Skill UI

This skill provides methodologies for designing sophisticated, layered memory architectures for AI agents. It moves beyond simple context windows and basic vector stores by incorporating short-term, long-term, and graph-based memory systems. Implementing this is crucial for agents that require persistence across sessions, maintaining complex entity consistency, and performing advanced, relationship-driven reasoning over accumulated knowledge bases, including time-aware fact tracking.

A comprehensive guide to implementing advanced asynchronous patterns with Mistral AI. This skill covers using the Agents API for stateful, multi-turn workflows, the Batch API for cost-effective bulk inference, and event-driven streaming architectures. It is essential for building robust, long-running, or high-volume AI applications that require reliable background job handling.

Simulates a highly structured, sequential peer-review process using multiple specialized AI agents (e.g., Skeptic, Constraint Guardian, User Advocate). This skill is designed to rigorously stress-test a design, surface hidden assumptions, identify potential failure modes, and enforce non-functional constraints before implementation. It transforms initial concepts into robust, validated specifications by simulating formal critique and achieving consensus via a mandatory Decision Log.

This guide details advanced architectural patterns for building complex AI systems using multiple Language Model instances (agents). It addresses the single-agent context bottleneck by distributing work, enabling parallelism, and facilitating specialization across different subtasks. Key patterns include Supervisor/Orchestrator, Peer-to-Peer/Swarm, and Hierarchical designs, providing guidelines for context isolation and effective coordination protocols.

Catalogs proven n8n workflow architectural patterns for webhook handling, APIs, database syncing, AI agents, and scheduled tasks, helping teams pick structures, plan nodes, and handle triggers, data paths, and error strategies during workflow design and troubleshooting.

Operates as an end-to-end GitHub repository steward, triaging issues, reviewing PRs, analyzing contributor activity, and generating maintenance guidance so the human can simply ask “what’s next” while the agent keeps UX, docs, and backlog healthy.

Implements standardized function/tool calling across various large language models (LLMs) via OpenRouter. This unified approach allows developers to build sophisticated, multi-step agents and complex workflows, regardless of the underlying provider (e.g., GPT-4o, Claude 3.5). It simplifies the process of achieving structured output and tool-augmented reasoning in production systems.

Enables Claude to orchestrate multi-agent systems using AI SDK v5, setting up agents, handoffs, intelligent routing, and workflows across OpenAI, Anthropic, and Google when users request complex agent coordination.

This skill enables the coordination of multiple specialized AI agents within a single session. It is designed for complex, multi-domain tasks such as comprehensive code reviews, security audits, or full-stack feature implementations. It coordinates expertise across various domains (backend, frontend, testing, architecture) to provide holistic analysis and actionable recommendations.

A sophisticated AI tool that coordinates multiple specialized agents (e.g., Security, Architecture, Performance) to provide comprehensive, multi-perspective code assessments. It goes beyond single-point reviews by managing context, running hybrid execution workflows, resolving conflicts, and synthesizing unified, actionable reports for high-quality code assurance.

Orchestrate PhantomBuster cloud agents through the Composio MCP integration, automating lead generation, web scraping, usage monitoring, container tracking, CSV exports, and hCaptcha solving in a single workflow.

This skill allows AI agents to manage complex, multi-step projects and research tasks using persistent markdown files (`task_plan.md`, `findings.md`, `progress.md`) stored directly in the project directory. It simulates external, long-term working memory, ensuring that project context and accumulated findings survive context window loss, session restarts, or explicit context clearing. Ideal for large-scale coding, research, or multi-phase development efforts.