Skill UI

Automates generating TorchServe deployment configurations with guided best practices for model serving, MLOps pipelines, inference, and production monitoring so ML deployment workflows stay consistent and reliable.

Automates Triton inference config guidance for ML deployment, covering serving, MLOps pipelines, monitoring, and production-ready configurations aligned with best practices.

A comprehensive guide to implementing fault-tolerant patterns for Vercel serverless functions. Learn how to build resilient APIs using Circuit Breakers to handle external dependency failures, implementing Exponential Backoff for retries, and achieving Graceful Degradation by serving stale cache data. Essential for production-grade, highly available serverless architecture.

Automates Vertex AI deployment tasks, offering step-by-step guidance, production-ready code, and validation for model serving, MLOps pipelines, monitoring, and optimization when you mention Vertex AI Deployer.

Guidance for creating, editing, and analyzing .xlsx workbooks while preserving formulas, formatting, and assumptions, leveraging pandas/openpyxl for data work and LibreOffice recalc to ensure error-free financial models.

Guides execution of implementation plans by dispatching isolated subagents per task, enforcing a spec-first then quality review loop, and preserving overall coordination context for faster, high-quality iterations.

This skill transforms flawed writing — whether pasted text or uploaded documents — into publication-ready prose. It eliminates grammatical, spelling, punctuation, clarity, and tone issues while strictly preserving the author’s original intent and unique voice. Use it for professional document refinement, academic paper polishing, or general text review, ensuring the corrected version maintains your authentic style.

A seven-pass copy editing framework that systematically improves marketing and conversion copy by sharpening clarity, consistency, benefits, proof, specificity, and emotion while preserving the original voice.

This skill provides a robust and safe mechanism for updating SpecKit templates and configurations from GitHub. It is designed to automatically apply the latest changes while meticulously preserving any existing project customizations, ensuring a non-disruptive workflow. It features a conversational, two-step approval process, guiding the user through the update process, reporting conflicts, and handling fresh installations gracefully. Ideal for developers needing reliable, version-controlled updates to their SpecKit environment.

This skill is intended for Perl testing functionalities. Currently, the Japanese translation and content are under development, serving as a placeholder. Users should refer to the original English skill file for the core functionality and detailed implementation.

RecallMax dramatically enhances AI agent memory capabilities by cleanly injecting massive external contexts (500K-1M tokens) without hallucination drift. It automatically summarizes lengthy conversations, preserving tone, intent, and key facts. Furthermore, it compresses multi-turn interaction histories into high-density token sequences, ensuring agents maintain perfect recall across complex and long-running sessions.

A comprehensive guide for digital forensics professionals to investigate compromised Docker containers. It covers best practices for preserving container state, analyzing image layers, reviewing runtime logs, and examining host system artifacts to identify evidence of malicious activity, container escapes, or misconfigurations.