different timezones (e.g. PST to EST). Use when a meeting request specifies availability in a timezone different from the calendar's timezone.

274 tokens
D3 Bubble Chart
by cxcscmu

> How to build a D3.js v6 force-directed bubble chart with sector clustering, size encoding, color legends, tooltips, and interactive selection. Use this skill whenever the user wants a bubble chart, force simulation, cluster layout, or interactive SVG circles with D3.

813 tokens
D3 Data Table
by cxcscmu

> How to build an interactive HTML data table driven by D3.js v6 with sortable columns, row highlighting, cross-component selection, and formatted values. Use this skill when building tabular displays alongside D3 charts, especially when the table needs to stay in sync with chart interactions.

619 tokens
Glm Lake Simulation
by cxcscmu

How to run the General Lake Model (GLM3) for lake temperature simulation, calibrate parameters in glm3.nml, read NetCDF output with Python, and compute RMSE metrics against field observations. Use this skill whenever the user mentions GLM, lake temperature simulation, glm3.nml, or wants to calibrate lake model parameters.

1k tokens
Travel Data Query
by cxcscmu

Query and filter travel CSV datasets (restaurants, accommodations, attractions, distances) using Python. Use this skill whenever you need to extract specific records from the travel database files, check pet policies, filter by cuisine, look up driving times, or validate that a city exists in the dataset.

833 tokens
Travel Itinerary Planner
by cxcscmu

Build a structured multi-day travel itinerary JSON from real CSV datasets. Use this skill whenever the user asks to create a travel plan, trip itinerary, or vacation schedule from a local database of cities, restaurants, accommodations, and attractions.

916 tokens
Image Grayscale Conversion
by cxcscmu

Convert RGB color images to grayscale and save them in-place, overriding the original files. Use this skill whenever the user asks to convert images to gray-scale, desaturate photos, or prepare images for grayscale processing pipelines using OpenCV or Pillow.

308 tokens
Video Frame Extraction
by cxcscmu

Extract key frames (I-frames) from video files using FFmpeg. Use this skill whenever the user needs to pull keyframes, thumbnails, or important frames from MP4, MKV, AVI, or other video formats. Outputs PNG image files named with zero-padded indices (e.g., keyframes_001.png).

355 tokens
Excel Lookup Formulas
by cxcscmu

How to write INDEX&MATCH, VLOOKUP&MATCH, XLOOKUP, and similar two-condition lookup formulas in Excel using openpyxl. Use this skill whenever the user needs to populate data cells using lookup functions that match on two criteria (e.g., series code AND year), especially when pulling cross-sheet data with dynamic row/column matching.

770 tokens
Excel Weighted Statistics
by cxcscmu

How to calculate weighted means, net export percentages, and statistical summaries (min, max, median, mean, percentiles) in Excel using SUMPRODUCT, ROUND, PERCENTILE, and other functions. Use this skill whenever the user needs GDP-weighted averages, trade statistics as percent of GDP, or descriptive statistics across a cross-section of countries or entities.

934 tokens
Anthropic Brand Design
by cxcscmu

Guidelines for applying Anthropic's brand identity, including color palettes, typography, and visual principles. Use this skill whenever creating branded assets, posters, or UI designs for Anthropic.

387 tokens
Technical Illustration
by cxcscmu

Techniques and Python script patterns for generating technical exploded-view illustrations, including component layering, annotation leader lines, and isometric projection basics. Use this skill when generating hardware diagrams or exploded views.

550 tokens
Classical Chinese Poetic Imagery
by cxcscmu

Guidance on using classical Chinese poetic imagery for themes like war and peace. Use this skill when writing traditional Chinese poetry to ensure appropriate vocabulary and evoke classical aesthetics.

502 tokens
Seven Char Regulated Verse
by cxcscmu

Guidance on composing seven-character regulated verse (七言律诗). Use this skill whenever a task requires writing traditional Chinese poetry in the seven-character regulated style, ensuring adherence to structural, parallelism, and rhyming rules (using modern Mandarin pronunciation).

509 tokens
California Small Claims Sc100
by cxcscmu
445 tokens
Grid Search Parallel
by cxcscmu
312 tokens
Mars Cloud Clustering
by cxcscmu
449 tokens
Pareto Frontier Analysis
by cxcscmu
287 tokens
Geospatial Distance Analysis
by cxcscmu

Procedures for performing precise distance calculations between points and geometries using GeoPandas. Use this skill when calculating distances in kilometers, reprojecting GeoDataFrames, or finding the nearest features in a geospatial dataset.

627 tokens
Plate Tectonics Data Processing
by cxcscmu

Techniques for processing tectonic plate data, specifically using the PB2002 dataset. Use this skill when filtering points within plates, identifying plate boundaries, or working with global tectonic geometries in GeoPandas.

517 tokens
Answer Formatting
by cxcscmu
280 tokens
Data Retrieval
by cxcscmu
351 tokens
Enterprise Data Analysis
by cxcscmu
375 tokens
13f Analysis
by cxcscmu
417 tokens
13f Search
by cxcscmu
401 tokens
Druid Javascript Security
by cxcscmu

Specific guidance for securing JavaScript execution in Apache Druid. Use this when working with JavaScriptDimFilter, JavaScriptExtractionFn, JavaScriptAggregatorFactory, and other JS-enabled components.

355 tokens
Druid Vulnerability Patching
by cxcscmu

Techniques for identifying and patching vulnerabilities in Apache Druid, specifically focusing on Jackson deserialization and JavaScript security. Use this skill when dealing with CVEs related to RCE or security bypasses in Druid.

428 tokens
Maven Build Optimization
by cxcscmu

Optimized Maven build commands for Apache Druid to save time and resources. Use this when you need to rebuild Druid after applying patches.

307 tokens
Community Pulse Reporter
by cxcscmu

Professional methodology for transforming raw repository activity into structured community pulse reports. Use this skill when you need to calculate metrics like merge times, contributor rankings, and bug resolution rates for meeting-ready summaries.

507 tokens
Github Data Extractor
by cxcscmu

Expert guidance on using the GitHub CLI (gh) to extract pull request and issue data for specific timeframes and repositories. Use this skill whenever you need to gather metrics for community reports, activity analysis, or repository health checks.

587 tokens
Nlp Environment Setup
by cxcscmu
386 tokens
DOCX Template Filling
by cxcscmu

Robustly fill Word (.docx) templates with JSON data. Handles split placeholders, nested tables, headers/footers, and conditional logic like IF/END_IF blocks. Use this skill whenever you need to generate professional documents from templates.

808 tokens
Offer Letter Data Mapping
by cxcscmu

Logic for mapping employee JSON data to offer letter template placeholders. Includes handling of conditional fields like relocation packages. Use this skill when preparing data for offer letter generation.

376 tokens
Document Organizer
by cxcscmu
312 tokens
Paper Classifier
by cxcscmu
573 tokens
Python Scala Data Structures Mapping
by cxcscmu

Guidelines for translating Python dataclasses, enums, and collections to Scala.

204 tokens
Python Scala Functional Idioms
by cxcscmu

Guidelines for translating Python functional patterns and simulations to idiomatic Scala.

190 tokens
Python Scala Generics Mapping
by cxcscmu

Guidelines for translating Python TypeVars and Protocols to Scala Generics and Traits.

234 tokens
Python Scala External Libraries
by cxcscmu

Guidelines for mapping Python standard libraries (json, datetime) to Scala equivalents (Circe, java.time).

152 tokens
Meeting Request Parser
by cxcscmu

Extracts meeting durations and constraints from a meeting request JSON file (e.g., test_input.json). Use this whenever you need to process incoming meeting invitations to understand their specific requirements.

328 tokens
Meeting Response Generator
by cxcscmu

Generates reply text files and the final result log with specific formatting for date, time, and JSON. Use this skill whenever you need to provide a professional meeting proposal in a fixed format.

341 tokens
Meeting Scheduler
by cxcscmu

Logic for finding the earliest possible meeting slot based on calendar availability and email request constraints. Use this skill whenever you need to propose a meeting time from a set of constraints and an existing schedule.

308 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: 11 350 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 79 566 files found on GitHub, 61 913 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: 7 886 skills here share a name with another skill, and two of them cannot sit side by side.