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 1,057–1,080 of 302,729 skills
- 1639 Spec 27767d0d**Feature Branch**: `openai-compatible-env-vars` **Input**: User description: "We have several openai compatible providers: @src/esperanto/providers/stt/openai_compatible.py @src/esperanto/providers/tts/openai_compatible.py @src/esperanto/providers/llm/openai_compatible.py @src/esperanto/providers/embedding/openai_compatible.py I noticed an issue with the way we configured this. All of them are using the same BASE_URL and API_KEY environment variables. So, if the user has different services f...Votes: 0GitHub stars: 9
- 1636 Transformers B17cd9d1The Transformers provider enables **complete privacy and local processing** by running models directly on your machine. No data is sent to external APIs, making it perfect for sensitive data and air-gapped environments.Votes: 0GitHub stars: 9
- 1635 Openrouter 191390efOpenRouter provides unified access to multiple AI models from different providers through a single API. It acts as a gateway to models from OpenAI, Anthropic, Google, Meta, Mistral, and many others, offering flexibility and easy model switching.Votes: 0GitHub stars: 9
- 1634 Openai Compatible 08c8bf2eThe OpenAI-Compatible provider enables you to use any service that implements the OpenAI API format. This includes local deployments, custom endpoints, and third-party services, giving you maximum flexibility while maintaining Esperanto's unified interface.Votes: 0GitHub stars: 9
- 1633 Ollama Fe63cc8dOllama enables local deployment of various open-source language models and embeddings with a simple API interface. It provides privacy-focused, self-hosted AI capabilities without cloud dependencies.Votes: 0GitHub stars: 9
- 1632 Mistral F0a7395cMistral AI provides high-performance language models and embeddings with a focus on efficiency, multilingual capabilities, and European data residency. Their models are known for excellent performance-to-cost ratios.Votes: 0GitHub stars: 9
- 1631 Jina 8622a5a4Jina provides advanced embedding and reranking capabilities with native support for task optimization, late chunking, and output dimension control. Perfect for production RAG systems and search applications requiring cutting-edge performance.Votes: 0GitHub stars: 9
- 1630 Deepseek 3d8178e5DeepSeek provides powerful language models with a focus on reasoning, coding, and general-purpose tasks. Their models offer competitive performance at attractive pricing, making them a strong choice for production applications.Votes: 0GitHub stars: 9
- 1629 Anthropic 4e802ab8To work with Anthropic's models, you need to provide your [Anthropic API key](https://docs.anthropic.com/claude/reference/getting-started-with-the-api) either in the `ANTHROPIC_API_KEY` environment variable or via the `--anthropic-api-key` command line switch. First, install aider: {% include install.md %} Then configure your API keys: ``` export ANTHROPIC_API_KEY=<key> # Mac/Linux setx ANTHROPIC_API_KEY <key> # Windows, restart shell after setx ``` Start working with aider and Anthropic on...Votes: 0GitHub stars: 9
- 1629 Anthropic 0a75ec46Anthropic provides access to the Claude family of large language models, known for their strong performance on reasoning, analysis, and longer-form tasks.Votes: 0GitHub stars: 9
- 1628 Task Aware Embeddings 95534dd0Task-aware embeddings represent a breakthrough in semantic processing. Instead of one-size-fits-all vectors, you can optimize embeddings for specific tasks, achieving 15-30% performance improvements in search relevance, classification accuracy, and similarity matching.Votes: 0GitHub stars: 9
- 1627 Model Discovery F2c93ffeEsperanto provides a convenient way to discover available models from providers without creating instances. This allows you to explore what models are available, check their capabilities, and make informed decisions about which models to use in your applications.Votes: 0GitHub stars: 9
- 1614 Commit 14acca21I'll analyze your changes and create a meaningful commit message. **Pre-Commit Quality Checks:** Before committing, I'll verify: - Build passes (if build command exists) - Tests pass (if test command exists) - Linter passes (if lint command exists) - No obvious errors in changed files First, let me check if this is a git repository and what's changed: ```bash if ! git rev-parse --git-dir > /dev/null 2>&1; then echo "Error: Not a git repository" echo "This command requires git version control"...Votes: 0GitHub stars: 9
- 1588 Usage 8a5d1b8dHow to use aider to pair program with AI and edit code in your local git repo.Votes: 0GitHub stars: 9
- 1570 Gotchas B2750204```typescript // ❌ WRONG - Don't install @cloudflare/ai import Ai from '@cloudflare/ai';Votes: 0GitHub stars: 9
- 157 Icons Bca73b6eUse consistent icons across all documentation. This mapping ensures visual consistency.Votes: 0GitHub stars: 9
- 1569 Sdk 17dd19d6The `mcpbr.sdk` module provides the public Python SDK for programmatic access to MCP server benchmarking. It is the primary entry point for Python users who want to configure, validate, and execute benchmarks without the CLI. All public symbols are re-exported from the top-level `mcpbr` package. ```python from mcpbr import MCPBenchmark, BenchmarkResult from mcpbr import list_benchmarks, list_models, list_providers, get_version ``` ---Votes: 0GitHub stars: 9
- 1568 Benchmarks 9a51e720[](https://aider.chat/assets/benchmarks.svg) Aider is an open source command line chat tool that lets you work with GPT to edit code in your local git repo. To do this, aider needs to be able to reliably recognize when GPT wants to edit local files, determine which files it wants to modify and what changes to save. Such automated code editing hinges on using the system prompt to tell GPT how to structure code edits in its responses. Aider currently ...Votes: 0GitHub stars: 9
- 156 Supported Providers E2addfb6DAIV currently supports integration with the following LLM providers: - [OpenRouter](https://openrouter.ai) - [OpenAI](https://openai.com) - [Anthropic](https://anthropic.com) - [Gemini](https://gemini.google.com) A combination of providers may be configured. For example, you can use OpenAI provider for one agent and Gemini provider for another. ---Votes: 0GitHub stars: 9
- 1558 Infraops Conductoragent A17e97cbMaster orchestrator for the 7-step Azure infrastructure workflow. Coordinates specialized agents (Requirements, Architect, Design, Bicep Plan, Bicep Code, Deploy) through the complete development cycle with mandatory human approval gates. Maintains context efficiency by delegating to subagents and preserves human-in-the-loop control at critical decision points.Votes: 0GitHub stars: 9
- 1556 Skills Skill 99d268aeSkills are contextual prompts that teach AI coding assistants how to accomplish specific tasks. For the canonical list of bundled skills, see `src/m4/skills/SKILLS_INDEX.md`.Votes: 0GitHub stars: 9
- 1535 Uat Assistantagent E3abfb76You are a User Acceptance Testing specialist who guides users through creating and executing UAT tests for their Azure services.Votes: 0GitHub stars: 9
- 153 Yaml Config E44080e8Customize DAIV for your repository using a `.daiv.yml` YAML configuration file in the default branch and repository root directory. This file lets you control features, code formatting, and more.Votes: 0GitHub stars: 9
- 153 Yaml Config 16d8a9beCustomize DAIV for your repository using a `.daiv.yml` YAML configuration file in the default branch and repository root directory. This file lets you control features, code formatting, and more.Votes: 0GitHub stars: 9