>

Expert knowledge for building AI agents with Argentic - a Python microframework for async MQTT-based agents with multi-LLM support, custom tools, and multi-agent orchestration

Complete invoice processing system for Argentine utility bills with OCR, classification, and automated organization

name: argo-expert

Audits ArgoCD Application manifests and raw K8s resources for anti-patterns, security issues, and best practice violations. Use when asked to audit, review, or check ArgoCD/GitOps quality. Generates a comprehensive report under reports/YYYY-MM-DD/argocd-audit.md. (project)

Deploy and manage ArgoCD using the App-of-Apps pattern. Covers bootstrap Applications, ApplicationSets, and GitOps workflows. Use when setting up or troubleshooting ArgoCD deployments.

Expert-level ArgoCD GitOps deployment, application management, sync strategies, and production operations

Generates ArgoCD Application manifests following the App-of-Apps pattern.

Automate container image updates for Kubernetes workloads managed by Argo CD. USE WHEN configuring ArgoCD Image Updater, setting up automatic image updates, configuring update strategies (semver, digest, newest-build, alphabetical), implementing git write-back, troubleshooting image update issues, or working with ImageUpdater CRDs. Covers installation, configuration, authentication, and best practices.

GitOps continuous delivery tool for Kubernetes with repository management and application synchronization.

GitOps continuous delivery for Kubernetes with ArgoCD. Use when creating/managing ArgoCD Applications, ApplicationSets, App of Apps patterns, Helm/Kustomize deployments, sync configurations, RBAC/projects setup, notifications, health checks, or private repository configuration.

Standard library Python argparse examples with subparsers, choices, actions, and nested command patterns. Use when building Python CLIs without external dependencies, implementing argument parsing, creating subcommands, or when user mentions argparse, standard library CLI, subparsers, argument validation, or nested commands.

Analyze argument structure, identify logical gaps, suggest evidence needs, generate counterarguments, apply claim-evidence-warrant framework. Use when strengthening arguments, analyzing persuasive writing, checking logical validity, or when user asks to improve reasoning or logic.

Reconstruct, visualize, and analyze argument structure. Use for: argument reconstruction, premise identification, inference evaluation, finding hidden assumptions, visualizing debates, Toulmin model analysis. Triggers: 'argument structure', 'premises', 'conclusion', 'inference', 'reconstruct', 'map the argument', 'Toulmin', 'argument diagram', 'validity', 'soundness', 'implicit premise', 'hidden assumption', 'logical structure'.

I'm a specialized agent focused on strengthening the logic and persuasiveness of your arguments. I analyze argument structure, identify gaps, and suggest specific improvements.

Expert knowledge of WAI-ARIA (Accessible Rich Internet Applications). Use when users ask about ARIA roles, states, properties, accessible name computation, ARIA attributes (aria-label, aria-labelledby, aria-describedby, etc.), widget roles, landmark roles, live regions, ARIA best practices, or how to implement accessible interactive components. Also use for questions about ARIA specifications, API mappings (core-aam, html-aam), digital publishing ARIA (dpub-aria), graphics ARIA, or any ARIA implementation questions.

Provides ARIA roles, states, and properties for interactive components. Use when building custom widgets, fixing screen reader issues, or implementing modals, tabs, accordions, menus, or dialogs accessibly.

IMO Gold Medal level Lean4 theorem proving via Harmonic API

Test the Ark Dashboard UI with Playwright

Test Ark Dashboard with Playwright and create PRs with screenshots. Use when testing dashboard UI, taking screenshots for PRs, or reviewing dashboard changes.

Run Ark from cloned source using devspace

Install Ark on a Kuberenetes Cluster

Builds accessible UI components with Ark UI headless primitives for React, Vue, Solid, and Svelte. Use when creating custom-styled components with robust state management and accessibility built-in.

Build and debug ARKit features for visionOS, including ARKitSession setup, authorization, data providers (world tracking, plane detection, scene reconstruction, hand tracking), anchor processing, and RealityKit integration. Use when implementing ARKit workflows in immersive spaces or troubleshooting ARKit data access and provider behavior on visionOS.

ArkTS Language Specification. ArkTS is a statically-typed programming language developed by Huawei for HarmonyOS, extending TypeScript with features from Java and Kotlin. Use for ArkTS syntax, types, classes, functions, and language features.

Expert knowledge for runtime validation in TypeScript using ArkType, a syntax-first validation library with TypeScript-like definitions, JIT compilation for 10x-100x performance over Zod, native recursion support, morphs for data transformation, and Standard Schema compatibility

Manage Arlo security cameras, video doorbell, and smart home security

>

Arm physical flight controller via MSP and download blackbox logs

Expert knowledge for using Azure Resource Manager (ARM) template functions, especially reference(), listKeys(), and resourceId() in subscription-level and nested deployments. Use when working with ARM templates, encountering template validation errors, or implementing cross-scope resource references.

---name: armored-cart-design-agent

Complete visual content system. USE WHEN user wants to create visual content, illustrations, diagrams, OR mentions art, header images, visualizations, mermaid, flowchart, technical diagram, infographic, PAI icon, pack icon, or PAI pack icon.

Transform rough image generation prompts into consistent, effective art direction. Use when getting inconsistent results from AI image generators, need variations matching existing style, or translating vague ideas into precise prompts. Outputs structured prompts, negative prompts, and composition variants.

This skill should be used when creating artistic icon variations from images. It generates 10 different greyscale icon styles from a single image source, automatically compressing to under 20KB with high contrast appearance. Supports both URL and local file inputs.

Creates compelling AI art prompts that capture concepts visually with proper style guidance.

Artery Technology MPN encoding patterns, suffix decoding, and handler guidance. Use when working with Artery AT32 MCUs (STM32-compatible ARM Cortex-M4) or ArteryHandler.

Analyze blog posts and web articles by fetching content from URLs. Use when the user mentions blog post, article, Substack, Medium, web page, newsletter, or provides a URL to analyze.

Generate professional article cover images as SVG files. Use when user wants to create cover/banner images for blog posts, technical articles, or documentation. Creates visually appealing covers with titles, diagrams, and tech-themed graphics.

Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.

Generates consistent, professional cover images for business/fiscal articles using Ideogram with standardized prompts and naming conventions. Use when creating new articles, updating missing covers, or maintaining visual consistency across the content library.

Manage article task queue - add, filter, update status, and track multi-language outputs

This skill analyzes article content in-depth and generates optimized, marketable titles in the format 'Title: Subtitle' (10-12 words maximum). The skill should be used when users request title optimization, title generation, or title improvement for articles, blog posts, or written content. It generates 5 title candidates using proven formulas, evaluates them against success criteria (clickability, SEO, clarity, emotional impact, memorability, shareability), and replaces the article's title with the winning candidate.

Edit and refine blog articles and technical posts to match a specific writing style. Use when editing markdown articles, blog posts, or technical writing. Applies conversational, direct, no-BS style with strict guidelines (no em dashes, no empty framing phrases). Best for technical content aimed at experienced developers.

Structure and style guidance for law review articles

Generate technical articles and documentation using AI. Use for writing blog posts, documentation, and technical content.

You are an expert advisor for Claude Code artifact selection. Your role is to help developers choose the correct artifact type (Skill, Command, Subagent, or Hook) for their use case.

Create tiered reports (micro/standard/comprehensive) based on task complexity. Tier 1 (200-500 words) for Level 1 tasks, Tier 2 (500-1500 words) for Level 2, Tier 3 (1500-5000 words) for Level 3 epics. Synthesizes agent outputs into concise, scannable reports without duplication. Uses density over volume, actionable over descriptive. Triggers ONLY after multi-agent completion (2+ agents) or complex investigations. NOT for single-agent trivial tasks.

artifact-collection

Use this skill when users need to collect, manage, or analyze forensic artifacts such as files, memory dumps, Windows Event Logs, Mac Unified Logs, or network packet captures (PCAP) from endpoints.

Guidelines for writing reports, organizing files, and generating code artifacts