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 889–912 of 302,729 skills
- 2515 Auto Routing E7ca64fdLiteLLM can auto select the best model for a request based on rules you define. <Image alt="Auto Routing" img={require('../../img/auto_router.png')} style={{ borderRadius: '8px', marginBottom: '1em', maxWidth: '100%' }} />Votes: 0GitHub stars: 9
- 2514 Processors 1f5dbcf0History processors for managing conversation context. These are re-exported from [summarization-pydantic-ai](https://github.com/vstorm-co/summarization-pydantic-ai).Votes: 0GitHub stars: 9
- 2514 Async Client 2881d252Guide for using the Weaviate Python async client in production applications (FastAPI, async frameworks).Votes: 0GitHub stars: 9
- 2514 Adapters Beef3be8Adapters connect EvalView to your AI agent's API. EvalView includes adapters for common patterns and makes it easy to build custom ones.Votes: 0GitHub stars: 9
- 2512 Audit Feffe771Loaded by: `/rwr:audit` command Orchestrator: Claude (reads this workflow and executes steps)Votes: 0GitHub stars: 9
- 2511 Tutorials 64a073b5Intro and tutorial videos made by aider users.Votes: 0GitHub stars: 9
- 2511 Context Optimization Research A8c94eb6Research conducted: 2026-02-24 Sources: docs.anthropic.com (official Claude Code documentation) ---Votes: 0GitHub stars: 9
- 2509 Readme Ru 5a27631dПример конфигурации `AGENTS.md` и набор скиллов (`.agents/`) для разработки игр с помощью ИИ на движке [Defold](https://defold.com). Это в первую очередь исследовательский проект, но вы можете свободно использовать конфигурацию и скиллы в своих проектах. Папка `.deps/` используется скиллом `defold-project-setup` для загрузки исходников зависимостей проекта и встроенных модулей Defold (builtins), давая вашему ИИ-агенту простой доступ к API и типам зависимостей (только для чтения). Для обновлен...Votes: 0GitHub stars: 9
- 2508 Reflection F2683beeAnalyse and improve CLAUDE.md instructions based on chat historyVotes: 0GitHub stars: 9
- 2508 Quality Checklist 0809ed01Load after Phase 4 improvements are applied. Use quality standards to verify the overall repair meets the bar, then run the checklist item by item. ---Votes: 0GitHub stars: 9
- 2508 Distribution 2cf7610fThis guide explains how to package and distribute the security scanner for Claude Code users.Votes: 0GitHub stars: 9
- 2507 Support 2a9ff792Type `/help <question>` and aider will respond with helpful information. You can ask questions about using aider, customizing settings, troubleshooting, using LLMs, etc. Behind the scenes, aider has indexed all of its [documentation](https://aider.chat/). It uses the question to find relevant docs and share them with the LLM to do retrieval augmented generation (RAG) The LLM also has the full context of your ongoing aider chat, so it can help with the exact issue you might be facing. <div cla...Votes: 0GitHub stars: 9
- 2502 Edit Formats 0d3c5081Aider uses various "edit formats" to let LLMs edit source files.Votes: 0GitHub stars: 9
- 2501 Notes Aebac3fcAll pricing information is the cost to run the benchmark at the time it was run. Providers change their pricing and sometimes introduce entirely novel pricing structures. Pricing is provided on a *best efforts* basis, and may not always be current or fully accurate.Votes: 0GitHub stars: 9
- 2500 Edit 92b57853Quantitative benchmark of basic LLM code editing skill.Votes: 0GitHub stars: 9
- 2498 Reasoning A05be33dHow to configure reasoning model settings from secondary providers.Votes: 0GitHub stars: 9
- 2497 Cross Platform Notes B77d95b9Verified against v1.0.1 source code read from `motherduckdb/mcp-server-motherduck` via GitHub API (2026-02-22). ---Votes: 0GitHub stars: 9
- 2497 Adv Model Settings 45ec2acdConfiguring advanced settings for LLMs.Votes: 0GitHub stars: 9
- 2496 Nano Banana Pro Prompting 82732dc9**Research Date**: 2026-02-23 **Source URL**: <https://dev.to/googleai/nano-banana-pro-prompting-guide-strategies-1h9n> **Developer Guide**: <https://dev.to/googleai/introducing-nano-banana-pro-complete-developer-tutorial-5fc8> **API Reference**: <https://ai.google.dev/gemini-api/docs> **Cookbook (Colab)**: <https://colab.sandbox.google.com/github/google-gemini/cookbook/blob/main/quickstarts/Get_Started_Nano_Banana.ipynb> **Version at Research**: Nano-Banana Pro (`gemini-3-pro-image-preview` ...Votes: 0GitHub stars: 9
- 2496 2026 02 19 Api Key Ux Improvement 11552849**Date:** 2026-02-19 **Owner:** agent **Phase:** ResearchVotes: 0GitHub stars: 9
- 2494 Failure Analysis Batch 20260211 221835 8382f786**Generated**: 2026-02-11 22:18:40Votes: 0GitHub stars: 9
- 2494 2026 02 21 Minimax Tool Call Bugs 3aa542efMiniMax M2.5 returns tool calls with empty `id` and sometimes empty `name` fields. Our Python code rejects empty strings in three places. The tinyagent Rust layer (alchemy-llm) handles IDs correctly via `ToolCallId` with `Into` trait -- this is NOT a tinyagent bug.Votes: 0GitHub stars: 9
- 2493 Batch 20260211 221835 Aggregate Ff3fbdf1**Generated**: 2026-02-11 22:18:35Votes: 0GitHub stars: 9
- 2492 Dify 0bddf0fe**Research Date**: 2026-02-23 **Source URL**: <https://dify.ai> **GitHub Repository**: <https://github.com/langgenius/dify> **Documentation**: <https://docs.dify.ai> **Version at Research**: v1.13.0 **License**: Dify Open Source License (Apache 2.0 with additional conditions) ---Votes: 0GitHub stars: 9