hashgraph-online/awesome-codex-plugins / plugins/beefiker/superloopy/skills/superloopy-frontend
superloopy-frontend
VerifiedUse only after explicit Codex `$superloopy:superloopy-frontend` or Claude Code `/superloopy:superloopy-frontend` invocation for supported screen-based application UI across browser-hosted Web, interactive deployed content-led Web, desktop, mobile/tablet, embedded/hybrid, Qt, custom-rendered, or mixed targets, such a task started with a leading `loopy` or `루피`, or an active Superloopy loop explicitly routing it here. Do not activate from UI, frontend, desktop, mobile, or framework vocabulary alone, or for TV, wearable, XR, automotive, game UI, TUI, static media/document artifacts, or non-UI work.
references/hybrid.md
View on GitHub# Hybrid Shell and Client Contract
Use this when a Web or custom-rendered client runs inside a native shell, or when multiple UI/runtime processes share one journey. Apply the shared UX contract plus the relevant desktop/mobile and Web references. Add the renderer reference only when a custom renderer actually owns pixels, semantics, text, or input; an ordinary DOM WebView does not inherit renderer proof merely because it is embedded.
## Ownership map
Name the owner of every boundary:
- the client owns document rendering and in-client interaction;
- the shell owns native windows/scenes, menus, pickers, permissions, accessibility integration, package lifecycle, and system handoff unless the inspected stack proves otherwise;
- a service or backend owns durable remote results; and
- the bridge owns serialization, authorization, cancellation, ordering, retries, and error translation across processes.
Map client, shell, service, document, and state owners for each journey. A WebView uses an OS/provider engine whose version and capability may vary; a bundled browser such as Chromium has a different update and security boundary. Do not treat them as interchangeable.
When multiple clients, shells, or presentation surfaces advertise the same product journey, add a capability reachability matrix. For every applicable capability, prove direct reachability on each promised surface or define an intentional handoff with a clear transition, return path, and preserved context/state; otherwise mark it not applicable with a concrete reason. Shared backend ownership or visual similarity does not prove that users can actually reach the capability from every advertised frontend.
## Bridge truth
Specify every IPC or bridge command by semantic input, validation, owner, result, failure, cancellation, lifetime, and observable state. A JavaScript handler, message receipt, spinner, or toast is not proof that the native or durable operation completed. Prevent duplicate submissions and stale replies; preserve enough context to recover after client reload, shell recreation, or service failure.
Keep privileged native operations behind a minimal authorized surface. Validate untrusted client data, avoid exposing raw filesystem or process capability, and prove that navigation or content injection cannot widen the bridge contract.
## Native and client evidence
Client proof cannot substitute for shell proof. Keep a **minimum regression floor** that builds and launches the real client and shell, executes the affected journey through the bridge, checks the resulting owner state, and covers the closest regression path. Add independent native picker, window, menu, permission, accessibility, package, update, and shutdown proof when that behavior is affected, claimed, release-critical, or selected by risk. Likewise, a native shell screenshot cannot prove client semantics, focus, text input, localization, or responsive rendering.
Record engine/provider/version, shell/runtime/version, OS/device, package channel, bridge mode, service state, and each artifact's owner. For a public surface deployed separately from the embedded client, evaluate its crawlability and Web evidence as a separate target.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |