Agent Skills Hub

prompt-engineering-patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production applications.

manufacturing-failure-reason-codebook-normalization

Normalizes testing defect logs by correcting typos, abbreviations, and ambiguous descriptions based on product-specific codebooks and station validation.

taide-botrun

A RAG-based AI solver for high school Chinese GSAT exams, featuring structured knowledge retrieval, reasoning templates, and explainable AI outputs.

basic-usage

Essential guide to llmemory for document storage and search: installation, database setup with pgvector, document ingestion, hybrid/semantic retrieval, and building RAG systems with multi-tenant support.

ai-multimodal

Process and generate multimedia with Google Gemini. Analyze audio, images, videos, and PDFs with high-context windows. Supports transcription, visual QA, OCR, and AI-driven image creation.

BDD-prompts-with-eval

An AI-driven active listening framework to extract, clarify, and structure requirements, business values, and scope from ambiguous user stories.

sync-readme

Synchronize English README.md with Chinese README_ZH.md, maintaining content parity and structural consistency for bilingual documentation projects.

claude-starter

An AI-powered skill that automatically retrieves relevant project context from your RAG knowledge base for complex coding tasks.

phone-agent-skill

Automate Android device operations using AI AutoGLM Phone Agent. Enables natural language control for app testing, data collection, and UI interactions like tapping, scrolling, and inputting text.

landing-page-conversion-audit

Perform a structured 8-factor conversion rate optimization (CRO) audit of any landing page to identify friction points and opportunities for growth.

zai-cli

Execute z.AI CLI for multimodal analysis, web search, reader, and GitHub repo exploration via CLI and MCP.

prompt-optimizer

Transforms vague or poorly structured prompts into optimized, high-performance instructions using proven prompt engineering principles for better AI model execution.