Add documentation for a new AI provider — usage docs, env vars, Docker config, image resources.
Add server-side environment variables that control default values for user settings.
Agent runtime lifecycle hooks. Use for before/after tool or step hooks, tool mocks, human intervention, sub-agent calls, context compression, evals, tracing, callAgent, or lifecycle events.
Build or extend LobeHub Agent Signal pipelines. Use for signal sources, signal/action types, policies, middleware, workflow handoff, dedupe, scope behavior, or observability.
Bot-channel end-to-end verification for LobeHub — drives the real native chat apps (Discord / Slack / Telegram / WeChat / Lark / QQ / iMessage) via osascript or the iMessage bridge, on macOS. Extends the generic agent-testing skill for bot surfaces. Triggers on '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'.
Agentic end-to-end testing for any project: backend verification via the project CLI, frontend verification via agent-browser (web), and desktop verification via CDP (Electron). Drives the real surface, captures visually confirmed evidence, and publishes a structured report to the LobeHub verify platform. Triggers on 'cli test', 'test with cli', 'verify with cli', 'backend test with cli', 'local test', 'test in electron', 'test desktop', 'manual test', 'test report', or any local end-to-end verification task.
Agent tracing CLI for execution snapshots. Use for agent-tracing, traces, snapshots, LLM call inspection, context engine data, agent step analysis, execution debugging, or pulling remote/production traces ("拉线上 tracing") by operation id. Also the first stop for debugging agent tool calls — wrong or missing tool_calls, unexpected tool arguments or results, which tools were available at a step, or why a tool ran where it did.
Agent Work registry (works / work_versions): how agent outputs — github/linear entities, files, documents, tasks — get registered, deduped, and rendered as cards, and how to extend it with a new skill provider, a new shell CLI scanner, or a new Work type.
Build LobeHub builtin tool packages. Use when adding agent-callable tools, manifests, executors, runtimes, inspectors, renders, placeholders, streaming, interventions, portals, or tool registries.
Build multi-platform chat bots with the chat SDK. Use for Slack, Teams, Google Chat, Discord, GitHub, Linear bots, webhooks, mentions, slash commands, cards, modals, or streaming responses.
LobeHub CLI (@lobehub/cli) development guide — commands, subcommands, architecture.
LobeHub data-fetching pipeline guide. Use for service layer, Zustand store, SWR, lambdaClient, useClientDataSWR, useFetchXxx hooks, or migrating useEffect fetches.
Use for database rollout strategy, Drizzle migrations, online index creation, data backfills, migration regeneration, sequence conflicts after rebase, idempotent SQL review, or migration renames.
Frontend diagnosis extension for agent-testing. Use for intermittent rendering, ordering, stale-state, navigation, virtual-list, React/Zustand, optimistic-update, refresh-dependent, or browser-only failures where the first broken boundary may be DOM, component input, derived state, client cache, network data, or a pure transformation. Before any browser, Electron, or live-app interaction, this skill must load and follow agent-testing; it adds only boundary tracing, minimal fixture replay, and regression attribution.
LobeHub debug package and log namespace guide. Use when adding debug() logging, choosing lobe-* namespaces, troubleshooting DEBUG output, localStorage.debug, or log format specifiers.
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): independent dimension coverage, adversarial verification, and global duplicate consolidation before reporting.
Produce an interactive single-file HTML design prototype using the REAL LobeHub design system (@lobehub/ui + antd + antd-style tokens) with production-style React — no build step, opens directly in a browser. Use when asked for a design prototype / interactive mockup / 交互原型 / 出个原型 / 设计稿 HTML for a page or flow, or to explore a redesign before committing to implementation.
Electron desktop development guide — IPC handlers, controllers, preload scripts, window/menu management.
Write website changelog pages under docs/changelog/*.mdx. Use for EN/ZH product update posts, changelog posts, update-log copy, or docs changelog edits; not GitHub Release notes.
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.
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.
Linear issue management. Use for LOBE-xxx issues, Linear links, PRs referencing Linear, retrieving issues, updating status, completion comments, or sub-issue trees.
LobeHub imperative modal conventions. Use when creating or migrating modals, dialogs, popups, confirm flows, ModalHost wiring, createModal, confirmModal, useModalContext, or base-ui modal APIs.
Backfill and maintain model-bank metadata (knowledgeCutoff, family, generation). Use when adding models, fixing cutoff/family data, running a metadata sweep across aiModels providers, or researching official knowledge cutoffs.
Create a PR for the current branch (targets `canary` by default), including splitting one cross-layer branch into ordered stacked PRs so a lower layer (db / shared package / server TRPC) merges before its callers (desktop / CLI / UI). Use when the user asks to create / submit a PR, or to split a branch because clients call a server contract that isn't on the trunk yet. Triggers on 'pr', 'create pr', 'submit pr', 'open a PR', 'pull request', 'split this PR', 'stacked PR', 'backend should merge first', '提 PR', '提个 PR', '新建 PR', '拆 PR', '后端先合', '分层合并'.
Turn a vague product ask ("this page feels wrong", "we need a team view") into a grounded, shippable design by establishing business semantics and the user task before proposing a surface. Use when scoping a new surface, redesigning an existing one, or deciding what a feature should be. Not for auditing a built screen (ux-audit) or choosing visual details (ux).
LobeHub open-source monorepo architecture map. Use when locating code layers, understanding apps/packages/src layout, business stubs, project structure, or onboarding to the repository.
LobeHub React component conventions. Use when editing TSX UI, choosing base-ui vs @lobehub/ui vs antd, styling with antd-style, routing, desktop variants, layouts, or component state.
OpenResponses API compliance testing. Use for Response API endpoint tests, compliance runs, schema debugging, response api test, or openresponses test tasks.
Audit .agents/skills SKILL.md files. Use for recurring checks of duplicate, overlapping, stale, inconsistent, or broken skills and merge/delete candidates.
LobeHub SPA route architecture. Use when editing src/routes, src/features delegation, desktop/mobile/popup router configs, .desktop variants, route segments, redirects, or new pages.
LobeHub Zustand store data-shape patterns. Use when designing store state, list/detail splits, normalized maps, reducers, messagesMap, topicsMap, or choosing shared type sources.
Vitest testing guide. Use when writing or updating tests, fixing failing tests, improving coverage, debugging test issues, or setting up mocks.
TRPC router development guide. Use when creating or modifying apps/server/src/routers, adding procedures, or implementing server-side API endpoints.
LobeHub TypeScript style and type-safety guide. Use when editing TS/TSX/MTS, fixing types, choosing interface vs type, avoiding any/object, import type, async flow, or ts-expect-error.
LobeHub Upstash Workflow and QStash guide. Use for async workflows, process/paginate/execute fan-out, serve handlers, context.run/call/sleep, or workflow triggers.
Audit a page / surface against the Designing Interfaces pattern language + the ux skill checklists, then land findings. Three layers — static (code), visual (screenshots), dynamic (automated user journey + perf). Use to run a repeatable, standards-based UX review of one screen.
LobeHub product design values / principles / checklists. Use whenever the work touches user-interface features or implementation — designing or building any user-facing flow — to get better UX results.