Search
AI & LLM Engineering · By github
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Patterns and techniques for evaluating and improving AI agent outputs. | github/ | 40k | 3 repos | ~1.5k | Automated safety check: Pass | MIT | today |
| 2 | Build agentic applications with GitHub Copilot SDK. An agent skill from github/awesome-copilot. | github/ | 40k | 4 repos | ~6.3k | Automated safety check: Pass | MIT | today |
| 3 | OpenInference semantic conventions and instrumentation for Phoenix AI observability. | github/ | 40k | 2 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | today |
| 4 | Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. | github/ | 40k | 1 repo | ~664 | Automated safety check: Pass | MIT | today |
| 5 | Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. | github/ | 40k | 2 repos | ~4.6k | Automated safety check: Pass | MIT | today |
| 6 | Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. | github/ | 40k | 1 repo | ~4.8k | Automated safety check: Notes | MIT | today |
| 7 | Debug LLM applications using the Phoenix CLI. An agent skill from github/awesome-copilot. | github/ | 40k | 1 repo | ~4k | Automated safety check: Pass | Apache-2.0 | today |
| 8 | Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and… | github/ | 40k | 1 repo | ~8.1k | Automated safety check: Notes | MIT | today |
| 9 | Create and synchronize prompt-based AI agents directly within Azure AI Foundry via REST API, from a local JSON manifest. | github/ | 40k | 1 repo | ~2.1k | Automated safety check: Pass | MIT | today |
| 10 | Internal gh-aw architecture: validation system design, safe output message patterns, schema validation, YAML compatibility notes, and MCP logs guardrail. | github/ | 5.4k | — | ~4.5k | Automated safety check: Pass | MIT | today |
| 11 | Use gh agent-session commands to inspect and manage agent sessions. | github/ | 5.4k | — | ~2.6k | Automated safety check: Pass | MIT | today |
| 12 | Use gh agent-task commands to create, run, and monitor agent tasks. | github/ | 5.4k | — | ~2.6k | Automated safety check: Pass | MIT | today |
| 13 | Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques. | github/ | 5.4k | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 14 | Build and run evaluators for AI/LLM applications using Phoenix. | github/ | 40k | 2 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 15 | Comprehensive AI prompt engineering safety review and improvement prompt. | github/ | 40k | 2 repos | ~2.5k | Automated safety check: Pass | MIT | today |
| 16 | Diagnoses Qdrant search quality issues. An agent skill from github/awesome-copilot. | github/ | 40k | 1 repo | ~928 | Automated safety check: Pass | MIT | today |
| 17 | Guides Qdrant search strategy selection. An agent skill from github/awesome-copilot. | github/ | 40k | 1 repo | ~1.7k | Automated safety check: Pass | MIT | today |
| 18 | Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot | github/ | 40k | 1 repo | ~737 | Automated safety check: Pass | MIT | today |
| 19 | Create, update, refactor, explain, or review Microsoft Agent Framework solutions using shared guidance plus language-specific references for .NET and Python. | github/ | 40k | 1 repo | ~1k | Automated safety check: Pass | MIT | today |
| 20 | Diagnoses and improves Qdrant search relevance. An agent skill from github/awesome-copilot. | github/ | 40k | 1 repo | ~336 | Automated safety check: Pass | MIT | today |
| 21 | Improve AI application with evaluation-driven development. An agent skill from github/awesome-copilot. | github/ | 40k | 1 repo | ~4.4k | Automated safety check: Warn | MIT | today |
| 22 | Adds Arize AX tracing to an LLM application for the first time. | github/ | 40k | — | ~6.2k | Automated safety check: Notes | MIT | today |
| 23 | Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. | github/ | 40k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | today |
| 24 | Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. | github/ | 40k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 25 | Build and evolve agentic web apps that pair a CopilotKit React frontend with a Microsoft Agent Framework agent running as a Microsoft Foundry hosted agent, connected over the AG-UI protocol. | github/ | 40k | — | ~2.5k | Automated safety check: Pass | MIT | today |