Skills for your AI
Sets up and maintains observability infrastructure — metrics collection, alerting rules, dashboards, log aggregation, SLA reporting, distributed tracing, and runbooks. Use when the user needs monitoring configured, alerts defined, dashboards built, logs centra
Navigate, manage, and optimize monorepos. Covers Turborepo, Nx, pnpm workspaces, and Lerna. Cross-package impact analysis, selective builds/tests on affected packages, remote caching, dependency graph visualization, and structured multi-repo to monorepo migrat
Analyzes the trade-offs between options a user is stuck on and makes a definitive recommendation. Use when the user presents two or more choices and asks which to pick, or says they are stuck, torn, or unable to decide.
Analyzes mortality and morbidity data for actuarial work, covering cleaning, trend analysis, risk scoring, forecasting, scenario modeling, reporting, compliance, experience studies and cost impact. Use when an actuary needs mortality or morbidity data processe
Sets up and troubleshoots Motion Canvas projects for programmatic video creation with TypeScript, covering scaffolding, the ESM/CommonJS vite config workaround, dependency installs, and common build errors. Use when starting a new Motion Canvas project, fixing
Designs a product's motion language — duration and easing scales, choreography rules, signature moves — and exports motion tokens, Framer Motion variants, and CSS. Use when auditing existing animations, defining motion tokens, writing choreography rules, namin
Manages the NanoClaw mount allowlist so agent containers can access host directories, letting the owner view, add, remove, or reset entries. Use when the owner asks to see mount configuration, grant or revoke agent access to a directory, or clear all directory
Analyzes Move packages against the Move Book Code Quality Checklist (2024 Edition) across 11 categories and reports specific, actionable violations. Use when reviewing Move code, checking Move.toml, auditing imports, structs, functions, macros, or tests, or ve
Manages and maintains Microsoft SQL Server databases through T-SQL and MS SQL extension tools, covering inspection, query tuning, backup and restore, monitoring, upgrades, security, and disaster recovery. Use when the user asks to connect to a SQL Server insta
Microsoft 365 tenant administration for Global Administrators. Automate M365 tenant setup, Office 365 admin tasks, Azure AD user management, Exchange Online configuration, Teams administration, and security policies. Generate PowerShell scripts for bulk operat
Generates Material-UI v7 component code with sx prop styling, theme integration, responsive breakpoints, v7-compliant imports, and MUI hooks. Use when the user asks for MUI v7 components, styling, theme customization, responsive patterns, breaking-change fixes
Designs coordination strategies for multi-agent systems, covering workflow analysis, inter-agent communication, dependency and execution control, fault tolerance, and performance monitoring. Use when mapping agent dependencies, specifying message channels, pla
Drafts, translates, and analyzes multi-channel insurance customer communications, including replies, campaigns, surveys, and channel plans. Use when a customer service rep needs an inquiry response, translation, sentiment read, FAQ or chatbot script, channel i
Designs and executes multi-source search strategies, optimizing queries, curating verified results, and reporting the full process. Use when the user needs hard-to-find information located across web, academic, patent, legal, government, news, or specialized s
Translates insurance claims inquiries, documents, forms, and communications across languages and checks regional language compliance. Use when a claims processor needs an inquiry translated, a claimant answered in their own language, multilingual forms or FAQs
Translates and localizes support content—articles, guides, FAQs, troubleshooting steps, scripts, UI strings, training materials, video scripts, feature descriptions, error messages, and chatbot responses—into target languages. Use when the user needs existing
Plans and drafts multilingual support assets—language routing, translations, knowledge bases, FAQs, canned responses, training, chatbot/IVR flows, social templates, performance reports, and QA evaluations—for call center supervisors. Use when a supervisor need
Plans, troubleshoots, and evaluates multimedia-rich lessons, projects, and assessments for teachers. Use when a teacher needs interactive lesson ideas, media troubleshooting, tool comparisons, multimedia assessments, accessibility adaptations, collaborative pr
Generates music, sound effects, and conditioned audio from text descriptions using AudioCraft models. Use when the user asks to create a music clip, sound effect, stereo track, melody- or style-conditioned track, or to continue an existing audio clip.
Runs BLIP-2 vision-language inference to caption images, answer visual questions, score image-text matches, and batch-process images. Use when the user supplies an image path or URL with an optional text prompt and wants a caption, a visual answer, a matching
Classifies images into given labels, scores image-text similarity, searches images by text query, moderates content, and batches embeddings using CLIP zero-shot. Use when the user provides image paths or URLs with candidate labels, a text description to compar
Analyzes images with the LLaVA vision-language model for visual question answering, detailed description, object listing, document reading, and multi-turn conversation. Use when the user supplies an image and asks what it contains, wants a caption or object in
Segments objects in a single image using point prompts, box prompts, combined prompts, iterative refinement, or automatic mask generation. Use when the user asks to segment an object, generate all masks for an image, refine a previous mask, or pick a model var
Generates and edits images from text prompts with Stable Diffusion pipelines, including image-to-image, inpainting, LoRA adapters, ControlNet conditioning, and scheduler tuning. Use when the user asks to create an image from a prompt or transform, fill, or res
