Tag: llm
AST-based smart code review and quality analysis
This skill performs deep, AST-aware code reviews by analyzing diffs across various scopes (staged, branch, commit). It identifies bugs, security flaws, and performance issues, providing structured feedback including a quality score and acti…
Structured framework for agent skill creation
This framework provides structured guidelines and validation scripts for developing agentic skills. It enforces best practices for keeping skill definitions lean, managing metadata, and structuring associated assets like scripts and referen…
CLI tool for deep LLM code review
This CLI tool facilitates deep, context-aware code analysis by bundling a prompt with selected project files for a single LLM pass. It supports multiple engines (browser/API) and manages long-running sessions for complex debugging or refact…
OpenAI Audio Transcription API Wrapper
This skill provides a wrapper for transcribing audio files using various OpenAI models, including gpt-4o and whisper-1. It supports advanced features such as speaker diarization, language specification, and custom prompts.
Gemini CLI for headless LLM interaction
This CLI allows developers to interact with Gemini models in a headless, one-shot mode. It supports structured outputs, prompt piping via stdin, and management of extensions, skills, and MCPs.
Manage scheduled reminders for QQ Bot
This tool enables agents to programmatically create, list, and cancel scheduled reminders within a QQ conversation. It supports both relative time offsets and complex cron expressions for setting recurring or one-time alarms.
Multi-Model AI Debate and Synthesis Engine
This tool orchestrates structured, multi-round debates between various LLM providers, allowing for diverse perspectives on complex topics. It facilitates deep analysis and provides a final synthesis of the collective model viewpoints.
Git Merge Conflict Resolution Skill
This skill resolves complex git merge conflicts by analyzing both conflicting branches' intents. It ensures code correctness, type safety, and test passing while preferring to combine changes rather than discarding them.
Configure internationalization and project settings
Manages the core internationalization strategy for an application, allowing developers to define locales, control routing, and configure content import modes. It centralises settings for AI integration, language support, and content transfo…
Persistent memory and knowledge sharing for agents
This tool provides persistent, long-term memory storage for agents, allowing facts and insights to survive session restarts. Developers can store, semantically recall, and manage memories across different scopes (agent, user, organization).
Gemini CLI for large codebase analysis
Initiates a dedicated Gemini CLI session, providing a massive 1M context window ideal for deep analysis of large codebases. It manages session state, allowing users to start new tasks or resume previous analyses via a unique task ID.
Multi-AI deliberation council consultation
Initiates a structured, multi-perspective deliberation by querying several advanced AI models in parallel. This process facilitates comprehensive analysis and consensus building on complex technical queries.
Persistent knowledge management and memory server
Memora is an MCP memory server designed for robust, persistent knowledge management and context loading. It facilitates advanced retrieval (semantic/hybrid search) and knowledge absorption, automatically handling supersession, deduplication…
Structured workflow for recalling project history and context
This skill implements a token-efficient, three-layer memory retrieval workflow, allowing agents to search, contextualise, and retrieve past decisions, errors, and project history. It guides the agent through indexed searching, temporal cont…
Structured Image Prompt Engineering Skill
Implements a structured five-section framework to transform vague user requests into precise, text-accurate prompts for models like GPT Image 2 and Flux. It uses specific rules for typography, layout preservation, and anti-slop to ensure hi…
Node.js AI Model Integration Skill
Integrates AI text and image generation into Node.js backends, cloud functions, and serverless environments using the CloudBase SDK. It supports various models including DeepSeek, Hunyuan, GLM, and Kimi through managed model groups.
Node.js AI Model SDK
An SDK for integrating AI text and image generation into Node.js backends, cloud functions, and CloudRun services. It enables server-side orchestration, batch processing, and managed model access using the CloudBase Node.js SDK.
WebPeel: Clean Web Content Extraction
Extracts clean, structured markdown from any URL while significantly reducing token usage for LLM agents. It handles JavaScript rendering, bot protection, and provides specialised extractors for platforms like YouTube and GitHub.
AI-powered browser automation and extraction
An AI-driven engine that uses LLMs and computer vision to automate web workflows, extract structured data, and manage browser sessions. It integrates via Python and TypeScript SDKs, a REST API, and an MCP server.
Generate comprehensive project documentation suite
This skill analyzes an entire codebase to produce a comprehensive documentation suite, adhering strictly to the Diátaxis framework. It generates detailed documentation covering architecture, package references, API surfaces, and developer g…
Shakespearean Persona and Style Skill
This skill enables an agent to adopt the persona of a Shakespearean scholar, utilising early modern English and poetic cadence. It transforms model outputs into the distinctive style of William Shakespeare.
Claude API Integration Skill
This skill assists in building applications using the Claude API and Anthropic SDK, prioritizing the official SDK and defaulting to Claude Opus 4.7 with adaptive thinking and streaming. It handles code migration between Claude model version…