Agent skill

Mas Frontend Standards

by AUTO-MAS-Project in AUTO-MAS-Project/AUTO-MAS

A skill your agent uses when working on AUTO-MAS frontend Vue, TypeScript, Vite, Electron renderer, routing, API composables, state, styles, forms, validation, or frontend verification tasks.

AGPL-3.0Auto-check passedFrontend & Design

Install Mas Frontend Standards

skills CLI
$ npx skills add AUTO-MAS-Project/AUTO-MAS --skill mas-frontend-standards -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AUTO-MAS-Project/AUTO-MAS mas-frontend-standards --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AUTO-MAS-Project/AUTO-MAS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/mas-frontend-standards .claude/skills/mas-frontend-standards && rm -rf skills-src

Use ~/.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/

Facts

Skill name
mas-frontend-standards
GitHub stars
711
Token cost
~3.8k tokens
SKILL.md length
2,110 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when working on AUTO-MAS frontend Vue, TypeScript, Vite, Electron renderer, routing, API composables, state, styles, forms, validation, or frontend verification tasks.

  • Works in 3 steps: Run frontend dependency commands from… → Use yarn install by default. → If the Electron binary download is slow…
  • Working on AUTO-MAS frontend Vue
  • SKILL.md covers Objective, Dependency Installation, Authority and Mandatory Intake, plus 9 more sections
  • Calls yarn, ruff and git; reaches npmmirror.com

What it does

Mas Frontend Standards is an agent skill from AUTO-MAS-Project/AUTO-MAS. Use when working on AUTO-MAS frontend Vue, TypeScript, Vite, Electron renderer, routing, API composables, state, styles, forms, validation, or frontend verification tasks.

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering Forms and validation. It works with Vue.js, Vite and TypeScript. The repository describes itself as: 多脚本多配置统一管理与自动化工具 | 轻松管理大量脚本并存储多个用户配置、设计自动化任务流、监看脚本日志,大幅提高自动化代理效率与稳定性!. The licence is AGPL-3.0.

When your agent uses it

  • Working on AUTO-MAS frontend Vue
  • Electron renderer
  • API composables
  • Frontend verification tasks

Example prompts

  • “/mas-frontend-standards”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Run frontend dependency commands from the frontend/ directory.
  2. Use yarn install by default.
  3. If the Electron binary download is slow or fails, use the one-shot mirror command: yarn cross-env…

What it can do on your machine

Read from SKILL.md and the folder at commit 699de5a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Shell commands in SKILL.md call:

    • yarn
    • ruff
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • npmmirror.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mas Frontend Standards loads about 3.8k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 2,110 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from AUTO-MAS-Project/AUTO-MAS at commit 699de5a, republished under its AGPL-3.0 licence (© AUTO-MAS-Project). 2,110 words, ~3,846 tokens.

Download SKILL.mdSave it as .claude/skills/mas-frontend-standards/SKILL.md (or your agent's skills folder).
name
mas-frontend-standards
description
Use when working on AUTO-MAS frontend Vue, TypeScript, Vite, Electron renderer, routing, API composables, state, styles, forms, validation, or frontend verification tasks.

MAS Frontend Standards

Objective

Keep AUTO-MAS frontend changes aligned with the current Vue 3, TypeScript, Vite, Electron, Ant Design Vue, Vue Router, OpenAPI, ESLint, Prettier, and Yarn 4 project conventions.

Dependency Installation

  1. Run frontend dependency commands from the frontend/ directory.
  2. Use yarn install by default.
  3. If the Electron binary download is slow or fails, use the one-shot mirror command: yarn cross-env ELECTRON_MIRROR="https://npmmirror.com/mirrors/electron/" yarn install.

Authority

This skill is self-contained for frontend engineering rules. If local code differs from this summary, inspect neighboring implementations and prefer the current module pattern unless it violates a red line here.

Mandatory Intake

Before editing frontend code:

  1. Confirm branch, remote, and working tree status.
  2. Inspect the target page, adjacent pages, related components, composables, API wrappers, router entries, and styles.
  3. Classify the task as new page, fix, refactor, style/UI adjustment, API integration, route change, or documentation-only.
  4. Select mas-frontend-ui as a required companion for any UI, layout, component, form, table, modal, feedback, or visual-state change.
  5. Keep changes limited to files directly required by the task.

Directory And Ownership

Code typePlace it hereDo not place it here
Route pagesrc/views/<module>/index.vue or src/views/Xxx.vuesrc/components
Single-module componentsrc/views/<module>/componentssrc/components root
Cross-module componentsrc/componentsCopied across page folders
Business API wrappersrc/composables/useXxxApi.tsVue page or src/api
Reusable page flowsrc/views/<module>/useXxxLogic.ts or composableTemplate expressions
Pure utilitysrc/utilsCopied inside components
Domain typesrc/types or generated src/api/modelsRepeated local component types
Shared reactive application statesrc/stores with PiniaPage-level localStorage access
Global style tokensrc/style.css or future src/stylesRepeated page-local variables
Global browser UI style such as scrollbarssrc/styles, imported once by the renderer entryRepeated component-level browser pseudo-elements
Electron capabilityelectron and preload typesDirect renderer Node access

Use the narrowest module boundary first. Promote to shared directories only after real cross-module reuse.

Vue Component Rules

  1. Use <script setup lang="ts"> unless a compatibility reason exists.
  2. Order code as imports, types, props/emits, composables, state, computed, watchers, lifecycle, functions.
  3. Type props and emits explicitly.
  4. Keep computed values for derived state; keep watchers for side effects only.
  5. Split components that exceed 500 lines or contain multiple independent business regions.
  6. Extract repeated logic into composables or module logic files instead of growing templates.
  7. Do not introduce a new UI, state, request, or routing library for a small task.

API And Data Flow

  1. Never hand-edit generated files under src/api.
  2. Do not write business axios or fetch calls directly in Vue pages.
  3. Use generated src/api types and services through src/composables/useXxxApi.ts or module logic.
  4. Treat response.code !== 200 as failure unless the local contract proves otherwise.
  5. API composables should expose loading, error, and business functions.
  6. Pages own business flow such as navigation, closing dialogs, and local state updates.
  7. Static-resource checks such as audio HEAD requests are not precedent for backend business API calls.
  8. Backend schema changes require regenerating frontend API clients; do not manually patch OpenAPI output.
  9. Do not hand-roll axios + OpenAPI.BASE URLs in composables either. If the endpoint is in the generated Service, call it; if it is missing, regenerate the client rather than bypass it.
  10. Generated services throw ApiError on non-2xx responses. Read the backend's message from error.body after narrowing it (instanceof ApiError, object check, typeof message === 'string'), then rethrow as Error. Wanting AxiosError.response.data is not a reason to skip the generated client. useMaaFWUpdateApi.ts and useHSRPluginApi.ts are the reference.
  11. Pass generated enums (e.g. MaaFWProjectUpdateIn.action.CHECK) instead of string literals cast to the request type.

Routing, State, Config

  1. Route paths use lowercase kebab-case; route names use PascalCase.
  2. Route components are lazy-loaded and business routes include meta.title.
  3. Prefer navigateTo or navigateToByName; avoid scattered hardcoded paths.
  4. Prefer Pinia for reactive application data shared across components or pages, coordinated state with multiple readers or writers, and state that should survive component unmounts or route changes during the current session.
  5. Do not store Pinia-suitable state directly in localStorage, and do not keep Pinia and localStorage as competing sources of truth.
  6. Keep truly component-local, short-lived state in the owning component. Do not create a store for a single isolated control or form draft with no cross-component lifecycle.
  7. Use localStorage only for small, non-sensitive browser-local preferences that must survive application restarts and do not belong to Pinia, backend data, or Electron configuration. Namespace keys, validate parsed values, and provide safe defaults for missing or invalid data.
  8. When shared Pinia state also needs durable persistence, prefer an existing backend or Electron configuration owner instead of adding ad hoc localStorage mirroring.
  9. Never place tokens, credentials, permissions, secrets, large business datasets, or server-authoritative data in localStorage.
  10. API and WebSocket endpoints come from Electron config helpers; do not hardcode backend addresses in business pages.
  11. Vite-exposed environment variables use the VITE_ prefix.

Style And Code Quality

  1. Component styles default to <style scoped>.
  2. Global styles are only for tokens, root layout, or deliberate Ant Design Vue global fixes.
  3. Use CSS variables or Ant Design tokens for color, spacing, radius, shadow, and typography.
  4. Use kebab-case class names and a semantic page root such as .queue-page.
  5. Prefer @/ imports over deep relative paths.
  6. Avoid any; if unavoidable, narrow the scope and explain why.
  7. Do not use console.log in business code; use window.electronAPI.getLogger('module').
  8. Extract magic values such as intervals, timeouts, status codes, and route names into constants when they repeat or carry meaning.
  9. Keep Ant Design Vue default CSS unless a local layout or readability need requires scoped customization.
  10. Keep project-wide browser UI rules such as scrollbar styling in one renderer-global stylesheet, imported once from the application entry and driven by light/dark theme variables.
  11. Derived filters and searches must preserve the source data order. A reduced search result must not be passed to persistence or reorder APIs as if it were the complete collection.

Verification Gate

All commands run from frontend/.

The repo-wide baseline is clean. On untouched dev (verified 2026-08-30), yarn lint reports 0 errors and exactly 1 warning (vue/no-v-html in LogPatternDocsModal.vue, which arrived with #399 on 2026-08-27), yarn typecheck reports 0 errors, and yarn test is fully green. weekly-format.yml re-runs ruff format, yarn lint:fix and yarn format on dev every Monday, so formatting drift does not accumulate.

Therefore any lint or typecheck error you see is almost certainly yours. Do not dismiss it as pre-existing noise without first checking the same command on an untouched checkout — the repository runs no lint, typecheck or test CI, so this baseline is held by convention alone and can drift.

Maintenance note: the warning budget of 1 exists only because that single vue/no-v-html is unfixed. Once it is suppressed or resolved, tighten the gate to --max-warnings 0; leaving the budget at 1 silently permits one arbitrary new warning.

Touched surfaceCommandPassing criterion
Any business codeyarn lint --max-warnings 1exit 0. The budget of 1 covers the single known warning (vue/no-v-html, introduced with #399), so any additional warning fails the gate. Plain yarn lint prints warnings but does not fail on them.
Types, props/emits, API usage, generated-client consumptionyarn typecheck0 errors
A module with a sibling *.test.ts, or shared logic under testyarn testfully green
Build, routing, or Electron entryyarn buildsucceeds
Documentation onlyfile existence, headings, sections, git status --short—
UIalso follow mas-frontend-ui verification—

Rules:

  1. Run all three gates whole — yarn lint --max-warnings 1, yarn typecheck, yarn test. They can and should pass; there is no baseline to subtract. Use the --max-warnings form, not plain yarn lint, or new warnings slip through.
  2. Lint and typecheck are still orthogonal — they check different things, so passing one says nothing about the other. Run both.
  3. yarn lint:fix resolves prettier/prettier findings; use it rather than hand-formatting. Warnings are part of the gate — do not leave a new one behind.
  4. A failure in any of the three is yours until proven otherwise. If you believe it pre-exists, verify on an untouched checkout and say so explicitly in your result.

Prefer yarn typecheck over a full yarn build for type validation; it is much faster and covers the renderer via tsconfig.app.json.

If a command cannot run, state the exact command and the reason. Never claim "complete", "fixed", or "passed" without verification evidence.

Show full SKILL.md (731 more words)Show less

Frontend Tests

Vitest runs with no config file and no DOM environment. There is no vitest.config.ts, no jsdom, and no @vue/test-utils. Tests execute in the default node environment and are colocated next to their subject as *.test.ts.

Three established patterns, in order of preference:

  1. Pure logic — extract the logic out of the .vue file into a sibling .ts, then import and test it directly. views/scripts/scriptSearch.ts with scriptSearch.test.ts is the reference. This is the main reason to extract logic from a component: testability.
  2. Composables — test in node with vi.mock() for boundaries. Mock @/api (the generated Service) and ant-design-vue (message) rather than reaching for a DOM. See composables/useEmulatorDeviceOptions.test.ts.
  3. Component rendering — when what a component shows for given props or state is the behavior under test, render it with createSSRApp + renderToString from @vue/server-renderer (ships with vue) and assert on the HTML. Stub Ant Design Vue components with slot-passthrough placeholders so the assertion covers this component's decisions, not antd's markup. See views/Initialization/components/LaunchFailure.test.ts and views/EditView/MaaFWFlavor/MaaFWFlavorSlot.test.ts.

Do not introduce mount(), jsdom, happy-dom, or @vue/test-utils for a routine change; that is a project-wide testing-stack decision, not a task-level one. If a behavior genuinely cannot be covered by these three patterns, say so in your result instead of adding a test dependency.

Source-text tests

Do not write tests that readFileSync a .vue, .ts, or .css file and assert it contains or lacks particular code — template bindings, handler bodies, style values, imports, or "does not use X" architecture greps. They break on harmless refactors, pass on broken behavior, and were removed in bulk for that reason. Cover the behavior with one of the three patterns above, or leave it to review and say so.

Reading source text is acceptable only when nothing importable exists:

  1. Cross-language contracts — a frontend constant that must mirror a Python backend value. See utils/maafwTaskInstance.test.ts and views/setting/notifyChannelsI18n.test.ts.
  2. Repo-wide scans — such as every literal t('ns.key') in src existing in zh-CN. See i18n/locales.test.ts.

When an existing source-text test fails because you refactored the code it greps, and it guards neither kind of contract, delete it rather than re-pinning the new string.

Red Lines

TemptationReality
"I can generate a fresh page faster."Inspect and reuse local page, component, and composable patterns first.
"The API call is tiny, so direct fetch is fine."Business API calls go through generated services and composables.
"Shared state is easiest to put in localStorage."Shared reactive application state belongs in Pinia; localStorage is only the narrow fallback for durable, non-sensitive local preferences.
"Pinia should hold every frontend value."Keep isolated short-lived state local, and keep persistent authoritative data in its backend or Electron configuration owner.
"I can tweak generated API files."src/api is generated; regenerate through the project command instead.
"New UI text is just a string; inline is faster."User-facing text goes through the i18n catalog in src/i18n/locales. Add the key to zh-CN.ts (source language); en-US.ts is partial by design and missing keys fall back.
"This Chinese literal is untranslated; I'll translate it."Chinese literals that drive logic must stay verbatim — e.g. tab.status === '运行', result.includes('异常'), SchedulerStatus values. Translating them breaks behaviour silently, with no error. Leave them and add a comment saying why.
"This UI-only change can ignore engineering rules."UI tasks still obey module, state, API, and verification boundaries.
"yarn lint is failing, but the repo baseline is dirty anyway."It is not. Clean dev passes lint, typecheck and tests. A failure is yours until you verify otherwise on an untouched checkout.
"Lint passed, so the types are fine."The two are orthogonal and check different things. Run both.
"I'll fix the surrounding lint noise while I'm here."weekly-format.yml already formats dev every Monday. Unrelated cleanup buries your real diff.
"I need jsdom to test this component."Tests run in node with no DOM. Extract logic to a sibling .ts, or render with @vue/server-renderer.
"I'll lock this in with a test that greps the .vue source."Source-text assertions on implementation details are not accepted. Test behavior, or leave it to review.
"The generated client throws ApiError, so I'll call axios directly to read the error message."Read it from ApiError.body. Business requests always go through the generated client.

Final Response

For frontend tasks, report:

  1. Changed files.
  2. Verification commands and results.
  3. UI checks when applicable.
  4. Known risks or "no known residual risk".

State that no business code was changed when the task is documentation-only.

© AUTO-MAS-Project, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/mas-frontend-standards of AUTO-MAS-Project/AUTO-MAS.

Open the folder on GitHubat commit 699de5a

Compare with similar skills

Mas Frontend Standards 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.

Mas Frontend Standards compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mas Frontend Standards this skillAUTO-MAS-Project/AUTO-MAS711—~3.8kAutomated safety check: PassAGPL-3.0
Uni Appsonofmagic/uni-app-tailwindcss-template3362 repos~1kAutomated safety check: PassMIT
Cross Platform Tauri UIifer47/markeron1.2k—~2kAutomated safety check: PassMIT
Vuetify Skilldlogue/vite-vuetify-ts-starter1811 repos~1.9kAutomated safety check: PassMIT
Tauri Config Ipcifer47/markeron1.2k—~1kAutomated safety check: PassMIT
Vue Component Developmentgdarko/laravel-vue-starter145—~1.1kAutomated safety check: PassMIT

Similar skills

  • Uni App

    sonofmagic/uni-app-tailwindcss-template

    Comprehensive skill reference for uni-app cross-platform development framework

    336 GitHub starsUsed in 2 repos~1k tokens
    Frontend & DesignAuto-check passed
  • Cross-platform UI styling for MarkerOn Tauri app (macOS WKWebView vs Windows WebView2).

    1.2k GitHub stars~2k tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • Vuetify Skilld

    logue/vite-vuetify-ts-starter

    Vue Material Component Framework. An agent skill from logue/vite-vuetify-ts-starter.

    181 GitHub starsUsed in 1 repo~1.9k tokens
    Frontend & DesignAuto-check passed
  • Tauri Config Ipc

    ifer47/markeron

    Extend MarkerOn settings, persisted config, or Tauri IPC commands.

    1.2k GitHub stars~1k tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • Vue Component Development

    gdarko/laravel-vue-starter

    Activate when creating or modifying Vue 3 components, pages, layouts, stores, or services in the frontend.

    145 GitHub stars~1.1k tokensUpdated 6 mo ago
    Frontend & DesignAuto-check passed
  • Vite Plugin SVG Icons Ng

    yangxu52/vite-plugin-svg-icons-ng

    Consumer setup and integration for vite-plugin-svg-icons-ng: installation, createSvgIconsPlugin configuration, direct SVG usage, Vue 3 and React components, htmlMode, virtual modules, TypeScript…

    117 GitHub stars~919 tokensUpdated 12 days ago
    Frontend & DesignAuto-check passed

More from AUTO-MAS-Project/AUTO-MAS

All 15 skills in this repo
  • Mas Game Sign

    AUTO-MAS-Project/AUTO-MAS

    Add, refactor, or review AUTO-MAS game community sign-in (game sign) code, including the provider registry in app/tools/gamesign.py, platform adapters for Skland/Miyoushe/Kuro/Taygedo, credential…

    711 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Mas Schema Naming

    AUTO-MAS-Project/AUTO-MAS

    Define canonical naming for future backend schema domains. An agent skill from AUTO-MAS-Project/AUTO-MAS.

    711 GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Mas Code Standards

    AUTO-MAS-Project/AUTO-MAS

    A skill your agent uses when implementing, fixing, refactoring, or reviewing non-generated AUTO-MAS code, or when preparing code-style guidance, comments, docstrings, version notes, or Conventional…

    711 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Mas Frontend UI

    AUTO-MAS-Project/AUTO-MAS

    A skill your agent uses when working on AUTO-MAS frontend UI, Ant Design Vue components, page layout, forms, tables, modals, drawers, feedback, empty/loading/error states, drag interactions, dark…

    711 GitHub stars~3.8k tokensUpdated today
    Auto-check passed
  • Mas Script Specialized Adapter

    AUTO-MAS-Project/AUTO-MAS

    Review, add, or refactor AUTO-MAS specialized script adapters by upstream architecture, including MAA, SRC, MaaEnd/MXU, General, ok-script adapters such as Okww and OkNte, multi-engine adapters such…

    711 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Mas API Contract

    AUTO-MAS-Project/AUTO-MAS

    Define backend API contract standards for FastAPI services. An agent skill from AUTO-MAS-Project/AUTO-MAS.

    711 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Questions about Mas Frontend Standards

What does Mas Frontend Standards do?

A skill your agent uses when working on AUTO-MAS frontend Vue, TypeScript, Vite, Electron renderer, routing, API composables, state, styles, forms, validation, or frontend verification tasks. Mas Frontend Standards is an agent skill from AUTO-MAS-Project/AUTO-MAS. Use when working on AUTO-MAS frontend Vue, TypeScript, Vite, Electron renderer, routing, API composables, state, styles, forms, validation, or frontend verification tasks.

When should I use Mas Frontend Standards?

Mas Frontend Standards fits situations like: working on AUTO-MAS frontend Vue; electron renderer; API composables; frontend verification tasks.

How do I install Mas Frontend Standards in Claude Code?

Run `npx skills add AUTO-MAS-Project/AUTO-MAS --skill mas-frontend-standards -a claude-code`. Or copy the skill folder (.agents/skills/mas-frontend-standards in AUTO-MAS-Project/AUTO-MAS) into .claude/skills/mas-frontend-standards in your project. Claude Code loads it when a task matches its description.

How do I install Mas Frontend Standards in Codex?

Run `npx skills add AUTO-MAS-Project/AUTO-MAS --skill mas-frontend-standards -a codex`. Or copy the skill folder (.agents/skills/mas-frontend-standards in AUTO-MAS-Project/AUTO-MAS) into .agents/skills/mas-frontend-standards in your project. Codex loads it when a task matches its description.

Can I use Mas Frontend Standards in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AUTO-MAS-Project/AUTO-MAS --skill mas-frontend-standards -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mas-frontend-standards, .gemini/skills/mas-frontend-standards, .github/skills/mas-frontend-standards and .opencode/skills/mas-frontend-standards in your project.

What does Mas Frontend Standards need to run?

Going by SKILL.md and its folder, Mas Frontend Standards needs the command-line tools its instructions call (yarn, ruff and git).

Does Mas Frontend Standards access the network?

SKILL.md names 1 domain. In commands or code: npmmirror.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Mas Frontend Standards safe to install?

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.

What licence does Mas Frontend Standards use?

Mas Frontend Standards is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mas Frontend Standards use?

About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mas Frontend Standards?

Skills that share tags, products or a category with Mas Frontend Standards: Uni App (sonofmagic/uni-app-tailwindcss-template, 336 stars), Cross Platform Tauri UI (ifer47/markeron, 1.2k stars), Vuetify Skilld (logue/vite-vuetify-ts-starter, 181 stars) and Tauri Config Ipc (ifer47/markeron, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mas Frontend Standards?

AUTO-MAS-Project (a GitHub organization) maintains it in AUTO-MAS-Project/AUTO-MAS, which has 711 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 10, 2026.

Source: AUTO-MAS-Project/AUTO-MAS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.