model-bank-metadata
Use for model knowledgeCutoff, family and generation metadata: onboarding, corrections, research and bulk backfills.
db-migrations
Use for Drizzle migration rollout, online indexes, backfills, idempotent SQL and migration regeneration or rebase conflicts.
pr
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'.
ux
Use for product design principles and UX checks when designing or implementing user-facing flows.
cli
LobeHub CLI (@lobehub/cli) development guide — commands, subcommands, architecture.
i18n
Use for user-facing strings and react-i18next locale keys, namespaces, interpolation, translations or bun run i18n.
modal
Use for modals, dialogs and confirmations with createModal, confirmModal, ModalHost or base-ui modal APIs.
react
Use for TSX components, UI libraries, styling, state locality, layout, render performance and memoization.
hotkey
Use for keyboard shortcuts, registration, key combinations, scope, conflicts and shortcut tooltips.
linear
Use for Linear issues, LOBE-xxx links, status updates, completion comments and sub-issue trees.
drizzle
Use for Drizzle schemas and queries: tables, indexes, relations, joins and inferred types. Rollout belongs to db-migrations.
testing
Use for Vitest tests, mocks, coverage and failing-test diagnosis.
zustand
Use for Zustand stores: list/detail splits, state type sources, slices, actions, reducers, selectors, optimistic updates and class-action composition.
chat-sdk
Use for multi-platform bots built with chat SDK: webhooks, mentions, slash commands, cards, modals and streaming.
ux-audit
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.
agent-work
Use for the Agent Work output registry: registration, deduplication, cards, skill providers, CLI scanners and Work types.
spa-routes
Use for SPA routes and page segments: Web/desktop/mobile/popup routers, redirects and src/routes-to-features boundaries.
typescript
Use for TypeScript style and type safety when editing TS/TSX/MTS, including imports, async code and error suppression.
deep-review
Use for independent PR, diff or branch review; not explanations. Full multi-agent review requires an explicit deep-review request.
trpc-router
Use for server TRPC routers, procedures and API endpoints in apps/server/src/routers.
agent-signal
Use for Agent Signal sources, actions, policies, middleware, workflow handoff and deduplication.
builtin-tool
Use for LobeHub builtin agent tools: manifests, executors, runtimes, inspectors, renders, streaming and intervention.
skills-audit
Audit .agents/skills SKILL.md files. Use for recurring checks of duplicate, overlapping, stale, inconsistent, or broken skills and merge/delete candidates.
agent-tracing
Use for agent traces by operation ID (拉线上 tracing): failed tools, arguments/results, available tools, execution location, LLM calls and context.
compose-atoms
Use for splitting heavy domains into capabilities (原子组件) across page, portal, share or micro-app hosts, sinking state (状态下沉) and replacing mode/readOnly flags. Simple component splits: react.
db-migrations
Use for Drizzle migration rollout, online indexes, backfills, idempotent SQL and migration regeneration or rebase conflicts.
docs-changelog
Use for EN/ZH website product changelogs in docs/changelog/*.mdx. Excludes GitHub Release notes.
llm-generation
Use for application prompts, generateObject/generateText, model selection and generation tracing. Excludes provider adapters and agent snapshots.
product-design
Use for new surfaces, redesigns and vague product asks: establish user tasks and business meaning. Built-screen audits and visual polish have separate skills.
add-setting-env
Add server-side environment variables that control default values for user settings.
split-micro-app
Use for standalone micro apps: React Router SSR/SSG, Cloud overlays, Workers, CDN/R2, SEO/OG, gateway routes, previews, Docker integration and SSR bundle isolation.
version-release
Version release workflow — release process and GitHub Release notes (not docs/changelog pages).
design-prototype
Use for interactive HTML prototypes (交互原型) with the real LobeHub UI stack. Excludes production UI implementation.
full-text-search
Use for product search: FtsSearchRepo, pg_search/Elasticsearch, mapping migrations, projections, Outbox sync, reindexing and performance. Excludes agent web search.
project-overview
Use for the OSS repository map, code-layer lookup, apps/packages/src ownership and business stubs.
upstash-workflow
Use for Upstash Workflow/QStash handlers, triggers, durable steps and async fan-out.
agent-testing-bot
Use for real bot-channel acceptance in Discord, Slack, Telegram, WeChat/Weixin, Lark/Feishu, QQ or iMessage on macOS. Extends acceptance with native chat apps.
add-model-provider
Add an AI model provider to LobeHub, including runtime integration, model cards, configuration, branding, documentation, and acceptance. Also use for provider documentation updates; adding models to an existing provider does not require a new provider integration.
agent-runtime-hooks
Use for agent lifecycle hooks, tool mocks, intervention, sub-agent calls and context compression.
heterogeneous-agent
Use for Claude Code/Codex external-agent adapters, IPC, event mapping, sessions, persistence and tool-call chains.
model-bank-metadata
Use for model knowledgeCutoff, family and generation metadata: onboarding, corrections, research and bulk backfills.
response-compliance
Use for OpenResponses/Response API compliance tests, endpoint schema failures and test runs.
cleanup-git-worktrees
Use for stale-worktree, Git registration and branch audits. Managed removal uses the repo lifecycle.
data-fetching-architecture
Use for client APIs, SWR hooks, cache invalidation, async errors, useEffect migration, home first paint and persistent caches.
debug-frontend-with-browser
Use for intermittent UI, stale state, ordering, navigation or browser-only bugs. Extends acceptance with boundary tracing and regression diagnosis.
testing-heterogeneous-agents
Manually runs the live LobeHub official-provider compatibility matrix across Claude Code, Codex, Grok Build, Kimi Code, Pi, and TRAE when explicitly invoked by the user.
Page 2 of 2 · 96 results