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.
Data engineering knowledge reference covering Airflow, Dagster, Kafka Streams, Flink, dbt, and data quality patterns. Use when building data pipelines, ETL workflows, stream processing, or data quality checks.
Processes Word document files (.docx). Creates, edits, annotates, tracks revisions, analyzes OOXML structure, and preserves formatting for contracts, policies, academic papers, and business documents. Use when working with .docx files or Word documents. Do NOT use for PDFs, spreadsheets, presentations, or plain text files.
Multi-agent adversarial-verification orchestration for high-confidence conclusions. Fan-out finders, then verify every finding through a three-prism panel (exploitability / correctness / refutation) that defaults to disbelief, gate fixes behind load-bearing proof tests that catch agents who falsely claim "done/fixed", and roll out behind a build-first exit-code guard. Use when a fan-out task must produce trustworthy results — security audit, code review, research synthesis, migration — and a single agent's self-report cannot be trusted. Composes with securing-systems (what to look for) and shipping-changes (change closed loop); orchestration engine is the Workflow tool.
Processes PDF files. Extracts text and tables, fills forms, merges and splits documents, batch-processes files, converts to images, and generates PDFs programmatically. Use when working with .pdf files. Do NOT use for Word documents, spreadsheets, or presentations.
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.
End-to-end change-shipping closed loop for non-trivial work — research → proposal doc → phased guarded implementation → PR self-review → harden → merge. Use when taking a substantial change from idea to merged PR, when a task needs a written proposal before code, when implementing in reversible phases behind a guarded commit chain (assert + test + verify, all green before commit), or when self-reviewing your own PR. Complements automating-devops (which is the git/CI/release knowledge reference); this skill is the orchestration spine that sequences a change from zero to merged.
云原生与软件供应链安全防御。容器/K8s 加固、Service Mesh、CI/CD 安全、SLSA/SBOM/Sigstore、云 IAM、Secrets 管理、IaC 安全。Use when hardening Kubernetes clusters, auditing CI/CD pipelines, implementing supply chain security, managing cloud IAM, or reviewing IaC code.
Cloud-native infrastructure knowledge reference covering Kubernetes, Helm, Kustomize, Operators, CRDs, GitOps (ArgoCD, Flux), and IaC (Terraform, Pulumi, CDK). Use when provisioning infrastructure, managing clusters, or working with GitOps workflows.
Scans directory structure, detects missing documentation, and verifies code-doc synchronization. Use when checking module completeness, README presence, or DESIGN.md alignment. Automatically triggered after creating new modules.
Security engineering router for penetration testing, code auditing, red/blue/purple team operations, threat intelligence, and vulnerability research. For specialized application security, cloud security, detection engineering, or security architecture, route to dedicated skills (defending-applications, securing-cloud-and-supply-chain, detecting-and-responding, architecting-security).
NestJS best practices and architecture patterns for building production-ready applications. This skill should be used when writing, reviewing, or refactoring NestJS code to ensure proper patterns for modules, dependency injection, security, and performance.
Make AI-powered assertions about screen state
Run TestDriver tests in CI/CD with parallel execution and cross-platform support
Solve captchas using 2captcha service
Execute natural language tasks using AI
Speed up tests with screenshot-based caching
How TestDriver learns your app and caches what it discovers for instant, deterministic replays
Click at specific coordinates or on elements
Deploy TestDriver on your AWS infrastructure using CloudFormation
The fastest way to get started with TestDriver. Just set your API key and start testing.
Configure TestDriver sandbox options and environment settings
Diagnose failing tests with screenshots, replays, and logs
Record test execution with video and logs
Perform a double-click action on an element or at specific coordinates
Initialize and configure the TestDriver SDK client
Locate and interact with UI elements using AI
Launch browsers, desktop apps, and extensions in your TestDriver sandbox
Self-hosted enterprise deployments with assisted setup and dedicated support
Custom error classes and error handling
Listen to SDK lifecycle events with wildcard support
Execute shell or PowerShell commands in the sandbox
Read information from the screen using AI and return it as a string
Bring an application window to the foreground
Locate UI elements using natural language
Generate tests by exploring your app with the AI vision agent
Hover over elements or coordinates
The fastest way to get started with TestDriver. Just set your API key and start testing.
Find UI elements using natural language descriptions
Configure Linux and Windows sandboxes, persist machines between runs, and install custom software
Locate elements and verify app state with AI-powered assertions
Build TestDriver tests iteratively using MCP tools with visual feedback
Execute natural language tasks using AI
Press the mouse button without releasing it
Release the mouse button
Detect all UI elements on screen using OmniParser
Press keyboard keys and shortcuts
Perform actions and handle dynamic, async UI so tests adapt to change
Wait for the screen to stabilize after interactions
Launch browsers, desktop apps, and extensions in your sandbox
Run your first computer-use test in minutes.
Build maintainable test suites with reusable code patterns
Perform a right-click action to open context menus
Run TestDriver tests with Vitest test runner
Capture and manage screenshots during test execution
Capture and save screenshots during test execution
Securely manage passwords and sensitive data in your tests
Scroll pages and elements
Per-test JSON result files with metadata, versions, and infrastructure details
Our enterprise solution with unlimited test execution, assisted setup, and dedicated support.
An expert at creating and refining automated tests using TestDriver.ai
Claude Skills — questions
Answers built from the skills we actually parsed.