chat-sdk
lobehub/lobehub/.agents/skills/chat-sdk/SKILL.md
Use for multi-platform bots built with chat SDK: webhooks, mentions, slash commands, cards, modals and streaming.
Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
lobehub/lobehub/.agents/skills/chat-sdk/SKILL.md
Use for multi-platform bots built with chat SDK: webhooks, mentions, slash commands, cards, modals and streaming.
lobehub/lobehub/.agents/skills/cleanup-git-worktrees/SKILL.md
Use for stale-worktree, Git registration and branch audits. Managed removal uses the repo lifecycle.
lobehub/lobehub/.agents/skills/cli/SKILL.md
LobeHub CLI (@lobehub/cli) development guide — commands, subcommands, architecture.
lobehub/lobehub/.agents/skills/compose-atoms/SKILL.md
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.
lobehub/lobehub/.agents/skills/data-fetching-architecture/SKILL.md
Use for client APIs, SWR hooks, cache invalidation, async errors, useEffect migration, home first paint and persistent caches.
lobehub/lobehub/.agents/skills/db-migrations/SKILL.md
Use for Drizzle migration rollout, online indexes, backfills, idempotent SQL and migration regeneration or rebase conflicts.
lobehub/lobehub/.agents/skills/debug-frontend-with-browser/SKILL.md
Use for intermittent UI, stale state, ordering, navigation or browser-only bugs. Extends acceptance with boundary tracing and regression diagnosis.
lobehub/lobehub/.agents/skills/debug-package/SKILL.md
Use for debug() logging, lobe-* namespaces, DEBUG/localStorage.debug configuration and log formatting.
lobehub/lobehub/.agents/skills/deep-review/SKILL.md
Use for independent PR, diff or branch review; not explanations. Full multi-agent review requires an explicit deep-review request.
lobehub/lobehub/.agents/skills/design-prototype/SKILL.md
Use for interactive HTML prototypes (交互原型) with the real LobeHub UI stack. Excludes production UI implementation.
lobehub/lobehub/.agents/skills/desktop/SKILL.md
Electron desktop development guide — IPC handlers, controllers, preload scripts, window/menu management.
lobehub/lobehub/.agents/skills/docs-changelog/SKILL.md
Use for EN/ZH website product changelogs in docs/changelog/*.mdx. Excludes GitHub Release notes.
lobehub/lobehub/.agents/skills/drizzle/SKILL.md
Use for Drizzle schemas and queries: tables, indexes, relations, joins and inferred types. Rollout belongs to db-migrations.
lobehub/lobehub/.agents/skills/full-text-search/SKILL.md
Use for product search: FtsSearchRepo, pg_search/pg_like/Elasticsearch, mapping migrations, projections, Outbox sync, reindexing and performance. Excludes agent web search.
lobehub/lobehub/.agents/skills/heterogeneous-agent/SKILL.md
Use for Claude Code/Codex external-agent adapters, IPC, event mapping, sessions, persistence and tool-call chains.
lobehub/lobehub/.agents/skills/hotkey/SKILL.md
Use for keyboard shortcuts, registration, key combinations, scope, conflicts and shortcut tooltips.
lobehub/lobehub/.agents/skills/i18n/SKILL.md
Use for user-facing strings and react-i18next locale keys, namespaces, interpolation, translations or bun run i18n.
lobehub/lobehub/.agents/skills/linear/SKILL.md
Use for Linear issues, LOBE-xxx links, status updates, completion comments and sub-issue trees.
lobehub/lobehub/.agents/skills/llm-generation/SKILL.md
Use for application prompts, generateObject/generateText, model selection and generation tracing. Excludes provider adapters and agent snapshots.
lobehub/lobehub/.agents/skills/modal/SKILL.md
Use for modals, dialogs and confirmations with createModal, confirmModal, ModalHost or base-ui modal APIs.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.