Pinia
JetBrains/skills
Pinia official Vue state management library, type-safe and extensible.
| Nuxt 4 data management: composables, data fetching with useFetch/useAsyncData, and state management with useState and Pinia.
$ npx skills add secondsky/claude-skills --skill nuxt-data -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install secondsky/claude-skills nuxt-data --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/secondsky/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/nuxt-v4/skills/nuxt-data .claude/skills/nuxt-data && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "nuxt-data" agent skill from https://github.com/secondsky/claude-skills/tree/main/plugins/nuxt-v4/skills/nuxt-data into .claude/skills/nuxt-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nuxt-data", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/secondsky/claude-skills/tree/main/plugins/nuxt-v4/skills/nuxt-dataType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add secondsky/claude-skills --skill nuxt-data -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install secondsky/claude-skills nuxt-data --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/secondsky/claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/nuxt-v4/skills/nuxt-data .agents/skills/nuxt-data && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nuxt-data" agent skill from https://github.com/secondsky/claude-skills/tree/main/plugins/nuxt-v4/skills/nuxt-data into .agents/skills/nuxt-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nuxt-data", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add secondsky/claude-skills --skill nuxt-data -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install secondsky/claude-skills nuxt-data --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/secondsky/claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/nuxt-v4/skills/nuxt-data .cursor/skills/nuxt-data && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "nuxt-data" agent skill from https://github.com/secondsky/claude-skills/tree/main/plugins/nuxt-v4/skills/nuxt-data into .cursor/skills/nuxt-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nuxt-data", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/secondsky/claude-skills.git --path plugins/nuxt-v4/skills/nuxt-data--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add secondsky/claude-skills --skill nuxt-data -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install secondsky/claude-skills nuxt-data --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/secondsky/claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/nuxt-v4/skills/nuxt-data .gemini/skills/nuxt-data && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "nuxt-data" agent skill from https://github.com/secondsky/claude-skills/tree/main/plugins/nuxt-v4/skills/nuxt-data into .gemini/skills/nuxt-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nuxt-data", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install secondsky/claude-skills nuxt-dataInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add secondsky/claude-skills --skill nuxt-data -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/secondsky/claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/nuxt-v4/skills/nuxt-data .github/skills/nuxt-data && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "nuxt-data" agent skill from https://github.com/secondsky/claude-skills/tree/main/plugins/nuxt-v4/skills/nuxt-data into .github/skills/nuxt-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nuxt-data", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add secondsky/claude-skills --skill nuxt-data -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install secondsky/claude-skills nuxt-data --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/secondsky/claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/nuxt-v4/skills/nuxt-data .opencode/skills/nuxt-data && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "nuxt-data" agent skill from https://github.com/secondsky/claude-skills/tree/main/plugins/nuxt-v4/skills/nuxt-data into .opencode/skills/nuxt-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nuxt-data", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
nuxt-data| Nuxt 4 data management: composables, data fetching with useFetch/useAsyncData, and state management with useState and Pinia.
Nuxt Data is an agent skill from secondsky/claude-skills. | Nuxt 4 data management: composables, data fetching with useFetch/useAsyncData, and state management with useState and Pinia. Use when: creating custom composables, fetching data with useFetch or useAsyncData, managing global state with useState, integrating Pinia, debugging reactive data issues, or implementing SSR-safe state patterns.
Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/composables.md`, `references/data-fetching.md` and `templates/composables/useAuth.ts`).
It sits in Frontend & Design, covering State management. It works with Nuxt. The repository describes itself as: Production-ready skills for Claude Code CLI - Cloudflare, React, Tailwind v4, and AI integrations. The licence is MIT.
Read from SKILL.md and the folder at commit 8837836. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (TypeScript), which the agent can run.
Shell commands in SKILL.md call:
bunFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Nuxt Data loads about 3.4k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 361 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from secondsky/claude-skills at commit 8837836, republished under its MIT licence (© secondsky). 361 words, ~3,402 tokens.
.claude/skills/nuxt-data/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Composables, data fetching, and state management patterns for Nuxt 4 applications.
| Method | Use Case | SSR | Caching | Reactive |
|---|---|---|---|---|
useFetch | Simple API calls | Yes | Yes | Yes |
useAsyncData | Custom async logic | Yes | Yes | Yes |
$fetch | Client-side only, events | No | No | No |
| Prefix | Purpose | Example |
|---|---|---|
use | State/logic composable | useAuth, useCart |
fetch | Data fetching only | fetchUsers (rare) |
Load references/composables.md when:
Load references/data-fetching.md when:
Load references/pinia-integration.md when:
useState creates SSR-safe, shared reactive state that persists across component instances.
// composables/useCounter.ts
export const useCounter = () => {
// Singleton - shared across all components
const count = useState('counter', () => 0)
const increment = () => count.value++
const decrement = () => count.value--
const reset = () => count.value = 0
return { count, increment, decrement, reset }
}// CORRECT: Shared state (singleton pattern)
export const useAuth = () => {
const user = useState('auth-user', () => null) // Shared!
return { user }
}
// WRONG: Creates new instance every call!
export const useAuth = () => {
const user = ref(null) // Not shared!
return { user }
}Rule: Use useState for shared/global state. Use ref for local component state only.
// composables/useAuth.ts
export const useAuth = () => {
const user = useState<User | null>('auth-user', () => null)
const isAuthenticated = computed(() => !!user.value)
const isLoading = useState('auth-loading', () => false)
const login = async (email: string, password: string) => {
isLoading.value = true
try {
const data = await $fetch('/api/auth/login', {
method: 'POST',
body: { email, password }
})
user.value = data.user
return { success: true }
} catch (error) {
return { success: false, error: error.message }
} finally {
isLoading.value = false
}
}
const logout = async () => {
await $fetch('/api/auth/logout', { method: 'POST' })
user.value = null
navigateTo('/login')
}
const checkSession = async () => {
if (import.meta.server) return // Skip on server
try {
const data = await $fetch('/api/auth/session')
user.value = data.user
} catch {
user.value = null
}
}
return { user, isAuthenticated, isLoading, login, logout, checkSession }
}// composables/useLocalStorage.ts
export const useLocalStorage = <T>(key: string, defaultValue: T) => {
const data = useState<T>(key, () => defaultValue)
// Only access localStorage on client
if (import.meta.client) {
const stored = localStorage.getItem(key)
if (stored) {
data.value = JSON.parse(stored)
}
// Watch and persist changes
watch(data, (newValue) => {
localStorage.setItem(key, JSON.stringify(newValue))
}, { deep: true })
}
return data
}// Simple GET request
const { data, error, pending, refresh } = await useFetch('/api/users')
// With options
const { data: users } = await useFetch('/api/users', {
method: 'GET',
query: { limit: 10, offset: 0 },
headers: { 'X-Custom-Header': 'value' }
})<script setup lang="ts">
const page = ref(1)
const search = ref('')
// Auto-refetches when page or search changes
const { data: users, pending } = await useFetch('/api/users', {
query: {
page,
search,
limit: 10
}
})
// Or with computed
const query = computed(() => ({
page: page.value,
search: search.value,
limit: 10
}))
const { data } = await useFetch('/api/users', { query })
</script>const { data: userNames } = await useFetch('/api/users', {
transform: (users) => users.map(u => u.name)
})
// data.value is now string[] instead of User[]const { data } = await useFetch('/api/user', {
pick: ['id', 'name', 'email'] // Only these fields in payload
})// Multiple parallel requests
const { data } = await useAsyncData('dashboard', async () => {
const [users, posts, stats] = await Promise.all([
$fetch('/api/users'),
$fetch('/api/posts'),
$fetch('/api/stats')
])
return { users, posts, stats }
})
// Access: data.value.users, data.value.posts, data.value.statsconst { data, error, status } = await useFetch('/api/users')
// Check error
if (error.value) {
console.error('Error:', error.value.message)
console.error('Status:', error.value.statusCode)
}
// Status values: 'idle' | 'pending' | 'success' | 'error'
if (status.value === 'error') {
showError(error.value)
}const { data, refresh, execute } = await useFetch('/api/users', {
immediate: false // Don't fetch on mount
})
// Fetch manually
await execute()
// Refresh (re-fetch)
await refresh()
// Refresh with new params
await refresh({ dedupe: true })// Nuxt 4 default: Shallow reactivity
const { data } = await useFetch('/api/user')
data.value.name = 'New Name' // Won't trigger reactivity!
// Enable deep reactivity for mutations
const { data } = await useFetch('/api/user', {
deep: true
})
data.value.name = 'New Name' // Now works!
// Or refresh instead of mutating
const { data, refresh } = await useFetch('/api/user')
await $fetch('/api/user', { method: 'PATCH', body: { name: 'New Name' } })
await refresh() // Re-fetch updated dataconst { data } = await useFetch('/api/users', {
key: 'users-list', // Custom cache key
dedupe: 'cancel', // Cancel duplicate requests
getCachedData: (key, nuxtApp) => {
// Return cached data if valid
return nuxtApp.payload.data[key]
}
})// useLazyFetch - Navigation happens immediately, data loads in background
const { data, pending } = useLazyFetch('/api/users')
// useLazyAsyncData
const { data, pending } = useLazyAsyncData('users', () => $fetch('/api/users'))// In event handlers (not during SSR)
const submitForm = async () => {
const result = await $fetch('/api/submit', {
method: 'POST',
body: formData.value
})
}
// In server routes
export default defineEventHandler(async (event) => {
const externalData = await $fetch('https://api.example.com/data')
return externalData
})// Simple counter
const count = useState('count', () => 0)
// Complex object
const settings = useState('settings', () => ({
theme: 'light',
notifications: true,
language: 'en'
}))
// Typed state
interface User {
id: string
name: string
email: string
}
const user = useState<User | null>('user', () => null)// composables/useCart.ts
interface CartItem {
id: string
name: string
price: number
quantity: number
}
export const useCart = () => {
const items = useState<CartItem[]>('cart-items', () => [])
const total = computed(() =>
items.value.reduce((sum, item) => sum + item.price * item.quantity, 0)
)
const itemCount = computed(() =>
items.value.reduce((sum, item) => sum + item.quantity, 0)
)
const addItem = (product: Omit<CartItem, 'quantity'>) => {
const existing = items.value.find(i => i.id === product.id)
if (existing) {
existing.quantity++
} else {
items.value.push({ ...product, quantity: 1 })
}
}
const removeItem = (id: string) => {
items.value = items.value.filter(i => i.id !== id)
}
const updateQuantity = (id: string, quantity: number) => {
const item = items.value.find(i => i.id === id)
if (item) {
item.quantity = Math.max(0, quantity)
if (item.quantity === 0) removeItem(id)
}
}
const clearCart = () => {
items.value = []
}
return { items, total, itemCount, addItem, removeItem, updateQuantity, clearCart }
}bun add pinia @pinia/nuxt// nuxt.config.ts
export default defineNuxtConfig({
modules: ['@pinia/nuxt']
})
// stores/auth.ts
import { defineStore } from 'pinia'
export const useAuthStore = defineStore('auth', {
state: () => ({
user: null as User | null,
token: null as string | null
}),
getters: {
isAuthenticated: (state) => !!state.user,
userName: (state) => state.user?.name ?? 'Guest'
},
actions: {
async login(email: string, password: string) {
const { user, token } = await $fetch('/api/auth/login', {
method: 'POST',
body: { email, password }
})
this.user = user
this.token = token
},
logout() {
this.user = null
this.token = null
}
}
})
// Usage in components
const authStore = useAuthStore()
await authStore.login('user@example.com', 'password')
console.log(authStore.userName)// WRONG - Creates new instance every time!
export const useAuth = () => {
const user = ref(null) // Not shared
return { user }
}
// CORRECT
export const useAuth = () => {
const user = useState('auth-user', () => null)
return { user }
}// WRONG
const { data } = await useFetch('/api/users')
console.log(data.value.length) // Crashes if error!
// CORRECT
const { data, error } = await useFetch('/api/users')
if (error.value) {
showToast({ type: 'error', message: error.value.message })
return
}
console.log(data.value.length)// WRONG - Causes hydration mismatch!
const { data } = await useFetch('/api/users', {
transform: (users) => users.sort(() => Math.random() - 0.5)
})
// CORRECT
const { data } = await useFetch('/api/users', {
transform: (users) => users.sort((a, b) => a.name.localeCompare(b.name))
})// WRONG - v4 uses shallow refs by default
const { data } = await useFetch('/api/user')
data.value.name = 'New Name' // Won't trigger reactivity!
// CORRECT - Option 1: Enable deep
const { data } = await useFetch('/api/user', { deep: true })
data.value.name = 'New Name'
// CORRECT - Option 2: Replace entire value
data.value = { ...data.value, name: 'New Name' }
// CORRECT - Option 3: Refresh after mutation
await $fetch('/api/user', { method: 'PATCH', body: { name: 'New Name' } })
await refresh()Data Not Refreshing When Params Change:
{ query: { page } } where page = ref(1).valueHydration Mismatch with useState:
useState('unique-key', () => value)Math.random() or Date.now() in initial valuesState Lost on Navigation:
useState instead of ref for persistent stateInfinite Refetch Loop:
watch with { immediate: false } for side effectsVersion: 4.0.0 | Last Updated: 2025-12-28 | License: MIT
© secondsky, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in plugins/nuxt-v4/skills/nuxt-data of secondsky/claude-skills.
Open the folder on GitHubat commit 8837836
Nuxt Data next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Nuxt Data this skillsecondsky/claude-skills | 227 | — | ~3.4k | Automated safety check: Pass | MIT | |
| PiniaJetBrains/skills | 363 | 9 repos | ~682 | Automated safety check: Pass | None | |
| Feature Sliced Designfeature-sliced/skills | 109 | — | ~5.5k | Automated safety check: Pass | None | |
| Vue ExpertJeffallan/claude-skills | 12k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Vue Patternsaffaan-m/ECC | 274k | 1 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Vue Masterycigery-useio/useio-skills | 103 | — | ~1.8k | Automated safety check: Pass | MIT |
JetBrains/skills
Pinia official Vue state management library, type-safe and extensible.
feature-sliced/skills
Official Feature-Sliced Design (FSD) v2.1 skill for applying the methodology to frontend projects.
Jeffallan/claude-skills
Builds Vue 3 apps with the Composition API and script setup, Pinia state, Nuxt 3, Vite tuning and Quasar or Capacitor mobile builds, checked with vue-tsc and Vitest.
affaan-m/ECC
Vue.js 3 Composition API patterns, component architecture, reactivity best practices, Pinia state management, Vue Router navigation, and Nuxt SSR patterns.
cigery-useio/useio-skills
Vue 3 expert skill for writing production-grade code. An agent skill from cigery-useio/useio-skills.
jiushiwon/wg-skills
当用户要创建 Next.js 14+(React 生态的全栈框架,非 Vue 的 Nuxt)App Router + TypeScript + Zustand 全栈项目时使用。引导完成需求澄清、项目初始化、SSR/RSC 配置、请求层集成、API Routes、认证中间件、后置验证。严格对齐 frontend-request-skill 请求层规范。触发词:"帮我做一个 Next.js…
secondsky/claude-skills
TanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama.
secondsky/claude-skills
AutoAnimate (@formkit/auto-animate) zero-config animations for React.
secondsky/claude-skills
MUI Base UI unstyled React components with Floating UI. An agent skill from secondsky/claude-skills.
secondsky/claude-skills
This skill should be used when the user asks to "upload images to Cloudflare", "implement direct creator upload", "configure image transformations", "optimize WebP/AVIF", "create image variants"…
secondsky/claude-skills
Deploy Next.js to Cloudflare Workers via the OpenNext adapter (@opennextjs/cloudflare).
secondsky/claude-skills
Cloudflare Sandboxes SDK for secure code execution in Linux containers at edge.
Works with
Categories
| Nuxt 4 data management: composables, data fetching with useFetch/useAsyncData, and state management with useState and Pinia. Nuxt Data is an agent skill from secondsky/claude-skills. | Nuxt 4 data management: composables, data fetching with useFetch/useAsyncData, and state management with useState and Pinia.
Nuxt Data fits situations like: : creating custom composables; fetching data with useFetch; managing global state with useState; integrating Pinia.
Run `npx skills add secondsky/claude-skills --skill nuxt-data -a claude-code`. Or copy the skill folder (plugins/nuxt-v4/skills/nuxt-data in secondsky/claude-skills) into .claude/skills/nuxt-data in your project. Claude Code loads it when a task matches its description.
Run `npx skills add secondsky/claude-skills --skill nuxt-data -a codex`. Or copy the skill folder (plugins/nuxt-v4/skills/nuxt-data in secondsky/claude-skills) into .agents/skills/nuxt-data in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add secondsky/claude-skills --skill nuxt-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nuxt-data, .gemini/skills/nuxt-data, .github/skills/nuxt-data and .opencode/skills/nuxt-data in your project.
Going by SKILL.md and its folder, Nuxt Data needs TypeScript for the scripts in its folder and the command-line tools its instructions call (bun). Our summary lists: Node.js.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Nuxt Data is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.4k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Nuxt Data: Pinia (JetBrains/skills, 363 stars), Feature Sliced Design (feature-sliced/skills, 109 stars), Vue Expert (Jeffallan/claude-skills, 12k stars) and Vue Patterns (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
secondsky (a GitHub user) maintains it in secondsky/claude-skills, which has 227 GitHub stars. The repository holds 169 skills in this directory. The repository was last updated on September 28, 2026.
Source: secondsky/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.