llm-architect: agent for designing production LLM systems
An agent by davila7 for designing production LLM systems, including fine-tuning, RAG architectures, inference serving and multi-model deployments.
Resources for cloud accounts, deployment, infrastructure as code, containers and monitoring.
2,325 results
An agent by davila7 for designing production LLM systems, including fine-tuning, RAG architectures, inference serving and multi-model deployments.
A Claude Code rule that lets a main model consult Claude Fable 5.2 as an advisor at key decision points.
A status line configuration that shows the latest production and preview deployment status of a Vercel project, using color-coded indicators.
An agent for database performance tuning, high-availability design and disaster recovery for production database systems.
A Claude Code agent for designing, implementing and optimising business process workflows with multiple states, error handling and transaction management.
An agent that offers guidance on troubleshooting, monitoring and improving the performance of Power BI models, reports and queries.
A rule by davila7 that replaces Claude Code's default spinner verbs with a "Don't Deploy On Fridays" reminder.
A skill by davila7 for DevOps work on CI/CD pipelines, infrastructure as code, containerization, deployment automation and monitoring across AWS, GCP and Azure.
An agent for red-teaming large language model deployments, covering jailbreak probes, prompt injection harnesses and output-safety evaluation.
A monitor that shows Vercel build status and time since the last deployment, with a clickable link to the deployment URL.
A rule-type configuration that monitors Vercel deployments and builds for failures and sends desktop notifications when errors are detected.
An agent that brings Dynatrace observability and security analysis into GitHub workflows for investigating incidents and managing vulnerabilities.
An MCP server that lets AI assistants such as GitHub Copilot and Claude interact with Azure Kubernetes Service (AKS) clusters through natural language requests.
An agent for Unity game development, covering C# scripting, 3D graphics, mobile optimization and cross-platform deployment.
A skill that compiles a daily digest of new AI releases from lab repositories, a changelog, a blog and Hacker News, and sends it by email.
A skill that runs a fix-and-push loop on a pull request until its CI checks pass, handling CI failures and review feedback.
An agent for setting up observability over multi-agent systems, covering system metrics, performance anomalies and resource usage.
A skill for testing and benchmarking LLM agents across behavior, capability, reliability and production monitoring.
A rule that sets LangSmith tracing environment variables so Claude Code conversation traces can be sent to LangSmith for monitoring and analysis.
A Claude Code agent for designing and implementing ML infrastructure, model CI/CD, versioning, and operational monitoring.
A statusline configuration by davila7 that the publisher describes as tracking asset processing status for game development workflows.
An agent for live production incidents, covering rapid diagnosis of critical service failures and blameless postmortems after resolution.
A Claude Code settings rule that adds Claude Sonnet 5.5 as a lower-cost advisor, consulted by the main model at key decision points.
A skill that covers workflow automation platforms (n8n, Temporal, Inngest) and execution patterns for building durable automated workflows.