Agent skills by lobehub

Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.

lobehub/lobehub

Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.

lobehub/lobehub

Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.

lobehub/lobehub

Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.

lobehub/lobehub

Guides building LobeHub builtin agent tools, from the manifest and execution runtime to executors, chat UI renders and registry wiring.

lobehub/lobehub

Build UI with the LobeHub design ecosystem — @lobehub/ui (plus its base-ui, chat, mobile, awesome, brand, mdx, i18n namespaces), @lobehub/icons, @lobehub/charts, @lobehub/fluent-emoji and…

lobehub/lobe-ui

Explains how LobeHub client code fetches data through services, SWR store hooks and cache keys, and when to avoid useEffect fetching or duplicated state.

lobehub/lobehub

Guides work on LobeHub's own product search: the shared search repository, provider choice, Elasticsearch mappings, change syncing and reindexing.

lobehub/lobehub

Add or modify icon keyword mappings for providers, models, or agents in lobe-icons.

lobehub/lobe-icons

Local browser verification for the lobe-ui component library and documentation site.

lobehub/lobe-ui

Runs existing Harbor evaluation jobs against a local LobeHub build or LobeHub Cloud, with preflight checks, resume support, and failure triage.

lobehub/lobehub

Set up and author a documentation site with @lobehub/docs-kit (the lobedocs CLI, React Router + Vite static docs used by ui.lobehub.com).

lobehub/lobe-ui

Implementation patterns for Upstash Workflow and QStash handlers in the LobeHub codebase: dry runs, fan-out chunking and single-item execution.

lobehub/lobehub

Conventions for Zustand stores in LobeHub: list and detail state shapes, public, internal and dispatch actions, reducers, optimistic updates and naming rules.

lobehub/lobehub

Registers lifecycle hooks on an agent run to observe, mock or intervene at each step, dispatching them in the order they were registered.

lobehub/lobehub

Extends a project's acceptance process to real chat bot channels: Discord, Slack, Telegram, WeChat, Lark, QQ, and iMessage on macOS.

lobehub/lobehub

Explains how LobeHub records Works, durable records of what an agent produced, covering registration, deduplication, versions, cards, type adapters and share-visitor access scopes.

lobehub/lobehub

Builds chat bots once for Slack, Teams, Google Chat, Discord, GitHub and Linear with the Chat SDK, covering event handlers, cards, modals, streaming and state adapters.

lobehub/lobehub

Splits a heavy front-end domain into capability atoms that each host imports separately, sinking state into each atom instead of adding mode or readOnly flags.

lobehub/lobehub

Covers schema conventions and safe rollout for Drizzle database migrations: online indexes, backfills, idempotent SQL and fixing regeneration or rebase conflicts.

lobehub/lobehub

Runs an independent, multi-dimension review of a PR, diff or branch with separate reviewers and adversarial verification, in a light or a deep multi-agent mode.

lobehub/lobehub

Writes bilingual English and Chinese product changelog pages for docs/changelog, with date-based file names, frontmatter rules and a factual, user-first tone.

lobehub/lobehub

Style guide for Drizzle ORM schemas and queries in LobeHub: file layout, naming, timestamp helpers, primary keys, indexes, relations and inferred types.

lobehub/lobehub

Walks through adding a keyboard shortcut to LobeHub: the id type, default registration, translation text, the hook and an optional tooltip, plus scope and conflict advice.

lobehub/lobehub

Rules for adding and editing LobeHub's user-facing strings with react-i18next: flat dot-notation keys, the default locale folder, namespaces and when to run bun run i18n.

lobehub/lobehub

Handles Linear issues for the team: reading details and images, checking sub-issues, marking progress, labeling AI-created issues and writing completion comments.

lobehub/lobehub

Implements business-facing LLM calls as explicit, traceable workflows, keeping prompt versions, model policy, structured output and tracing scenarios in separate places.

lobehub/lobehub

Shows how to build modals, dialogs and confirmations in LobeHub with the base-ui imperative API (createModal, confirmModal, ModalHost) instead of declarative Modal components.

lobehub/lobehub

Fills and maintains the knowledgeCutoff, family and generation fields on model cards in LobeHub's model bank, from a single new model up to repo-wide backfills.

lobehub/lobehub

Creates a pull request for the current branch against canary, or splits a cross-layer branch into ordered stacked PRs so backend changes merge before their callers.

lobehub/lobehub

A map of the LobeHub open-source repository: tech stack, monorepo layout, where each code layer lives and who owns apps, packages and src.

lobehub/lobehub

Runs the official OpenResponses compliance test suite against a local or remote Response API endpoint and helps diagnose schema and authentication failures.

lobehub/lobehub

Audits a project's .agents/skills folder for duplicate, overlapping, stale or broken skills and suggests merge or delete candidates, weekly or after skill changes.

lobehub/lobehub

Explains LobeHub's split between src/routes page segments and src/features domain code, and where router config, redirects and platform adapters belong.

lobehub/lobehub

A user-invoked check that every official model the server advertises works through six external CLI agents, from Claude Code and Codex to TRAE, in a live test matrix.

lobehub/lobehub

Conventions for LobeHub's server tRPC routers: file locations, middleware that injects models into ctx, procedure patterns, aggregated detail endpoints and return shapes.

lobehub/lobehub

Adds an AI model provider to LobeHub end to end: runtime integration, model cards, configuration, branding and documentation, or documentation-only updates.

lobehub/lobehub

Guides building event-driven background work for LobeHub agents, with sources, signals, actions, policies, workflow handoff and deduplication.

lobehub/lobehub

Explains how the LobeHub command line tool is built and organized, with its command groups, architecture and per-area reference notes for adding or changing commands.

lobehub/lobehub

Traces intermittent UI, stale state, ordering and navigation bugs through a browser to find the first boundary where correct data becomes wrong.

lobehub/lobehub

Walks through adding features to the LobeHub Electron desktop app: controllers, IPC types, preload exposure, renderer services, store actions and tests.

lobehub/lobehub

Helps debug and extend LobeHub's pipeline for external Claude Code and Codex agents: drivers, adapters, event mapping, sessions, persistence and tool-call chains.

lobehub/lobehub

Frames new surfaces, redesigns and vague product requests by grounding the business model and the user's task before any layout, in discover, frame or materialize modes.

lobehub/lobehub

Sets out how to write React components in LobeHub: which styling approach to use, which component libraries to prefer and in what order.

lobehub/lobehub

Explains how to write and run Vitest tests in the LobeHub monorepo: single-file commands, mocking rules, database model tests and regression tests for fixes.

lobehub/lobehub

Applies LobeHub's four design values and per-module interaction checklists when building or reviewing user-facing flows, covering behavior over time rather than visual style.

lobehub/lobehub

Runs a repeatable UX review of one screen against the Designing Interfaces pattern language and LobeHub's ux checklists, using static, visual and dynamic layers.

lobehub/lobehub

Inspects LobeHub agent execution snapshots by operation ID: failed tool calls, arguments and results, available tools, LLM calls and the surrounding context.

lobehub/lobehub