lobehub

Agentic end-to-end testing for LobeHub: backend verification via the CLI, frontend verification via agent-browser (Electron), full-stack verification in the browser, and bot-channel verification via osascript. Local-first today, designed to extend to cloud automation. Triggers on 'cli test', 'test with cli', 'verify with cli', 'backend test with cli', 'local test', 'test in electron', 'test desktop', 'test bot', 'bot test', 'test in discord', 'test in telegram', 'test in slack', 'test in wechat', 'test in weixin', 'test in lark', 'test in feishu', 'test in qq', 'manual test', 'osascript', 'test report', or any local end-to-end verification task.

LobeHub Drizzle ORM schema and query style. Use for pgTable schemas, indexes, joins, inferred types, db.select/db.query, schema fields, foreign keys, junction tables, or postgres query patterns.

Add server-side environment variables that control default values for user settings.

Build LobeHub builtin tool packages. Use when adding agent-callable tools, manifests, executors, runtimes, inspectors, renders, placeholders, streaming, interventions, portals, or tool registries.

Multi-dimensional code review. Use when the user asks to review, evaluate, or audit a PR, diff, branch, or pasted change — including informal review asks like "look at this change for problems" — via light mode: inline review against the dimension quick checklists. Not for explain-only questions about what a change does or why. Deep mode runs only on explicit invocation (/deep-review): one review subagent per dimension plus independent verification subagents that falsify findings before reporting.

Implement or debug LobeHub heterogeneous agents. Use for Claude Code/Codex adapters, external CLI agents, event mapping, IPC, persistence, tool-call chains, sessions, traces, or adapter bugs.

Add or edit LobeHub keyboard shortcuts. Use for HotkeyEnum, HOTKEYS_REGISTRATION, combineKeys, useHotkeyById, tooltip hotkeys, shortcut scope, conflicts, or Cmd/Ctrl key combos.

LobeHub i18n with react-i18next. Use for user-facing strings, locale keys, namespaces, useTranslation, t(), interpolation, zh-CN/en-US previews, hardcoded UI copy, or bun run i18n.

Add or modify icon keyword mappings for providers, models, or agents in lobe-icons. Use this whenever a task involves mapping a provider/model id to an icon, adding a new entry to ModelProvider enum or providerMappings/modelMappings/agentMappings, or fixing a provider/model that renders the fallback (default) icon in LobeHub. Trigger even if the request only says "add icon for X provider" or references a Linear issue about icon keyword mapping — the actual icon component usually already exists; only the mapping is missing.

Local UI automation testing for the lobe-ui component library. Uses agent-browser CLI to drive the dumi dev server (default http://localhost:8000) via Chrome DevTools Protocol — navigate to component demo pages, interact with components, capture screenshots, and verify rendering. Triggers on 'local test', 'ui test', 'verify component', 'test component', 'test in browser', 'visual check', 'screenshot demo', or any UI verification task.

Command-line tool for managing LobeHub services. Use this skill when you need to manage AI agents, knowledge bases, conversations, files, models, providers, bot integrations, or any LobeHub Cloud resources. Covers authentication, agent execution, content generation, memory management, and device connectivity.