lobehubSkillmodel-bank-metadata
lobehub/lobehub/.agents/skills/model-bank-metadata/SKILL.md
Use for model knowledgeCutoff, family and generation metadata: onboarding, corrections, research and bulk backfills.
Claude skills and agent skills
Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Most stars first · from page 34Worked for most · soon
lobehubSkilllobehubSkillproduct-design
lobehub/lobehub/.agents/skills/product-design/SKILL.md
Use for new surfaces, redesigns and vague product asks: establish user tasks and business meaning. Built-screen audits and visual polish have separate skills.
lobehubSkillproject-overview
lobehub/lobehub/.agents/skills/project-overview/SKILL.md
Use for the OSS repository map, code-layer lookup, apps/packages/src ownership and business stubs.
lobehubSkillpr
lobehub/lobehub/.agents/skills/pr/SKILL.md
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'.
lobehubSkillreact
lobehub/lobehub/.agents/skills/react/SKILL.md
Use for TSX components, UI libraries, styling, state locality, layout, render performance and memoization.
lobehubSkillresponse-compliance
lobehub/lobehub/.agents/skills/response-compliance/SKILL.md
Use for OpenResponses/Response API compliance tests, endpoint schema failures and test runs.
lobehubSkillrun-eval-harbor
lobehub/lobehub/.agents/skills/run-eval-harbor/SKILL.md
Run and diagnose existing Harbor evaluations against local production LobeHub or LobeHub Cloud. Use for eval infrastructure, target preflight, lh CLI injection, Harbor smoke or job runs, resume, and failure triage. Excludes authoring Harbor tasks and product acceptance.
lobehubSkillskills-audit
lobehub/lobehub/.agents/skills/skills-audit/SKILL.md
Audit .agents/skills SKILL.md files. Use for recurring checks of duplicate, overlapping, stale, inconsistent, or broken skills and merge/delete candidates.
lobehubSkillspa-routes
lobehub/lobehub/.agents/skills/spa-routes/SKILL.md
Use for SPA routes and page segments: Web/desktop/mobile/popup routers, redirects and src/routes-to-features boundaries.
lobehubSkillsplit-micro-app
lobehub/lobehub/.agents/skills/split-micro-app/SKILL.md
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.
lobehubSkillstore-data-structures
lobehub/lobehub/.agents/skills/store-data-structures/SKILL.md
Explicit compatibility entry for Zustand data-shape guidance.
lobehubSkilltesting-heterogeneous-agents
lobehub/lobehub/.agents/skills/testing-heterogeneous-agents/SKILL.md
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.
lobehubSkilltesting
lobehub/lobehub/.agents/skills/testing/SKILL.md
Use for Vitest tests, mocks, coverage and failing-test diagnosis.
lobehubSkilltrpc-router
lobehub/lobehub/.agents/skills/trpc-router/SKILL.md
Use for server TRPC routers, procedures and API endpoints in apps/server/src/routers.
lobehubSkilltypescript
lobehub/lobehub/.agents/skills/typescript/SKILL.md
Use for TypeScript style and type safety when editing TS/TSX/MTS, including imports, async code and error suppression.
lobehubSkillupstash-workflow
lobehub/lobehub/.agents/skills/upstash-workflow/SKILL.md
Use for Upstash Workflow/QStash handlers, triggers, durable steps and async fan-out.
lobehubSkillux-audit
lobehub/lobehub/.agents/skills/ux-audit/SKILL.md
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.
lobehubSkillux
lobehub/lobehub/.agents/skills/ux/SKILL.md
Use for product design principles and UX checks when designing or implementing user-facing flows.
lobehubSkillversion-release
lobehub/lobehub/.agents/skills/version-release/SKILL.md
Version release workflow — release process and GitHub Release notes (not docs/changelog pages).
lobehubSkillwrite-landing-docs
lobehub/lobehub/.agents/skills/write-landing-docs/SKILL.md
Use for public LobeHub website documentation under docs/**, including self-hosting, deployment, migration, and configuration guides. Excludes product changelogs and source-code API docs.
About skills
What is a Claude skill?
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.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
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.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.