All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 304,347
- 12,682
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 1,465–1,488 of 304,347 skills
- 2865 Agent Sdk Skills A3151c07options = ClaudeAgentOptions( allowed_tools=["Skill"] ) options = ClaudeAgentOptions( setting_sources=["user", "project"], # Required to load Skills allowed_tools=["Skill"] ) For more details on `settingSources`/`setting_sources`, see the [TypeScript SDK reference](https://platform.claude.com/docs/en/agent-sdk/typescript#settingsource) or [Python SDK reference](https://platform.claude.com/docs/en/agent-sdk/python#settingsource). **Check working directory**: The SDK loads Skills relative to t...Votes: 0GitHub stars: 9
- 2861 Quickstartpython F2939f5c<!-- prettier-ignore --> [)](https://pypi.org/project/anthropic/) The Anthropic Python library provides convenient access to the Anthropic REST API from any Python 3.9+ application. It includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients powered by [httpx](https://github.com/encode/httpx).Votes: 0GitHub stars: 9
- 2860 Access Groups 686814b0Access Groups simplify how you define and manage resource access across your organization. Instead of configuring models, MCP servers, and agents separately on each key or team, you create one group that bundles the resources you want to grant, then attach that group to your keys or teams.Votes: 0GitHub stars: 9
- 2851 Python Project Structure C07b2b03Standard directory layouts for LangGraph Python projects.Votes: 0GitHub stars: 9
- 2851 Events Migration Guide A1d86b29This guide documents the migration pattern from span events to OTel log events for LLM instrumentation, following the [OpenTelemetry Gen-AI Semantic Conventions](https://github.com/open-telemetry/semantic-conventions/blob/main/docs/gen-ai/gen-ai-events.md). **Reference Implementation:** OpenAI instrumentation (completed) **Status:** Production-ready pattern for adoption across all providers ---Votes: 0GitHub stars: 9
- 2850 Mcp Server 11b333fcskene-growth provides an [MCP (Model Context Protocol)](https://modelcontextprotocol.io/) server that exposes codebase analysis capabilities to AI assistants like Claude Desktop and Claude Code. The server communicates via stdio and exposes 12 tools organized into tiers by speed and complexity. Tier 1 tools run in under a second with no LLM calls. Tier 2 tools perform LLM-powered analysis with automatic caching. Tier 3 tools combine cached results into final outputs.Votes: 0GitHub stars: 9
- 2849 Llm Setup 0e48d404This page covers the minimum LLM configuration required to run bearlike/Assistant.Votes: 0GitHub stars: 9
- 2848 Core Orchestration 822de604This page summarizes the orchestration loop, core components, and operational features for bearlike/Assistant.Votes: 0GitHub stars: 9
- 2830 Gemini Invocation 8f204a18- Model: `gemini-3-pro-preview` - Extensions: `code-review`, `gemini-cli-security`Votes: 0GitHub stars: 9
- 2829 Codex Invocation 4328260e- Model: `gpt-5.3-codex` - Reasoning effort: `xhigh`Votes: 0GitHub stars: 9
- 2817 Proxy Integration Plan Da078dae- Provide a **single proxy service** that acts as a drop-in replacement for both OpenAI and Anthropic APIs. - Support **OpenAI** `/v1/chat/completions` (route GPT-4o-mini → GPT-4o cascade). - Support **Anthropic** `/v1/messages` (route Haiku → Sonnet cascade). - Preserve client compatibility with official SDKs, LangChain, and Claude Code. - Maintain shared cascade logic, consistent telemetry, and per-provider cost tracking.Votes: 0GitHub stars: 9
- 2805 Reading Material 7 88e80e12You can find all the files for L7 <a href="https://github.com/https-deeplearning-ai/sc-agent-skills-files/tree/main/L7" target="_blank">here</a>, with a few variations from what's shown in the video: - Used `haiku` as the model for each subagent - Specified the exact list of MCP tools to useVotes: 0GitHub stars: 9
- 2795 Tun 1658 Phase6 Messaging Normalization A07396d7Normalized message utilities to operate on tinyagent dict messages (role + content[type]) only. Token estimation and resume sanitization no longer attempt to interpret legacy pydantic-ai message objects, aligning with the “full rip-out” direction.Votes: 0GitHub stars: 9
- 2755 Agent Skills Spec 18c62f91A skill is a folder of instructions, scripts, and resources that agents can discover and load dynamically to perform better at specific tasks. In order for the folder to be recognized as a skill, it must contain a `SKILL.md` file. A minimal skill folder looks like this: ``` my-skill/ - SKILL.md ``` More complex skills can add additional directories and files as needed. The skill's "entrypoint" is the `SKILL.md` file. It is the only file required to exist. The file must start with a YAML front...Votes: 0GitHub stars: 9
- 2737 Event Schema E25a35ef本文档旨在说明 `infiAgent` 项目中经过规范化重构后的事件驱动架构，为二次开发和系统集成提供指导。Votes: 0GitHub stars: 9
- 2721 Forward Client Headers 239e5a02Control which model groups can forward client headers to the underlying LLM provider APIs.Votes: 0GitHub stars: 9
- 2716 07 Retrieval Bdd4868eOpenViking 采用两阶段检索：意图分析 + 层级检索 + Rerank。Votes: 0GitHub stars: 9
- 2714 08 Session 81bc51a0Session manages conversation messages, tracks context usage, and extracts long-term memories.Votes: 0GitHub stars: 9
- 2714 08 Session 8154b9adSession 负责管理对话消息、记录上下文使用、提取长期记忆。Votes: 0GitHub stars: 9
- 2714 08 Session 5a5f7931Session manages conversation messages, tracks context usage, and extracts long-term memories.Votes: 0GitHub stars: 9
- 2713 05 Sessions F591f19e会话用于管理对话状态、跟踪上下文使用情况，并提取长期记忆。Votes: 0GitHub stars: 9
- 2713 05 Sessions E21b9ee2会话用于管理对话状态、跟踪上下文使用情况，并提取长期记忆。Votes: 0GitHub stars: 9
- 2713 05 Sessions B7bf55afSessions manage conversation state, track context usage, and extract long-term memories.Votes: 0GitHub stars: 9
- 2713 05 Sessions 7403180a会话用于管理对话状态、跟踪上下文使用情况，并提取长期记忆。Votes: 0GitHub stars: 9