Automate Uptimerobot tasks via Rube MCP (Composio).
Fetch and analyze component health regressions for OpenShift releases
Use when positioning a Journal of Applied Econometrics (JAE) manuscript against prior work — applied-econometrics precedent, the methods…
Use when positioning a Journal of Business & Economic Statistics (JBES) methods paper against prior econometric and statistical methods.
Automate Livesession tasks via Rube MCP (Composio).
llama.cpp local GGUF inference + HF Hub model discovery.
Unsloth GRPO training, HF export and vLLM serving lifecycle.
Implements layered resilience engineering, retry mechanisms, and self-healing pipelines for unattended LLM batch and scheduled jobs.
Use when: (1) Entering an LLM-based Kaggle competition (open-source model required, prompt engineering, few-shot), (2) Need to choose…
When to activate: LLM integration, LangChain, LlamaIndex, prompt templates, chains, tool calling, streaming, token budgeting, LLM caching…
Investigate LLM output quality issues — trace hallucination root causes across context, retrieval, prompts, tool use, and workflow design
Profiles runtime performance with CPU, memory, and I/O metrics.
Safely auto-detect the current machine's hardware (GPU, VRAM, system RAM, OS) with read-only commands, then recommend the top 3 local AI…
Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and…
Run OCR on local images through an OpenAI-compatible local vision endpoint (LM Studio, vLLM/vmlx).
Audits local Claude Code and Codex skill directories to verify usage history, detect trigger failures, and resolve multi-layer runtime…
Display CO2 emissions report for Claude Code sessions
Generate shareable PNG report cards of your Claude Code carbon footprint
Analyze application logs for performance insights and issue detection
Enforces active voice for logger messages and the Event Details API.
Monitor and log API requests with correlation IDs, performance metrics,