LazyAGI

Build and review UI components for robust accessibility and runtime resilience, including semantic structure, keyboard support, loading and error states, retry flows, and predictable async behavior.

Implement or refactor UI forms with defense-in-depth validation, safe input handling, reliable submission behavior, and privacy-aware error handling. Use when building login, registration, profile, payment, admin, or file-upload forms.

Review frontend and UI changes for concrete security risks such as XSS, unsafe URL handling, token leakage, missing origin checks, and client-side authorization gaps. Use when users ask for a UI code review focused on safety and reliability.

LazyLLM framework for building multi-agent AI applications. Use when task mentioned LazyLLM or AI program for: (1) Flow orchestration - linear, branching, parallel, loop workflows for complex data pipelines, (2) Model fine-tuning and acceleration - finetuning LLMs with LLaMA-Factory/Alpaca-LoRA/Collie and acceleration with vLLM/LMDeploy/LightLLM. Includes comprehensive code examples for all components, (3) RAG systems - knowledge-based QA with document retrieval, vectorization, and generation, (4) Agent development - single/multi-agent systems with tools, memory, planning, and web interfaces.

Run AI code review using the LazyLLM review CLI tool (lazyllm review / lazyllm review-local). Use when the user mentions: review, code review, review-local, review PR, fix review issues, post review to GitHub, lazyllm review, PR review, review 代码, 代码 review, review 问题, 修复 review, fix review comments, fix bug from review, 修复 review 评论, 处理 PR review 意见, 根据 review 修 bug, 回复 review 评论。 Covers installation, model/API-key config, local review JSON processing, GitHub auth, posting review comments to PRs, and fixing bugs from PR review comments.