Audit token usage patterns — avg context size, waste, truncation frequency, budget adherence.
You are an expert in Tokio, the asynchronous runtime for Rust that powers most of the Rust async ecosystem.
Build or evolve a complex agent-enabled Tutti workspace app repository.
Configure TwinMind across development, staging, and production environments
Unified LLM torch-profiler triage skill for `sglang`, `vllm`, `TensorRT-LLM`, and `TokenSpeed`.
Performance and hybrid architecture specialist - Masters C++/Blueprint continuum, Nanite geometry, Lumen GI, and Gameplay Ability System…
Update Azure Verified Modules (AVM) to latest versions in Bicep files.
Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project.
URL content extraction. Use for fetching any URL - webpages, articles, PDFs, JavaScript-heavy sites. Token-efficient: runs in forked…
Deploy and manage projects on Vercel using token-based authentication.
Implement computer vision features including text recognition (OCR), face detection, barcode scanning, image segmentation, object…
Automate Anchor Browser tasks via Rube MCP (Composio).
Automate Baselinker tasks via Rube MCP (Composio).
Automate Booqable tasks via Rube MCP (Composio).
Best practices for building Stripe integrations.
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM…
Interact with GitHub using the `gh` CLI.
Build VS Code extensions from scratch or convert existing JS/React/Vue apps.
Wave methodology knowledge for the buddy agent — what each wave does, its inputs and outputs, and how to route questions.
Signs of taste in web UI. Use when building or reviewing any user-facing web interface — dashboards, SaaS apps, marketing sites, internal…
Setup and use WebF's Cupertino UI library to build native iOS-style UIs with pre-built components instead of crafting everything with…