All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 302,729
- 12,614
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse ai & agents skills
Showing 961–984 of 302,729 skills
- 2471 Migration Guide 8870fb19> This guide maps every concept from the Agentforce Builder UI (Setup > Agents) to its Agent Script DSL equivalent. Use it when converting existing agents from the visual builder to code. ---Votes: 0GitHub stars: 9
- 2471 Designagent B9e009a9Step 3 - Design Artifacts. Generates architecture diagrams and Architecture Decision Records (ADRs) for Azure infrastructure. Uses azure-diagrams skill for visual documentation and azure-adr skill for formal decision records. Optional step - users can skip to Implementation Planning.Votes: 0GitHub stars: 9
- 2470 Function Calling C7d3f383<Tip> Function Calling allows AI models to call external functions and APIs, greatly expanding the capability boundaries of intelligent agents, enabling them to perform specific operations and obtain real-time data. </Tip>Votes: 0GitHub stars: 9
- 2470 Function Calling 5feec9abschedule_meeting_function = { "name": "schedule_meeting", "description": "Schedules a meeting with specified attendees at a given time and date.", "parameters": { "type": "object", "properties": { "attendees": { "type": "array", "items": {"type": "string"}, "description": "List of people attending the meeting.", }, "date": { "type": "string", "description": "Date of the meeting (e.g., '2024-07-29')", }, "time": { "type": "string", "description": "Time of the meeting (e.g., '15:00')", }, "topi...Votes: 0GitHub stars: 9
- 2470 Function Calling 3bb0b907tools = [ { "type": "function", "name": "get_horoscope", "description": "Get today's horoscope for an astrological sign.", "parameters": { "type": "object", "properties": { "sign": { "type": "string", "description": "An astrological sign like Taurus or Aquarius", }, }, "required": ["sign"], }, }, ] def get_horoscope(sign): return f"{sign}: Next Tuesday you will befriend a baby otter." input_list = [ {"role": "user", "content": "What is my horoscope? I am an Aquarius."} ] response = client.res...Votes: 0GitHub stars: 9
- 2469 Reasoning Content 59834855:::info Requires LiteLLM v1.63.0+ ::: Supported Providers: - Deepseek (`deepseek/`) - Anthropic API (`anthropic/`) - Bedrock (Anthropic + Deepseek + GPT-OSS) (`bedrock/`) - Vertex AI (Anthropic) (`vertexai/`) - OpenRouter (`openrouter/`) - XAI (`xai/`) - Google AI Studio (`google/`) - Vertex AI (`vertex_ai/`) - Perplexity (`perplexity/`) - Mistral AI (Magistral models) (`mistral/`) - Groq (`groq/`) LiteLLM will standardize the `reasoning_content` in the response and `thinking_blocks` in the a...Votes: 0GitHub stars: 9
- 2468 Tool Use Overview Deab414f--- Claude is capable of interacting with tools and functions, allowing you to extend Claude's capabilities to perform a wider variety of tasks. <Tip> Learn everything you need to master tool use with Claude as part of our new [courses](https://anthropic.skilljar.com/)! Please continue to share your ideas and suggestions using this [form](https://forms.gle/BFnYc6iCkWoRzFgk7). </Tip> <Tip> **Guarantee schema conformance with strict tool use** [Structured Outputs](/docs/en/build-with-claude/str...Votes: 0GitHub stars: 9
- 2467 Heavy Df9a52caRemember the following: - Use the GitHub CLI (`gh`) for all GitHub-related tasks - Search the codebase for relevant files - Ensure code passes linting and type checking after doing any work - Use cpp-pro, python-pro, emacs-lisp-pro, rust-pro or haskell-pro as needed for diagnosing and analyzing PRs, fixing code, and writing any new code. - If this worktree is anywhere under the "positron" or "pos" directories, then use pal to confer with gemini-3-pro-preview and gpt-5.3-codex to reach consens...Votes: 0GitHub stars: 9
- 2466 Heavy 2e20d963Remember the following: - Use the claude-code skill to provide context for the rest of the task - Use beads to keep track of tasks you notice you work, and then complete those tasks in order to fully complete the initial task - Use the GitHub CLI (`gh`) for all GitHub-related tasks - Search the codebase for relevant files - Ensure code passes linting and type checking after doing any work - Use cpp-pro, python-pro, emacs-lisp-pro, rust-pro or haskell-pro as needed for diagnosing and analyzing...Votes: 0GitHub stars: 9
- 2465 Arch 780fe763> Generated for developer orientation. Reduces repeated archaeology sessions.Votes: 0GitHub stars: 9
- 2464 Quickstartpython A18edb06Z.AI provides interfaces compatible with OpenAI API, which means you can use existing OpenAI SDK code and seamlessly switch to Z.AI's model services by simply modifying the API key and base URL. This compatibility allows you to: * Quickly migrate existing OpenAI applications * Use familiar development patterns and tools * Enjoy the powerful capabilities of Z.AI models * Maintain code consistency and maintainability <Warning> In some scenarios, there are still differences between Z.AI and Open...Votes: 0GitHub stars: 9
- 2463 Arch 21db9a08> Generated for developer orientation. Reduces repeated archaeology sessions.Votes: 0GitHub stars: 9
- 2461 Audit 256f139fAudit Namshub installation — show hooks, skills, permissions, data storage, and security postureVotes: 0GitHub stars: 9
- 2460 Multi Tenant Design 4fdd0f01OpenViking 已定义了 `UserIdentifier(account_id, user_id, agent_id)` 三元组（PR #120），但多租户隔离尚未实施。当前状态：Votes: 0GitHub stars: 9
- 2456 Expose Skill A1c1f744> Expose agent skills as MCP resources Agent skills are directories containing instructions and supporting files that teach an AI assistant how to perform specific tasks. Tools like Claude Code, Cursor, and VS Code Copilot each have their own skills directories where users can add custom capabilities. The Skills Provider exposes these skill directories as MCP resources, making skills discoverable and shareable across different AI tools and clients.Votes: 0GitHub stars: 9
- 2456 Agent Sdk Custom Tools Fc89c16bCustom tools allow you to extend Claude Code's capabilities with your own functionality through in-process MCP servers, enabling Claude to interact with external services, APIs, or perform specialized operations.Votes: 0GitHub stars: 9
- 2455 Agent Sdk Cost Tracking A74087bfThe Claude Agent SDK provides detailed token usage information for each interaction with Claude. This guide explains how to properly track costs and understand usage reporting, especially when dealing with parallel tool uses and multi-step conversations. For complete API documentation, see the [TypeScript SDK reference](https://platform.claude.com/docs/en/agent-sdk/typescript).Votes: 0GitHub stars: 9
- 2452 Sampling 5b367a3a> Request LLM text generation from the client or a configured provider through the MCP context. LLM sampling allows your MCP tools to request text generation from an LLM during execution. This enables tools to leverage AI capabilities for analysis, generation, reasoning, and more—without the client needing to orchestrate multiple calls. By default, sampling requests are routed to the client's LLM. You can also configure a fallback handler to use a specific provider (like OpenAI) when the clie...Votes: 0GitHub stars: 9
- 2448 Agentic Retrieval Guide Ca6feca4Agentic retrieval is an LLM-guided multi-round retrieval method that significantly improves retrieval quality for complex queries through intelligent judgment and query optimization.Votes: 0GitHub stars: 9
- 2442 Prompt Injection Patterns Fe043847Patterns to detect when scanning agent skills for prompt injection attacks.Votes: 0GitHub stars: 9
- 2440 Provider Configuration 2591aec0Guide to configuring API keys and credentials for various LLM providers.Votes: 0GitHub stars: 9
- 2427 Bedrock Eb9102a9Pass-through endpoints for Bedrock - call provider-specific endpoint, in native format (no translation). | Feature | Supported | Notes | |-------|-------|-------| | Cost Tracking | ✅ | For `/invoke` and `/converse` endpoints | | Load Balancing | ✅ | You can load balance `/invoke`, `/converse` routes across multiple deployments| Logging | ✅ | works across all integrations | | End-user Tracking | ❌ | [Tell us if you need this](https://github.com/BerriAI/litellm/issues/new) | | Streaming | ✅ | |...Votes: 0GitHub stars: 9
- 2427 Bedrock 98618766ALL Bedrock models (Anthropic, Meta, Deepseek, Mistral, Amazon, etc.) are Supported | Property | Details | |-------|-------| | Description | Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs). | | Provider Route on LiteLLM | `bedrock/`, [`bedrock/converse/`](#set-converse--invoke-route), [`bedrock/invoke/`](#set-invoke-route), [`bedrock/converse_like/`](#calling-via-internal-proxy), [`bedrock/llama/`](#deepseek-not-r1), [`bedrock/deepseek...Votes: 0GitHub stars: 9
- 2413 Config 5257307cConfiguration classes for cascadeflow models and cascade behavior.Votes: 0GitHub stars: 9