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

42 841–42 900 of 61 947

page 715 of 1 033
Run2 Matplotlib Technical Poster
by cxcscmu

Complete guide to generating polished technical poster PNGs with matplotlib, including typography, pseudo-3D layers, and annotations.

1k tokens
Run2 Chinese Poetry Composition
by cxcscmu

Refined techniques for composing classical Chinese regulated verse on war-and-peace themes, with verified imagery, couplet examples, and common pitfalls.

1k tokens
Run2 Qiyan Lushi
by cxcscmu

Complete rules, structure, and verification checklist for seven-character regulated verse (七言律诗), with corrected rhyme groups and parallel couplet standards.

884 tokens
Run2 Sc100 Small Claims Form
by cxcscmu

How to fill California SC-100 Small Claims Court PDF form using fillable field IDs; includes complete field mapping, checkbox behavior, and field fill strategy.

2k tokens
Run2 Dbscan Clustering
by cxcscmu

Efficient DBSCAN clustering with a custom parameterized distance metric using precomputed distance matrices for speed, plus centroid computation.

723 tokens
Run2 Greedy Matching
by cxcscmu

Greedy matching of predicted centroids to expert points by closest pairs first, with max distance threshold, computing F1 and delta.

732 tokens
Run2 Pareto Frontier
by cxcscmu

Computing the Pareto frontier for multi-objective optimization (maximize F1, minimize delta) with correct dominance handling and output formatting.

616 tokens
Run2 Cvss Score Extraction
by cxcscmu

Extract CVSS v3 scores from Trivy vulnerability JSON with source priority (NVD > GHSA > RedHat) and fallback to N/A.

379 tokens
Run2 Trivy Offline Scanning
by cxcscmu

Use Trivy vulnerability scanner in offline mode to scan dependency lock files and produce JSON vulnerability reports without internet access.

768 tokens
Run2 Vulnerability CSV Reporting
by cxcscmu

Generate structured CSV security audit reports from Trivy JSON output with severity filtering, deduplication, and proper field mapping.

880 tokens
Run2 Earthquake Analysis
by cxcscmu

Parse USGS GeoJSON earthquake data into GeoPandas GeoDataFrame and output structured JSON results for geospatial analysis.

762 tokens
Run2 Geopandas Plate Tectonics
by cxcscmu

Load and work with PB2002 tectonic plate boundary data using GeoPandas for spatial filtering and distance calculations, with antimeridian awareness.

844 tokens
Run2 Competitor Analysis
by cxcscmu

Finding competitor product discussions, insights, and demo URLs across all ContentForce-related Slack channels

644 tokens
Run2 Enterprise Data Retrieval
by cxcscmu

Complete guide to retrieving structured answers from enterprise product JSON data files containing Slack, documents, meetings, and PRs

808 tokens
Run2 13f Fund Analysis
by cxcscmu

Analyze fund AUM, holdings count, and cross-quarter investment changes from SEC 13F filings.

537 tokens
Run2 Fuzzy Fund Search
by cxcscmu

Fuzzy search for hedge funds or stocks by name in SEC 13F filings; handles cases where rank 1 is skipped due to amendment filtering.

448 tokens
Run2 Holdings Comparison
by cxcscmu

Complete workflow for finding top stock increases/decreases between Q2 and Q3 for a specific fund.

361 tokens
Run2 Palantir Holders
by cxcscmu

Find top fund managers holding a specific stock (by CUSIP) using a fixed version of the holding_analysis workflow.

452 tokens
Run2 Druid Cve 2021 25646
by cxcscmu

Complete guide to patching Apache Druid CVE-2021-25646 - JavaScript RCE via Jackson @JacksonInject bypass with empty JSON key

837 tokens
Run2 Jackson Inject Bypass
by cxcscmu

Security guide for Jackson @JacksonInject vulnerabilities - how attackers override injectable values via JSON and how to prevent it

712 tokens
Run2 Gh Issue Analysis
by cxcscmu

How to identify bug report issues and count resolved bugs in a date range from GitHub Search API results.

461 tokens
Run2 Gh Pr Analysis
by cxcscmu

How to compute PR statistics (merged, closed, avg_merge_days, top_contributor) from GitHub Search API items using Python.

521 tokens
Run2 Gh Search API
by cxcscmu

How to query the GitHub Search API for PRs and issues with date filtering, handling pagination and unauthenticated access via Python urllib.

667 tokens
Run2 Report Builder
by cxcscmu

How to assemble and write a structured JSON report for GitHub community pulse statistics with validation.

522 tokens
Run2 Nlp Paper Reproduction
by cxcscmu

Complete setup guide for reproducing NLP paper results with HuggingFace TRL/transformers on Python 3.12 - use when setting up environments for preference optimization experiments.

728 tokens
Run2 Simpo Loss
by cxcscmu

Complete implementation of the SimPO (NeurIPS 2024) loss function with all variants and edge cases - use when reproducing SimPO or implementing reference-free preference optimization.

835 tokens
Run2 DOCX Conditional Sections
by cxcscmu

Handle {{IF_X}}...{{END_IF_X}} conditional blocks in Word .docx templates — keep or remove content, with correct ordering relative to placeholder replacement.

2k tokens
Run2 Python DOCX Placeholders
by cxcscmu

Replace {{PLACEHOLDER}} tokens in Word .docx templates using python-docx, correctly handling split runs, nested tables, headers/footers, and verification.

1k tokens
Run2 File Classification Improved
by cxcscmu

Improved keyword-based document classification with false-positive prevention, manual review of zero-score files, and post-classification verification.

1k tokens
Run2 PDF Text Extraction
by cxcscmu

Extract text from PDF files using PyPDF2 with pdfplumber fallback; optimized for title/abstract extraction for classification.

510 tokens
Run2 PPTX DOCX Reading
by cxcscmu

Extract text from PPTX and DOCX files using python-pptx and python-docx, including tables and all shapes.

535 tokens
Run2 Circe JSON
by cxcscmu

Using Circe for JSON tokenization and dot-path navigation in Scala, with the exact APIs needed to replace Python's json module and dict traversal.

918 tokens
Run2 Scala Builder
by cxcscmu

Implementing an immutable fluent builder in Scala with companion object apply, varargs metadata, and a build() method returning a function — translating Python's mutable builder class.

1k tokens
Run2 Scala Sealed Traits
by cxcscmu

Translating Python Enum and frozen dataclass to idiomatic Scala sealed ADTs and case classes, with precise metadata typing and withMetadata pattern.

924 tokens
Run2 Scala Type Classes
by cxcscmu

Translating Python Protocol, ABC, and isinstance dispatch to Scala traits, overloaded methods, and functor/monad abstractions.

1k tokens
Run2 Scala Variance
by cxcscmu

Translating Python TypeVar covariant/contravariant generics to Scala variance annotations, with concrete patterns for containers, sinks, and handlers.

918 tokens
Run2 Meeting Scheduler With Output
by cxcscmu

Schedule multiple meeting requests into a calendar with earliest-first logic, then generate formatted reply .txt files and a results.json summary.

843 tokens
Run2 PDF Calendar Parsing
by cxcscmu

Precisely parse a PDF day-view calendar to extract event times, durations, and colors by reading visual block positions and the 15-minute grid.

570 tokens
Run2 Timezone Dst
by cxcscmu

Convert US time zones to the calendar's local timezone, correctly handling Daylight Saving Time for dates in March through November.

444 tokens
Run2 D3 Bubble Chart
by cxcscmu

Creating D3.js v6 bubble charts with market cap sizing (scaleSqrt), sector coloring, inside ticker labels, and ETF uniform sizing — with correct tooltip suppression for ETFs.

807 tokens
Run2 D3 Force Cluster
by cxcscmu

D3.js v6 force simulation for clustered bubbles by category using forceX/forceY anchors, forceCollide for no overlap, with truly deterministic initial positions.

818 tokens
Run2 D3 Interactive Table
by cxcscmu

Building a scrollable D3.js HTML table linked to a bubble chart with bidirectional click-highlight, correct scrollIntoView for overflow containers, and sector color badges.

835 tokens
Run2 Glm Calibration
by cxcscmu

How to run and calibrate GLM3 for lake temperature simulation - includes correct parameter effects, grid search strategy, and verified working parameter ranges.

626 tokens
Run2 Glm Netcdf Analysis
by cxcscmu

How to read GLM3 NetCDF output (shape/dimension details verified) and extract simulated temperature profiles matched to field observations.

680 tokens
Run2 Glm Rmse Metrics
by cxcscmu

Exact RMSE metric computation for GLM lake temperature evaluation - verified matching procedure with correct threshold values.

809 tokens
Run2 Itinerary Data Exploration
by cxcscmu

Explore and query travel dataset files (CSV/TXT) to find cities, restaurants, accommodations, attractions, and driving distances — with precise filtering patterns and data field notes.

742 tokens
Run2 Itinerary Planning
by cxcscmu

Build a multi-city road-trip travel itinerary from dataset files with complete budget tracking, pet-friendly constraints, cuisine coverage, and correct JSON output format.

949 tokens
Run2 Ffmpeg Keyframes
by cxcscmu

Extract I-frame keyframes from video files using FFmpeg CLI, saving as zero-padded PNG sequences starting at 001.

276 tokens
Run2 Image Grayscale
by cxcscmu

Convert PNG images to grayscale inplace using ImageMagick; covers both keyframes and template images for consistent matching.

273 tokens
Run2 Object Counting
by cxcscmu

Count template objects in keyframes using count_objects.py; parse integer from output string and generate a CSV with results per frame.

454 tokens
Run2 Excel Index Match
by cxcscmu

Use INDEX&MATCH with two conditions (series code + year) to populate data tables in Excel from a source sheet, with proper anchoring for copyable formulas.

598 tokens
Run2 Excel Sumproduct
by cxcscmu

Calculate GDP-weighted mean of net exports as % of GDP using SUMPRODUCT in Excel, including all supporting statistics (min, max, median, percentiles).

702 tokens
Run2 Openpyxl Editing
by cxcscmu

Safely insert Excel formulas into specific cells using openpyxl without altering formatting, colors, or structure of existing workbooks.

646 tokens
Run2 Advanced Technical Pillow
by cxcscmu

A skill for advanced technical illustration with Pillow, including complex hardware shapes, cooling fins, and annotation shelf-lines.

394 tokens
Run2 Anthropic Brand Identity
by cxcscmu

A skill for managing and applying Anthropic's specific brand identity, including color tokens, typography fallbacks, and technical illustration standards.

352 tokens
Run2 Classical Poetry Mastery
by cxcscmu

Detailed rules for seven-character regulated verse (七言律诗), including the "Sticky" (黏) and "Opposing" (对) rules.

346 tokens
Run2 Literary Emotive Writing
by cxcscmu

Advanced vocabulary and poetic devices for expressing suffering, war, and the hope for peace from an ordinary person's perspective.

266 tokens
Run2 Mandarin Rhyme Comprehensive
by cxcscmu

Comprehensive rhyme groups for modern Mandarin (新韵), ensuring consistent rhyming throughout the poem.

236 tokens
Run2 PDF Field Mapping
by cxcscmu

Techniques for mapping case descriptions to PDF form fields.

188 tokens
Run2 PDF Form Filling Advanced
by cxcscmu

Advanced techniques for filling PDF forms with fillable fields.

183 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.