Tag: llm
CloudBase Full-Stack Development and AI Integration Guide
This skill provides comprehensive guidelines for developing, deploying, and debugging full-stack applications across multiple platforms, including web, mini-programs, and native mobile apps. It covers everything from database management and…
Client-Side AI Model Integration via JavaScript SDK
This skill facilitates direct integration of various large language models into client-side web applications using the dedicated JavaScript SDK. It is designed for Single Page Applications and dashboards, enabling text generation and stream…
Node.js Backend AI Model Integration Skill
This skill enables secure, server-side integration of various AI models into Node.js backends, supporting functions like text generation, image creation, and agent orchestration via the CloudBase SDK. It is designed for cloud functions and …
Persistent memory and knowledge management server
A robust memory server designed for agents to manage persistent knowledge and context. It facilitates advanced retrieval (semantic, hybrid) and knowledge absorption, automatically handling supersession, deduplication, and consolidation of f…
Persistent Semantic Memory and Knowledge Management
Memora provides a persistent, semantic memory layer for managing knowledge, architectural decisions, and task tracking across multiple sessions. It allows developers to store, retrieve, and organize context using hybrid search, structured h…
bug issue triage for apify mcp server
This skill automates the process of triaging open bug reports on the Apify MCP server's GitHub repository. It analyzes issue context, categorises root causes, drafts developer-to-developer responses, and proposes necessary GitHub actions fo…
Design QA for Llamactl CLI Changes
This skill facilitates design-QA for llamactl changes, allowing human reviewers to assess the rendered output, naming conventions, and error messaging against a live backend. It generates a matrix of carefully chosen test cases and produces…
A2UI JSON response generation skill
This skill facilitates the generation of rich, interactive user interfaces by retrieving specific A2UI UI JSON schematics and templates. It allows agents to structure responses according to the A2UI protocol, ensuring validation and reducin…
Oracle: Context-Aware Prompt Bundling CLI
A CLI tool that bundles prompts and repository files into single-shot requests for LLMs using API or browser engines. It supports advanced file globbing, session management for long-running tasks, and token usage previews.
Gemini CLI for one-shot AI interactions
This tool provides a command-line interface for executing one-shot prompts with the Gemini model, enabling structured tasks such as Q, summarisation, and JSON generation. Users can specify models and manage extensions entirely via CLI argum…
Orchestrate AI Agents for Complex Coding Tasks
This skill delegates complex coding tasks, such as feature building or refactoring, to various AI agents (Codex, Claude Code, Pi). It manages background sessions, handles PTY requirements for different agents, and provides process control a…
Reproducible Redteaming for Prompt Security QA
This tool facilitates reproducible redteaming evaluations of prompts, allowing developers to run, inspect, and triage security scan results. It supports stable evaluation of existing test artifacts or full regeneration, enabling focused rer…
Creating and managing promptfoo evaluation suites
This skill guides the creation and maintenance of comprehensive promptfoo evaluation suites, enabling rigorous QA for non-redteam coverage, regression testing, and new matrix development. It details structuring configs, writing prompts, sel…
LobeHub CLI for managing AI services
This comprehensive command-line interface provides robust management capabilities for LobeHub services, including agent lifecycle management, content generation, and knowledge base operations. It is built with Commander.js and interacts wit…
Agent lifecycle hooks for observation and interception
Allows developers to observe and intercept agent execution at critical lifecycle points, including tool calls, context compression, and sub-agent interactions. Hooks can be registered to implement custom logic for tracing, mocking, or loggi…
Augments Code Review with Senior Partner Insights
This skill acts as a senior review partner, helping developers thoroughly evaluate code changes by summarizing intent, mapping ownership responsibilities, detailing structural changes, and surfacing key concerns using conventional comment l…
Automated Financial Report Analysis and Deep Reporting
This skill automates the comprehensive analysis of listed company financial reports by extracting core metrics, calculating key ratios, and generating visualizations. It synthesises a professional report, providing deep insights into profit…
mem0: persistent memory layer for ai agents
Mem0 provides a managed, API-driven memory layer enabling agents to store, retrieve, and manage long-term user context. Developers can integrate this persistent memory into their applications using Python or TypeScript SDKs, facilitating th…
Mem0 Memory Provider for Vercel AI SDK
This provider integrates Mem0 memory management directly into the Vercel AI SDK, automatically retrieving relevant memories and storing conversation history during LLM calls. It supports both wrapped models for seamless integration and stan…
Integrate Mem0 into existing repositories via TDD
This skill guides the integration of Mem0 into an existing codebase using a goal-driven, test-driven development pipeline. It automatically detects the language, writes failing tests, and ensures the integration is additive and opt-in via f…
Memory Consolidation and Cleanup Protocol
This skill reviews and improves the quality of stored memories by consolidating facts, deleting stale or sensitive data, and rewriting vague entries. It ensures the memory store remains clean, accurate, and adheres to defined quality standa…
Vercel AI SDK Development and Integration Guide
This skill assists developers in implementing advanced AI features using the Vercel AI SDK. It provides comprehensive guidance on building agents, managing streaming, and adhering to the latest API standards for various LLM providers.
Comprehensive examples for AI SDK function development
This repository provides a comprehensive suite of examples and templates for validating, testing, and demonstrating various AI SDK functions across multiple providers. It covers core capabilities such as text generation, structured object o…
Adding AI function examples for testing
This skill guides developers through adding functional examples to test specific AI features against actual provider APIs. Examples must be created for relevant top-level functions, including both generateText and streamText variants.