All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 302,615
- 12,609
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 1,321–1,344 of 302,615 skills
- 1178 Name Skill 10b44fd1Add an MCP server using Dex-safe scope (user by default)Votes: 0GitHub stars: 9
- 1178 Name Skill 04e3c3ecConfigure LLM models and providers for Letta agents and servers. Use when setting model handles, adjusting temperature/tokens, configuring provider-specific settings, setting up BYOK providers, or configuring self-hosted deployments with environment variables.Votes: 0GitHub stars: 9
- 1163 Config Reference 3c5c1195All options for `~/.agent-deck/config.toml`.Votes: 0GitHub stars: 9
- 1097 Troubleshooting A7a910a2This guide covers common issues and their solutions.Votes: 0GitHub stars: 9
- 028 Agents B5618f59This file provides essential guidance for AI coding agents working with the Skill Seekers codebase. ---Votes: 0GitHub stars: 9
- 028 Agents 5421ee8eThis document provides guidance specifically for AI agents working on the strands-agents/private-docs-staging codebase. For human contributor guidelines, see [CONTRIBUTING.md](CONTRIBUTING.md).Votes: 0GitHub stars: 9
- 028 Agents 463e45fcThis file provides essential guidance for AI coding agents working with the Skill Seekers codebase. ---Votes: 0GitHub stars: 9
- 028 Agents 314631aeModule Context: Central registry for all available skills. Referenced by agents during execution.Votes: 0GitHub stars: 9
- 028 Agents 05228376This file provides essential guidance for AI coding agents working with the Skill Seekers codebase. ---Votes: 0GitHub stars: 9
- 979 Skill 8395d2fcGuide for using SLIME (LLM post-training framework for RL Scaling). Use when working with SLIME for reinforcement learning training of language models, including setup, configuration, training execution, multi-turn interactions, custom reward models, tool calling scenarios, or troubleshooting SLIME workflows. Covers GRPO, GSPO, PPO, Reinforce++, multi-agent RL, VLM training, FSDP/Megatron backends, SGLang integration, dynamic sampling, and custom generation functions.Votes: 0GitHub stars: 9
- 979 Skill 2cdb776fTesting strategies for LangChain4j-powered applications. Mock LLM responses, test retrieval chains, and validate AI workflows. Use when testing AI-powered features reliably.Votes: 0GitHub stars: 9
- 910 Research Protocol D219729cThis document defines the research decision and execution flow.Votes: 0GitHub stars: 9
- 818 Readme Ko Ca704477[](https://badge.fury.io/py/memu-py) [](https://opensource.org/licenses/Apache-2.0) [](https://www.python.org/downloads/) [](https://discord.gg/memu) [](https://awesome.re) A flat list view of all resources. Category: **All** | Sorted: by latest release (30 days) ---Votes: 0GitHub stars: 9
- 772 Readme Es 69de1345[](https://badge.fury.io/py/memu-py) [](https://opensource.org/licenses/Apache-2.0) [](https://www.python.org/downloads/) [](https://discord.gg/memu) [服务进行**动态信息收集**与分析。本阶段旨在为后续安全检测、架构评估提供基础数据支撑。 **核心要求:本阶段的信息来源以 MCP server 的 tools 描述为主**(即系统提示词中提供的 `<mcp_tools>` 工具描述块)。你需要从这些工具的**名称、描述、输入/输出形态**中提炼“项目概览信息”,并且避免任何无依据的推测。 任务要求 1. **基于 tools 描述进行信息收集**:阅读 MCP tools 列表与描述,归纳该 MCP 服务的核心能力、业务域、主要数据对象与典型工作流。 2. **推导项目概览(必须可追溯)**:对“项目类型/用途/集成点/暴露面”等结论,必须能对应到具体工具描述(在报告中引用工具名称作为依据)。 3. **最小化动态探测**:如需补充信息,只允许调用**只读、低风险**的探测型工具(例如“list / describe / get / read / status / health / ping”等语义),并记录调用与结果;**严...Votes: 0GitHub stars: 9
- 618 New Project 74688a39When creating a new Colin project, start with `colin init`: ```bash mkdir my-project && cd my-project colin init ``` This creates: - `colin.toml` - Project configuration - `models/` - Directory for source documentsVotes: 0GitHub stars: 9
- 618 New Project 6520356bWhen creating a new Colin project, start with `colin init`: ```bash mkdir my-project && cd my-project colin init ``` This creates: - `colin.toml` - Project configuration - `models/` - Directory for source documentsVotes: 0GitHub stars: 9
- 474 Installation 8bf298f1NextGenUI Agent mono repository offers a variety of options for you to align the agent to your environment needs. We took an approach where core implementation is agnostic to inference provider, [UI rendering plugin](guide/renderer/index.md) and [AI framework](guide/ai_apps_binding/index.md). This way you have full flexibility in picking the right pieces and conveniently using it. If any particular AI framework or UI rendering option is not available out of the box, it's easy to implement it ...Votes: 0GitHub stars: 9
- 148 Client Ba778cc6OpenViking 客户端是所有操作的主入口。Votes: 0GitHub stars: 9
- 1038 Summary F68a6c94The `/skills` slash command in Claude Code was slow and consumed thousands of tokens because it required: 1. Reading multiple SKILL.md files 2. Parsing YAML frontmatter 3. Formatting output 4. All processing done by Claude's LLMVotes: 0GitHub stars: 9
- 028 Agents F6c62914You are an AI assistant running inside the Synth AI TUI with access to the user's working directory and the Synth AI platform.Votes: 0GitHub stars: 9
- 009 Actions Guide 69fe0742Complete guide to implementing actions in Agentforce agents, including Flow, Apex, external API integrations, and advanced patterns.Votes: 0GitHub stars: 9
- 989 Admin Configuration Improvements Fix 6011c0f1**Version:** 0.229.058Votes: 0GitHub stars: 9