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. 80 149 files from 1 774 authors, of which 62 489 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.

62 489
unique skills
out of 80 149 files found on GitHub
17 660
are copies
same content, someone else's repository
1 741
tokens, median
what a typical skill costs you in context
7 984
name collisions
two skills with one name cannot sit side by side

32 101–32 160 of 62 489

page 536 of 1 042
FastAPI Testing Patterns
by PramodDutta

FastAPI application testing with TestClient, dependency injection overrides, async testing, database testing with SQLAlchemy, and OpenAPI validation.

984 tokens
Feature Flag Testing
by PramodDutta

Testing feature flag implementations including flag evaluation, gradual rollout verification, fallback behavior, and flag cleanup detection.

1k tokens
First Time User Tester
by PramodDutta

Validate the first-time user experience including onboarding flows, empty states, tutorial completion, progressive disclosure, and initial setup wizards

10k tokens
File Upload Testing
by PramodDutta

Comprehensive file upload testing including format validation, size limits, malware scanning, storage verification, and concurrent upload handling.

1k tokens
Flaky Test Doctor
by PramodDutta

Diagnose flaky test failures from Playwright reports, traces, and rerun history. Classify each failure as product, test, environment, data, or unknown with cited evidence and a proposed fix. Never auto-modifies code without opt-in.

3k tokens
Flaky Test Quarantine
by PramodDutta

Detect, quarantine, and systematically fix flaky tests with automated retry analysis, root cause categorization, and CI pipeline integration for test reliability

9k tokens
Gatling Performance Testing
by PramodDutta

High-performance load testing using Gatling with Scala/Java DSL for simulating thousands of concurrent users and analyzing response time distributions.

986 tokens
Form Validation Breaker
by PramodDutta

Exhaustive testing of form validation logic including boundary values, injection payloads, encoding edge cases, and client-server validation bypass techniques

10k tokens
Flutter Testing Patterns
by PramodDutta

Flutter app testing with widget tests, integration tests, golden tests, Mockito, bloc testing, and Flutter Driver for end-to-end scenarios.

974 tokens
Flask Testing Patterns
by PramodDutta

Flask application testing with test client, fixture patterns, SQLAlchemy model testing, blueprint testing, and Flask-specific extension testing.

975 tokens
Frontend Performance Testing
by PramodDutta

Frontend performance testing covering bundle size analysis, render performance, animation frame rate, React re-render detection, and lazy loading verification.

999 tokens
Gauge Testing
by PramodDutta

Test automation with Gauge framework using Markdown specifications, step implementations in Java/Python/JavaScript/Ruby/C#, concepts, data-driven testing, and living documentation.

5k tokens
GDPR Compliance Testing
by PramodDutta

Testing GDPR compliance requirements including data deletion, consent management, data portability, right to erasure, and privacy policy enforcement.

983 tokens
Geb Testing
by PramodDutta

Browser automation testing with Geb framework for Groovy/JVM using jQuery-like content DSL, Page Object pattern, Spock integration, and WebDriver abstraction.

4k tokens
GitHub Actions CI Testing
by PramodDutta

Setting up and optimizing test pipelines in GitHub Actions with caching, parallel execution, matrix builds, and test result reporting.

1k tokens
GitHub CI Fix Debugging
by PramodDutta

Debug and fix failing GitHub PR checks by inspecting GitHub Actions logs, summarizing failure context, drafting fix plans, and implementing fixes after approval.

708 tokens
Go Testing Patterns
by PramodDutta

Go testing with testing package, table-driven tests, subtests, benchmarks, test fixtures, httptest, and testify assertions.

951 tokens
Golden File Testing
by PramodDutta

Golden file testing pattern for comparing output against approved baselines with update workflows, diff tools, and version control integration.

994 tokens
GraphQL Subscription Testing
by PramodDutta

Testing GraphQL subscriptions including WebSocket lifecycle, real-time event delivery, authorization on subscriptions, and connection management.

993 tokens
gRPC Testing
by PramodDutta

gRPC service testing including protobuf validation, streaming tests, error handling, deadline testing, and load testing for gRPC endpoints.

963 tokens
GraphQL Testing
by PramodDutta

Comprehensive GraphQL API testing including query/mutation testing, schema validation, resolver testing, subscription testing, and N+1 query detection.

986 tokens
HIPAA Compliance Testing
by PramodDutta

Testing HIPAA compliance for healthcare applications including PHI handling, audit logging, access controls, and data encryption verification.

982 tokens
Internationalization Testing
by PramodDutta

i18n testing covering locale switching, date/number formatting, RTL layout, plural forms, ICU messages, and translation completeness verification.

983 tokens
Image Processing Testing
by PramodDutta

Testing image processing pipelines including format conversion, resize quality, metadata handling, watermark verification, and thumbnail generation.

978 tokens
Integration Testing Patterns
by PramodDutta

Integration testing strategies including database integration, external service integration, message queue testing, and test container patterns.

1k tokens
IoT Device Testing
by PramodDutta

IoT device testing including firmware validation, protocol testing (MQTT, CoAP), power consumption testing, and over-the-air update verification.

962 tokens
Infrastructure Drift Detection
by PramodDutta

Detecting and testing infrastructure drift between desired state and actual state using automated scanning, alerting, and remediation patterns.

983 tokens
Jasmine Testing
by PramodDutta

BDD-style JavaScript testing with Jasmine covering spies, async patterns, custom matchers, clock manipulation, and comprehensive test organization for frontend and Node.js applications.

4k tokens
JavaScript Testing Patterns
by PramodDutta

Modern JavaScript testing strategies with Jest, Mocha, and testing best practices covering unit testing, integration testing, mocking, async patterns, and DOM testing.

4k tokens
ISTQB Test Design Techniques
by PramodDutta

Apply classic test design techniques the ISTQB way, equivalence partitioning, boundary value analysis, decision tables, state transition testing, and pairwise combinations, to derive minimal high-coverage test sets from requirements.

2k tokens
Jest Mocking Patterns
by PramodDutta

Teaches the agent the right way to mock in Jest — jest.fn, mockImplementation, mockResolvedValue, jest.mock factories, spyOn with restore, and isolating modules like axios.

2k tokens
Jira QA Workflows
by PramodDutta

Run QA work in Jira like a professional, bug lifecycle and triage, JQL queries for testers, quality dashboards, sprint QA rituals, and REST API automation for bulk bug operations and reporting.

2k tokens
Jest Unit Testing
by PramodDutta

Unit testing skill using Jest for TypeScript and JavaScript, covering mocking, spies, snapshots, coverage, async testing, and custom matchers.

4k tokens
JMeter Load Testing
by PramodDutta

Load and performance testing skill using Apache JMeter, covering test plans, thread groups, assertions, listeners, timers, and distributed testing.

3k tokens
JUnit 5 Testing
by PramodDutta

Production-grade Java unit and integration testing with JUnit 5 covering assertions, parameterized tests, lifecycle hooks, Mockito mocking, nested tests, and extensions.

4k tokens
JWT Security Testing
by PramodDutta

Comprehensive JWT token security testing including signature verification, expiration checks, algorithm confusion attacks, and claim validation.

976 tokens
Kafka Event Driven Testing
by PramodDutta

Test Kafka-based event-driven systems, producer and consumer integration tests with Testcontainers, schema compatibility gates, idempotency and ordering verification, dead-letter handling, and end-to-end event flow assertions.

2k tokens
k6 Performance Testing
by PramodDutta

Performance and load testing skill using k6, covering load test scripts, thresholds, scenarios, checks, custom metrics, and results analysis.

3k tokens
Karma Testing
by PramodDutta

Comprehensive Karma test runner skill for browser-based JavaScript unit testing with Jasmine, Mocha, or QUnit frameworks, real browser execution, coverage reporting, and CI/CD pipeline integration.

5k tokens
Kotlin Testing Patterns
by PramodDutta

Kotlin testing with JUnit 5, MockK, Kotest, coroutine testing, Android testing with Espresso, and Kotlin-specific assertion libraries.

975 tokens
Katalon Studio Testing
by PramodDutta

Comprehensive testing patterns for Katalon Studio including codeless record-and-playback, Groovy scripted testing, custom keywords, data-driven testing, cross-browser execution, and CI/CD integration with Katalon TestOps.

5k tokens
Kubernetes Testing Patterns
by PramodDutta

Kubernetes deployment testing including manifest validation, Helm chart testing, pod health checks, network policy testing, and rollback verification.

1k tokens
Langfuse LLM Observability Testing
by PramodDutta

Instrument LLM apps with Langfuse tracing, then use traces, scores, and datasets to test in production, run evaluations on real traffic, catch regressions, and close the loop from incident to golden dataset.

2k tokens
Laravel Dusk Testing
by PramodDutta

Expert-level Laravel Dusk browser testing skill for PHP/Laravel applications. Covers Chrome-based E2E testing, browser assertions, Page Objects, component testing, authentication helpers, and database integration.

4k tokens
Laravel Testing Patterns
by PramodDutta

Laravel PHP testing with PHPUnit, feature tests, browser tests with Dusk, database factories, mocking facades, and HTTP testing helpers.

978 tokens
Lettuce BDD Testing
by PramodDutta

Expert-level Lettuce BDD testing skill for Python applications. Covers Gherkin feature files, step definitions, terrain hooks, Selenium integration, data-driven scenarios, and migration guidance to Behave for modern projects.

4k tokens
LibFuzzer Coverage Guided Fuzzing
by PramodDutta

Coverage-guided fuzz testing using libFuzzer for C/C++ applications to find memory corruption, buffer overflows, and crash-inducing inputs.

984 tokens
License Compliance Testing
by PramodDutta

Automated open-source license compliance testing to detect license conflicts, copyleft violations, and license compatibility issues in dependencies.

987 tokens
Lighthouse Performance Audit
by PramodDutta

Automated web performance auditing using Google Lighthouse for Core Web Vitals, accessibility, SEO, and best practices scoring with CI integration.

1k tokens
LLM Output Testing
by PramodDutta

Testing LLM-powered features including output quality validation, hallucination detection, token usage monitoring, and prompt regression testing.

964 tokens
Load Balancer Testing
by PramodDutta

Testing load balancer configurations including health check validation, routing algorithms, session affinity, failover behavior, and SSL termination.

1k tokens
LLM Security Testing
by PramodDutta

Security testing for LLM-powered applications including prompt injection, jailbreak detection, data leakage prevention, and AI safety testing.

965 tokens
Loading State Tester
by PramodDutta

Verify loading indicators, skeleton screens, and progress bars appear correctly during async operations and disappear on completion or error.

10k tokens
Localization Bug Finder
by PramodDutta

Detect localization and internationalization defects including untranslated strings, text expansion overflow, RTL layout issues, and locale-specific formatting errors

9k tokens
Locust Load Testing
by PramodDutta

Python-based load testing with Locust for writing user behavior scripts, distributed testing, real-time web UI monitoring, and custom load shapes.

974 tokens
Log Testing Patterns
by PramodDutta

Testing logging implementations including log level verification, structured logging validation, log rotation testing, and log aggregation pipeline testing.

989 tokens
Maestro Mobile Testing
by PramodDutta

Black-box mobile UI testing with Maestro YAML flows - launchApp, tapOn, inputText, assertVisible, reusable runFlow subflows, environment parameters, JUnit reporting, and emulator-based CI pipelines.

2k tokens
Mabl AI Testing
by PramodDutta

AI-powered testing patterns with Mabl including auto-healing tests, visual regression, API testing, performance monitoring, CI/CD integration, and intelligent test maintenance using Mabl's machine learning capabilities.

5k tokens
MCP Server Testing
by PramodDutta

Comprehensive testing patterns for Model Context Protocol servers including tool validation, transport testing, schema verification, and end-to-end MCP integration testing with stdio and SSE transports.

9k tokens
Memory Leak Detector
by PramodDutta

Identify and diagnose memory leaks in web applications using heap snapshots, allocation timelines, and automated leak detection patterns.

8k 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: 11 696 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 80 149 files found on GitHub, 62 489 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: 7 984 skills here share a name with another skill, and two of them cannot sit side by side.