AI Agent & Automation Workflows

Add a Tauri splashscreen, loading screen, or startup screen to an app, covering configuration, custom splash HTML, styling, and closing the splash when ready. USE WHEN showing a loading or startup window before a Tauri app's main window is ready.

Implement Tauri system tray functionality including tray icon setup, tray menu creation, event handling, and runtime updates in the notification area. USE WHEN adding a menu-bar or system-tray icon, tray menu, or notification-area behavior to a Tauri app.

Shared reference for the agentic-ops cluster: the evidence-first operator loop (resolve surface → read live state → smallest reversible action → prove it → report exact status), the surface taxonomy, the status-word vocabulary, and the secrets/PII guardrails every operator spoke obeys. USE WHEN operating any live external surface — inbox, repo, tracker, billing, docs — or before any send/push/refund/mutation in this cluster.

Route a real-world operations task to the right skill among 16 agentic-ops specialists — email, messages, GitHub, Jira, Google Workspace, project flow, unified notifications, terminal/CI, knowledge base, customer + finance billing, automation audit, workspace-surface audit, social connections, and dashboards. USE WHEN an agent must operate, triage, or prove work on a live external surface (inbox, repo, tracker, billing, docs) but the user hasn't named the specific skill.

Shared reference for the ai-agents-meta cluster: the eval-first + default-deny-autonomy model every spoke turns on, plus shared conventions (the agent stack, cold-start briefs, cost routing tiers) and the gate/loop/cost matrix. USE WHEN wiring an autonomous loop, granting an agent tools, setting an eval gate, or routing by model cost — the interlocking rules every meta spoke shares.

Route an AI-agent engineering task to the right skill among 14 meta specialists — planning a multi-session build, decomposing a plan into an agent chain, orchestrating a squad, running an autonomous loop, auditing/debugging the agent stack, optimizing prompts, and controlling token/cost budget. USE WHEN a user is designing, building, operating, or hardening an LLM-agent system but hasn't named the specific concern.

Shared reference for the Astro cluster: the rendering-mode decision (static / on-demand SSR / hybrid + server islands), hydration directives, the Content Layer & collections model, astro:env / sessions / actions conventions, and SSR adapter selection. USE WHEN deciding how an Astro page renders or where data comes from — the cross-cutting model the Astro spokes share. Implementation depth lives in astro-framework.

Astro framework specialist for building fast, content-driven websites with islands architecture. Use when creating Astro components, configuring hydration (client:load/idle/visible/media), using server:defer (server islands), Content Layer API (glob/file loaders, live loaders), sessions, astro:env, i18n routing, actions, SSR adapters, view transitions, or integrating React/Vue/Svelte/Solid. Not for full-SPA frameworks (Next.js, Remix, SvelteKit).

Use when adding, fixing, or reviewing GSAP ScrollTrigger behavior in Astro pages, especially with view transitions, static routes, client scripts, reduced motion, cleanup, or browser-only lifecycle constraints.

Route an Astro task to the right spoke — building the site (components, islands/hydration, content, SSR, actions, i18n) or publishing a docs/wiki/press-kit site. USE WHEN working on an Astro project but the specific concern isn't named, or when deciding the rendering mode (static vs on-demand vs hybrid). For scroll/animation/video on an Astro page, hand off to the creative-frontend cluster.

Use when publishing or hardening an Astro docs/wiki/press-kit site with Markdown or MDX content, generated routes, artifact data, public copy QA, browser verification, Vercel or Cloudflare deploy checks, or README/docs media outputs.

Segment audiences by underlying needs, motivations, and behaviors to enable targeted strategy. USE WHEN a task matches the Craft workspace workflow for audience-segmentation-generator.

Shared reference for the backend-architecture cluster: the dependency-inversion boundary (domain → ports → adapters), the layering contract, REST/transport conventions, and the runtime/framework matrix. USE WHEN drawing a module boundary, designing an API, wiring an integration, or planning a deploy — the interlocking rules every backend spoke shares.

Route a backend task to the right skill among 8 server-side specialists — architecture boundaries (hexagonal/ports-and-adapters), REST API design, HTTP connector building, NestJS structure, MCP servers, deployment/CI-CD, and decision records. USE WHEN a user is designing, building, integrating, or shipping a backend service but hasn't named the specific concern.

Shared reference for the blockchain-web3 cluster: the adversarial on-chain threat model (immutable, anyone-can-call, MEV), checks-effects-interactions, oracle-manipulation resistance, token-decimals precision, and the non-advisory stance for trading/prediction-market work. USE WHEN writing, auditing, or reasoning about smart-contract / DeFi / on-chain code — the cross-cutting model every web3 spoke shares.

Route a blockchain/web3 task to the right specialist among six — Solidity AMM security, autonomous trading-agent security, EVM token-decimal correctness, Node Keccak-256 hashing, prediction-market oracle research, and the cross-cutting market/agent risk review. USE WHEN a user is building, auditing, or wiring an EVM contract, a crypto trading agent, or a prediction-market workflow but hasn't named the specific concern.

Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.

Set up Tauri CI/CD with GitHub Actions and tauri-action for cross-platform desktop builds. USE WHEN automating Tauri build, test, or release across Windows/macOS/Linux, configuring workflow triggers, or publishing signed releases.

Shared reference for the business-content cluster: the source-derived Voice Profile every lane reuses, the research/evidence substrate, the per-channel message contract, and the publish/market/fund/reach lane map. USE WHEN drafting any launch-, reputation-, or fundraising-sensitive content, building a Voice Profile, or planning multi-channel outbound — the interlocking conventions every spoke shares.

Route a business-content task to the right skill among 10 specialists — voice profiling, long-form articles, multi-platform content systems, SEO, market/competitor research, launch campaigns, investor decks/memos, investor outreach, lead intelligence, and social-graph ranking. USE WHEN a user is writing, marketing, fundraising, or doing outbound for a product or company but hasn't named the specific concern.

Call the Tauri v2 frontend from Rust via the event system, channels, and JavaScript evaluation. USE WHEN emitting events from Rust to the webview, streaming data over IPC channels, or pushing state changes from backend to frontend.

Call Rust backend functions from the Tauri v2 frontend with invoke and [tauri::command]. USE WHEN defining commands, passing arguments or return values across IPC, handling command errors, or wiring async frontend-to-Rust calls.

Use this skill to monitor a deployed URL for regressions after deploys, merges, or dependency upgrades.

Defines appetite, scope, no-go zones, and design before any prompts are written. Use when a goal is Medium or High complexity, requirements are unclear, scope needs bounding, or the user says "shape", "design", "brainstorm", "think through".