AkaraChen

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

Adapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints, fluid layouts, and touch targets. Use when the user mentions responsive design, mobile layouts, breakpoints, viewport adaptation, or cross-device compatibility.

Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. Use when the user mentions adding animation, transitions, micro-interactions, motion design, hover effects, or making the UI feel more alive.

Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability. Use when the user says the design looks bland, generic, too safe, lacks personality, or wants more visual impact and character.

Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.

Add strategic color to features that are too monochromatic or lack visual interest, making interfaces more engaging and expressive. Use when the user mentions the design looking gray, dull, lacking warmth, needing more color, or wanting a more vibrant or expressive palette.

Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.

Release a macOS desktop app version through GitHub Releases, watch the GitHub Actions build until completion, download the macOS DMG asset, mount it, copy the app into /Applications, detach the image, launch the installed app, and verify the installed version. Use when the user asks to release a version, ship a beta, watch CI, download a DMG from GitHub Releases, install a macOS app artifact, or continue a release/install workflow.

Create a GitHub release with auto-generated changelog for the 2code Tauri desktop app. Use when the user wants to create a new release, publish a version, generate a changelog, build and ship a DMG, or run the release pipeline. Handles the full pipeline: reads version from src-tauri/tauri.conf.json, builds DMG via bun tauri build, generates changelog from conventional commits since the last release, creates a GitHub draft release, uploads the DMG artifact, and publishes.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

Archive multiple completed changes at once. Use when archiving several parallel changes.

Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

Apply Eric's design standards. Use when designing, implementing, or reviewing UI visuals — landing pages, app UI, error feedback, icons, headings, page overscroll, or when choosing a visual direction from a design DNA spec in Eric's style.

Apply Eric's GitHub pull request review operations. Use when operating on GitHub PR changed-file review state, marking safe test-only files viewed, preparing a GitHub PR for review, or using gh GraphQL review mechanics.

Review code using Eric's standards. Use when the user asks for review, code review, frontend review, backend review, desktop review, React review, architecture review, PR review, or asks whether code matches Eric's style; prioritize concrete bugs, risks, overengineering, style drift, and missing focused tests.

Apply Eric's test-writing standards. Use when deciding whether to add tests, choosing unit vs integration coverage, writing focused regression or correctness tests, reviewing tests, or explaining test strategy.

Apply Eric's frontend coding standards. Use when implementing, refactoring, or reviewing frontend web/app UI code, TanStack Query usage, feature-folder organization, styling boundaries, app-vs-website UI decisions, frontend state, or frontend tests in Eric's style. For React-specific components, hooks, providers, memoization, effects, or local reducer work, also use $eric-react.

Stress-test product, technical, and domain-modeling plans before implementation in Eric's style. Use when the user asks to grill, challenge, validate, or sharpen a plan/design/domain model; when terminology, boundaries, invariants, or ADR-worthy decisions are fuzzy; or before implementing a feature where shared understanding matters.

Apply Eric's browser end-to-end testing standards. Use when a task needs a real browser, UI smoke test, screenshot capture, browser bug reproduction, Dockerized browser test run, or agent-browser based verification.

Apply Eric's quality-control standards. Use when setting up or fixing formatter, linter, type-check, compile, test, dependency, security, or CI gates; reproducing quality failures; or choosing boring project quality checks.

Release Angel Engine desktop builds through the repository's GitHub Actions workflow. Use when the user asks to publish, cut, ship, tag, or release an Angel Engine desktop version, including beta/prerelease and stable releases. Enforces the required order: update desktop/package.json version first, commit it, create and push the release tag, then let or trigger the desktop release Action, and verify signed/notarized artifacts and updater metadata.

Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include "cross-platform desktop", "Electron alternative", "Tauri vs native", "WebView wrapper", "near-native performance", "Raycast architecture", "WebKit/WebView2 quirks", "WKWebView", "system tray app", "global hotkey app", "launcher app". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.

Context for working on the next AI SDK major release. Only use when explicitly invoked by the user (e.g. via '/major-version-mode'). Do NOT trigger autonomously based on task content.

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

Idiomatic Effect-TS patterns for TypeScript functional programming. USE THIS SKILL WHEN: Writing new Effect services or layers, debugging Effect type errors (layer composition, error types), choosing between Effect patterns, setting up Effect testing. TRIGGERS ON: 'effect pattern', 'Layer.provide', 'Context.Tag', 'effect service', 'effect error', 'effect test', 'idiomatic effect'. NOT FOR: general TypeScript without Effect.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Review code and produce Guided Review artifacts. Use when the user asks for review, code review, PR review, architecture review, a guided review, PR walkthrough, line map, suggested reading order, or a structured PR review summary with risk and verification focus; prioritize concrete bugs, risks, overengineering, style drift, and missing focused tests.

Generate hierarchical AGENTS.md and ensure paired CLAUDE.md files for codebases. Creates root AGENTS.md + CLAUDE.md plus complexity-scored subdirectory files. Use when user asks to "generate AGENTS.md files", "create codebase knowledge base", "run /init-deep", or wants comprehensive project documentation. Supports update mode (default) and --create-new flag to regenerate from scratch.

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.

Benchmark the handover mess command on real-world open source projects. Use when the user wants to test mess transformations at scale, benchmark performance on large repos, or validate mess output quality. Triggers on "benchmark mess", "test mess on real projects", "run mess on fixtures", or similar requests.

Create and configure dox.yaml files for the Docker Compose wrapper CLI. Use when the user asks to: (1) Create or set up a dox.yaml configuration file, (2) Add profiles, aliases, or hooks to their Docker Compose setup, (3) Configure environment-specific compose files like dev/prod/staging, (4) Set up automation hooks for container lifecycle events, (5) Define command shortcuts for common Docker Compose operations. The dox.yaml file is the project-local configuration for the 'dox' CLI tool that simplifies multi-file Docker Compose setups.