analyze-project
Low Risk 78Analyze Deep Learning Projects Safely
by lllllllama
Understanding a new deep learning repository is time-consuming and error-prone. This skill provides read-only static analysis to map model structure, training entrypoints, and suspicious patterns without modifying code or running expensive training jobs.
full-output-enforcement
Safe 70Enforce Complete, Unabridged Output Every Time
by leonxlnx
LLMs often truncate or summarize code instead of delivering complete files. This skill enforces exhaustive output by banning placeholder patterns and managing token-limit splits cleanly.
frontend-code-review
Safe 74Review Frontend Code
by langgenius
Frontend code reviews help developers catch bugs and anti-patterns before deployment. This skill provides automated checklist-based reviews for TypeScript, JavaScript, TSX, and JSX files using industry best practices.
component-refactoring
Safe 72Refactor Complex React Components
by langgenius
Complex React components become hard to test and maintain. This skill provides patterns and workflows to refactor high-complexity components by extracting hooks, splitting sub-components, and applying Dify-specific conventions.
langchain-architecture
Safe 71Build LLM Applications with LangChain Framework
by sickn33
Building production-grade LLM applications requires understanding complex architectural patterns. This skill provides proven LangChain patterns for agents, chains, memory management, and tool integration.
skill-creator
Low Risk 70Create effective AI skills with templates
by langchain-ai
Creating AI skills from scratch requires understanding structure, best practices, and validation. This skill provides step-by-step guidance and automated tools to build, scaffold, and validate skills for any domain or workflow.
caveman-review
Safe 70Review code with compressed one-line comments
by juliusbrussee
Code review feedback is often verbose and repetitive, burying actionable items in polite filler. This skill formats each review finding as a single line with exact location, problem, and fix.
cavecrew
Safe 68Delegate tasks to caveman subagents
by juliusbrussee
Long coding sessions exhaust context window when verbose subagent outputs pile up. Cavecrew provides a decision framework for delegating to specialized caveman-style subagents that return compressed output, extending context lifespan by 60% across many delegations.
react-flow-best-practices
Safe 73Review and Improve React Flow Canvases with Best Practices
by JohnWayneeee
Building correct, performant React Flow v12 canvases requires deep knowledge of custom nodes, handles, edges, and viewport management. This skill provides version-specific best practices and a structured review workflow to help developers avoid common pitfalls and produce production-ready workflow UIs.
casely
Safe 81Generate test cases from documentation automatically
by JohnWayneeee
Casely eliminates 40% of QA engineering time by converting requirement documents into structured test cases. It learns your team's writing style from examples and exports TestRail-ready Excel files.
browser-audit
Low Risk 69Audit web pages for accessibility, SEO, and quality before deployment
by JohnWayneeee
Web developers need to verify accessibility, SEO, and quality before deploying updates. This skill performs a structured browser audit covering WCAG 2.2 AA compliance, Lighthouse checks, keyboard navigation, and critical UX issues.
tests-maintenance
Safe 70Review and maintain test suite quality
by JetBrains
Test suites accumulate technical debt over time. Disabled tests lose context, Neovim exclusions lack documentation, and test content becomes meaningless. This skill helps maintainers systematically review disabled tests, document exclusion reasons, and improve test readability.
laravel-specialist
Safe 70Build Laravel 10+ Applications with AI
by jeffallan
Get expert Laravel development assistance for Eloquent ORM, REST APIs, queue systems, and Livewire components. The skill provides senior-level guidance for building scalable PHP applications.
flutter-expert
Safe 72Build cross-platform Flutter apps
by jeffallan
Building mobile applications across iOS, Android, and web requires deep expertise in Flutter, state management, and platform-specific implementations. This skill provides comprehensive guidance for Flutter 3+ development with Riverpod, Bloc, and GoRouter patterns.
agent-tools
Safe 71Access 150+ AI Models from Your Terminal
by inf-sh
This skill provides access to the inference.sh CLI platform, which lets you run over 150 AI applications without requiring local GPU resources. Generate images with FLUX, create videos with Veo, query LLMs like Claude and Gemini, perform web searches, and automate Twitter posts through simple bash commands.
python-sdk
Low Risk 69Build AI-powered Python applications with inference.sh
by inferen-sh
Integrate 150+ AI models into your Python applications with a unified SDK. Build agents, run inference, and automate workflows with sync, async, and streaming support.
python-executor
Medium Risk 61Execute Python code in a sandboxed environment
by inferen-sh
Running Python code locally requires setting up environments and managing dependencies. This skill provides instant access to a pre-configured Python environment with 100+ libraries ready to use.
javascript-sdk
Medium Risk 59Build AI Agents with the JavaScript SDK
by inferen-sh
Integrate 150+ AI models into JavaScript/TypeScript applications with a unified SDK. Build agents, handle streaming responses, manage file uploads, and implement human approval workflows with full type safety.
chat-ui
Safe 69Build React Chat Interfaces with Prebuilt Components
by inferen-sh
Creating chat UIs from scratch requires significant time and design effort. This skill provides ready-to-use React components with shadcn/ui styling for rapid chat interface development.
remotion-render
Medium Risk 64Render Videos from React Code Using inference.sh
by inference-sh-skills
Creating MP4 videos from React components requires complex rendering infrastructure that is difficult to set up locally. This skill sends your Remotion TSX code to the inference.sh cloud API and returns a ready-to-use MP4 video file with configurable resolution, FPS, and duration.