SKILL.md files package domain expertise into something any AI agent can use. Drop one into your project and your agent learns how to process PDFs, design interfaces, write tests, or whatever the skill teaches.
1396 skills
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence.
Build real-time chat applications with Azure Communication Services Chat Java SDK. Use when implementing chat threads, messaging, participants, read receipts, typing notifications, or real-time chat features.
Build production React Native apps with Expo, navigation, native modules, offline sync, and cross-platform patterns. Use when developing mobile apps, implementing native integrations, or architecting React Native projects.
Check robots.txt and sitemap.xml for crawl-blocking mistakes. Use when the user says "check my robots.txt", "validate my sitemap", or "is my site crawlable".
22 skills · installable as Plugin
Automate Linear tasks via Rube MCP (Composio): issues, projects, cycles, teams, labels. Always search tools first for current schemas.
+W is a universal "save for later" action for commerce. This MCP server lets AI assistants save any product URL to a user's Wishfinity wishlist with one click. Works with Claude, ChatGPT, Gemini, LangChain, OpenAI Agents SDK, and any MCP-compatible client. When an AI recommends a product, it can offer +W Add to Wishlist. The user clicks the link, and the product is saved to their Wishfinity accoun
Search logs and codebases for error patterns, stack traces, and
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
MCP Server for the GitLab API, enabling project management, file operations, and more. - Automatic Branch Creation: When creating/updating files or pushing changes, branches are automatically created if they don't exist - Comprehensive Error Handling: Clear error messages for common issues - Git History Preservation: Operations maintain proper Git history without force pushing - Batch Operations:
English | 中文 Zero-dependency MCP memory server for AI agents — persistent, searchable, local-first, single binary. - No infra to babysit. Single Go binary. No Docker, no Node.js runtime, no cloud account, no API keys. brew install in 30 seconds. - Memory stays with the project. Stored in .aimemo/ next to your code — commit it to git or add it to .gitignore. Switch branches; memory follows the dire
English | 中文 kom 是一个用于 Kubernetes 操作的工具,相当于SDK级的kubectl、client-go的使用封装。 它提供了一系列功能来管理 Kubernetes 资源,包括创建、更新、删除和获取资源。这个项目支持多种 Kubernetes 资源类型的操作,并能够处理自定义资源定义(CRD)。 通过使用 kom,你可以轻松地进行资源的增删改查和日志获取以及操作POD内文件等动作,甚至可以使用SQL语句来查询、管理k8s资源。 1. 简单易用:kom 提供了丰富的功能,包括创建、更新、删除、获取、列表等,包括对内置资源以及CRD资源的操作。 2. 多集群支持:通过RegisterCluster,你可以轻松地管理多个 Kubernetes 集群,支持AWS EKS集群。 3. MCP支持:支持多集群的MCP管理,同时支持stdio、sse两种模式,内置58种工具,支
Comprehensive guide to implementing RAG systems including vector database selection, chunking strategies, embedding models, and retrieval optimization. Use when building RAG systems, implementing semantic search, optimizing retrieval quality, or debugging RAG performance issues.
Review semantic changes to Codex and Claude Code repository configuration across working trees, staged diffs, and Git ranges.
Claude Code plugins for AWS development with specialized knowledge and MCP server integrations, including CDK, serverless architecture, cost optimization, and Bedrock AgentCore for AI agent deployment. Shared AWS agent skills including AWS Documentation MCP configuration for querying up-to-date AWS knowledge. - AWS MCP server configuration guide - Documentation MCP setup for querying AWS knowledge
A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market
Master modern SQL with cloud-native databases, OLTP/OLAP
A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market
A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market
Download the MCPBundles Hub .mcpb file directly: Download hub.mcpb This .mcpb package contains a pre-configured MCP server proxy that connects to the MCPBundles Hub endpoint. Once installed, your AI assistant can discover and execute tools from all your enabled bundles. MCP Bundles is the simplest way to connect AI assistants to real-world tools. Instead of configuring hundreds of individual MCP s