Skill Store 33
LobeHub

LobeHub

@lobehub

56 skills · 84,229 GitHub stars

Website

Agent teammates that grow with you

LobeHub's skills help an AI agent work on agent infrastructure, including builtin tool manifests and executors, external agent adapters such as Claude Code and Codex, and tracing agent runs by operation ID to diagnose failed tool calls. The author also covers developer tooling, with skills for TypeScript and React code, public documentation under docs/, Harbor evaluation runs, and refactoring files over 1200 lines into cohesive modules.

Lobehub

56 skills · 84,229 stars · NOASSERTION

  • Acceptance End-to-end verification and self-evidence for a delivery in any repository, with or without a pre…
  • Add Model Provider Add an AI model provider to LobeHub, including runtime integration, model cards, configuration, b…
  • Add Setting Env Add server-side environment variables that control default values for user settings.
  • Agent Runtime Hooks Use for agent lifecycle hooks, tool mocks, intervention, sub-agent calls and context compression.
  • Agent Signal Use for Agent Signal sources, actions, policies, middleware, workflow handoff and deduplication.
  • Agent Testing Bot Use for real bot-channel acceptance in Discord, Slack, Telegram, WeChat/Weixin, Lark/Feishu, QQ o…
  • Agent Tracing Use for agent traces by operation ID (拉线上 tracing): failed tools, arguments/results, available to…
  • Agent Work Use for the Agent Work output registry: registration, deduplication, cards, skill providers, CLI…
  • Alint Ruleset Maintain LobeHub's model-backed alint rule set in packages/alint: author a rule, calibrate its fa…
  • Builtin Tool Use for LobeHub builtin agent tools: manifests, executors, runtimes, inspectors, renders, streami…
  • Chat Sdk Use for multi-platform bots built with chat SDK: webhooks, mentions, slash commands, cards, modal…
  • Cleanup Git Worktrees Use for stale-worktree, Git registration and branch audits.
  • Cli LobeHub CLI (@lobehub/cli) development guide — commands, subcommands, architecture.
  • Compose Atoms Use for splitting heavy domains into capabilities (原子组件) across page, portal, share or micro-app…
  • Data Fetching Architecture Use for client APIs, SWR hooks, cache invalidation, async errors, useEffect migration, home first…
  • Db Migrations Use for Drizzle migration rollout, online indexes, backfills, idempotent SQL and migration regene…
  • Debug Frontend With Browser Use for intermittent UI, stale state, ordering, navigation or browser-only bugs.
  • Debug Package Use for debug() logging, lobe-* namespaces, DEBUG/localStorage.debug configuration and log format…
  • Deep Review Use for independent PR, diff or branch review; not explanations.
  • Design Prototype Use for interactive HTML prototypes (交互原型) with the real LobeHub UI stack.
  • Desktop Electron desktop development guide — IPC handlers, controllers, preload scripts, window/menu mana…
  • Desktop Security Update Inspect, mark, or revoke vulnerable LobeHub Desktop versions through the existing release workflo…
  • Docs Changelog Use for EN/ZH website product changelogs in docs/changelog/*.mdx.
  • Drizzle Use for Drizzle schemas and queries: tables, indexes, relations, joins and inferred types.
  • Full Text Search Use for product search: FtsSearchRepo, pg_search/pg_like/Elasticsearch, mapping migrations, proje…
  • Heterogeneous Agent Use for external-agent launchers and execution identity, Claude Code/Codex adapters, IPC, event m…
  • Hotkey Use for keyboard shortcuts, registration, key combinations, scope, conflicts and shortcut tooltips.
  • I18N Use for user-facing strings and react-i18next locale keys, namespaces, interpolation, translation…
  • Linear Use for Linear issues, LOBE-xxx links, status updates, completion comments and sub-issue trees.
  • Llm Generation Use for application prompts, generateObject/generateText, model selection and generation tracing.
  • Lobe Design Single entry for LobeHub UI design work.
  • Modal Use for modals, dialogs and confirmations with createModal, confirmModal, ModalHost or base-ui mo…
  • Model Bank Metadata Use for model knowledgeCutoff, family and generation metadata: onboarding, corrections, research…
  • Pr Create a PR for the current branch (targets `canary` by default), including splitting one cross-l…
  • Product Design Use for new surfaces, redesigns and vague product asks: establish user tasks and business meaning.
  • Project Overview Use for the OSS repository map, code-layer lookup, apps/packages/src ownership and business stubs.
  • React Use for TSX components, UI libraries, styling, state locality, layout, render performance and mem…
  • Response Compliance Use for OpenResponses/Response API compliance tests, endpoint schema failures and test runs.
  • Run Eval Harbor Run and diagnose existing Harbor or FrontierHarness evaluations against local production LobeHub…
  • Skills Audit Audit .agents/skills SKILL.md files.
  • Source Layout Use for where a file lives, how it is named, where its tests go, and how to split a source or tes…
  • Spa Routes Use for SPA routes and page segments: Web/desktop/mobile/popup routers, redirects and src/routes-…
  • Split Large File Refactor a source file over 1200 lines into a directory of cohesive modules without changing beha…
  • Split Micro App Use for standalone micro apps: React Router SSR/SSG, Cloud overlays, Workers, CDN/R2, SEO/OG, gat…
  • Store Data Structures Explicit compatibility entry for Zustand data-shape guidance.
  • Task Manages a LobeHub task through the `lh task` CLI via runCommand: view task instructions and activity
  • Testing Use for Vitest tests, mocks, coverage and failing-test diagnosis.
  • Testing Heterogeneous Agents Manually runs the live LobeHub official-provider compatibility matrix across Claude Code, Codex,…