Agent skill

Mas Skills

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

A skill your agent uses when a task needs AUTO-MAS engineering conventions across frontend, UI, code style, schema naming, module boundaries, function design, API contracts, data modeling, script…

AGPL-3.0Auto-check passedDatabases

Install Mas Skills

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

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

GitHub CLI
$ gh skill install AUTO-MAS-Project/AUTO-MAS mas-skills --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-skills .claude/skills/mas-skills && 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-skills
GitHub stars
711
Token cost
~3.6k tokens
SKILL.md length
1,901 words
Files
2
Skills in repo
15
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when a task needs AUTO-MAS engineering conventions across frontend, UI, code style, schema naming, module boundaries, function design, API contracts, data modeling, script…

  • Works in 3 steps: AUTO-MAS-Project/AUTO-MAS keeps… → AUTO-MAS-Project/AUTO-MAS-docs / owns… → Local .agents/skills owns the…
  • A task needs AUTO-MAS engineering conventions across frontend
  • SKILL.md covers Objective, Repository Authority, Project Rule Areas and Sub-Skills, plus 5 more sections
  • Calls git and python

What it does

Mas Skills is an agent skill from AUTO-MAS-Project/AUTO-MAS. Use when a task needs AUTO-MAS engineering conventions across frontend, UI, code style, schema naming, module boundaries, function design, API contracts, data modeling, script adapters (MAA, SRC, MaaEnd, General, ok-script family such as Okww and OkNte, multi-engine HSR), plan schedules, or game community sign-in.

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Databases, covering Frontend development, API design and Database schema design. 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

  • A task needs AUTO-MAS engineering conventions across frontend
  • Module boundaries
  • Function design
  • Script adapters (MAA

Example prompts

  • “/mas-skills”

Requirements

  • Python 3

Workflow steps

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

  1. AUTO-MAS-Project/AUTO-MAS keeps application code and a minimal AGENTS.md entrypoint.
  2. AUTO-MAS-Project/AUTO-MAS-docs / owns branch, contribution, commit, version, Issue, and PR writing rules.
  3. Local .agents/skills owns the project-affiliated Agent Skill behavior and engineering routing rules for this checkout.

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:

    • git
    • python

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

  • Network

    Links to these hosts (documentation or services it may open):

    • doc.auto-mas.top

    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 Skills loads about 3.6k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 1,901 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k

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). 1,901 words, ~3,643 tokens.

Download SKILL.mdSave it as .claude/skills/mas-skills/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
mas-skills
description
Use when a task needs AUTO-MAS engineering conventions across frontend, UI, code style, schema naming, module boundaries, function design, API contracts, data modeling, script adapters (MAA, SRC, MaaEnd, General, ok-script family such as Okww and OkNte, multi-engine HSR), plan schedules, or game community sign-in.

MAS Skills

Objective

Provide one routing entrypoint for MAS engineering standards and keep implementation decisions consistent with current project maintainer review preferences.

Repository Authority

AUTO-MAS splits responsibilities across repositories:

  1. AUTO-MAS-Project/AUTO-MAS keeps application code and a minimal AGENTS.md entrypoint.
  2. AUTO-MAS-Project/AUTO-MAS-docs / https://doc.auto-mas.top/developer/ owns branch, contribution, commit, version, Issue, and PR writing rules.
  3. Local .agents/skills owns the project-affiliated Agent Skill behavior and engineering routing rules for this checkout.

When these areas overlap, use this skill for engineering decisions and use the docs site for contribution-process decisions.

Project Rule Areas

Apply these project rules directly when they overlap with a task:

  1. Cherry-picks to an already released release/{version} branch must be small pure-backend fixes that touch no frontend code, because released apps hot-update only backend code from that branch while the frontend ships inside the installer. Cherry-picking a commit that carries frontend logic is a violation: close the related PR and revert the related commit. Judge by the files the commit actually touches, not by the type / scope in its message. Never help prepare or push such a cherry-pick.

  2. API work follows the schema-first route flow: define app/models/schema.py, wire the matching app/api/ module, then regenerate frontend API clients.

  3. Config work follows ConfigBase and ConfigItem ownership: declare fields before super().__init__(), use validators as auto-correction behavior, and register multi-config classes in the owning collection.

  4. Script adaptation must be complete across config, schema, API, task dispatch, task folder, and frontend entry points, and must respect the black-box boundary: lower the configuration barrier before filling any gap, then decide capability ownership: work the script owns (in-game actions, task execution and verdicts, script config semantics) may only be reused through upstream entry points; when upstream lacks such work, consider contributing it upstream first and only fill in inside MAS as a temporary measure (marked for removal once upstream ships it) when that is not viable; MAS-owned domains (accounts, scheduling, plans, notifications, statistics, emulator lifecycle, cross-script orchestration) may be implemented in MAS but must not read or infer upstream internal state; upstream private formats may only be passed through, never modeled on, and no self-invented verdicts for upstream-executed tasks. Once upstream ships an entry point for such work, existing implementations become violations and must be replaced by reuse. After this skill is loaded, self-check the task and, on a hit, report "This may violate the MAS development norms" with file:line evidence and an alternative; the warning does not block work. Read .agents/skills/mas-script-specialized-adapter/references/blackbox-boundary.md before designing.

  5. Frontend work follows the dedicated frontend skills in this directory.

  6. Contribution style follows Conventional Commits, Google-style backend docstrings where useful, config-item comments, and keyword arguments for booleans or multi-argument calls.

  7. CI must pin every external reference to immutable content: GitHub Actions uses entries use a full 40-character commit SHA with a # <tag> version comment (resolve annotated tags to the peeled commit), and container images use @sha256:<digest>. Apply this across GitHub workflows, composite actions, and CNB pipelines; local actions such as ./.github/actions/... are the only exception. Never leave a mutable tag, branch, or short hash. When changing CI, scan every uses: and image: reference and verify that all external references remain pinned.

  8. Start every branch from the latest upstream dev (git fetch first; in a fork, branch off upstream dev), never from a stale local dev: a branch built on an old baseline silently overwrites other people's merged work when it is synced, with no conflict and green type checks. Branch rules: https://doc.auto-mas.top/developer/development-specifications.html.

Sub-Skills

Use these skills as needed:

  1. mas-frontend-standards: Vue 3, TypeScript, Vite, Electron renderer, routing, API composables, state, styles, forms, validation, and frontend verification.
  2. mas-frontend-ui: Ant Design Vue UI, desktop business layout, visual tokens, forms, tables, dialogs, feedback, drag interactions, dark mode, and UX constraints.
  3. mas-code-standards: project code standards derived from representative dev commits and existing AUTO-MAS modules.
  4. mas-schema-naming: canonical naming for shared schema semantics in future domain work.
  5. mas-module-boundary: module ownership and dependency direction across backend layers.
  6. mas-function-design: function-level design for responsibility, signatures, side effects, and errors.
  7. mas-api-contract: endpoint contract standards for HTTP/WS request-response behavior.
  8. mas-data-model: modeling standards for schema/config/task layers and compatibility evolution.
  9. mas-script-specialized-adapter: specialized script integration by script frontend architecture line; requires intake before implementation.
  10. mas-plan-schedule: plan schedule type registration, backend/frontend plan dispatch, plan combobox consumers, and per-type table integration.
  11. mas-game-sign: game community sign-in providers, credential encryption and login routes, sign-in locks and trigger paths, and result/notification contracts.

Global Constraints

Apply these constraints before selecting or combining sub-skills.

  1. Make minimal necessary changes first; avoid broad refactors unless explicitly requested.
  2. Align with current code style and existing project conventions in the touched module.
  3. Avoid over-engineering, over-abstraction, and defensive programming that does not match existing code patterns.
  4. Study similar existing implementations deeply before coding and follow established local patterns.
  5. Never edit files generated by OpenAPI code generation under any circumstance. If regeneration is needed, explicitly tell the developer to run the generation process manually.
  6. For frontend work, load mas-frontend-standards; for UI or user-facing component behavior, also load mas-frontend-ui.
  7. When local patterns and generalized guidance differ, prefer concrete maintainer review comments and fold them back into the selected sub-skills.
  8. Before completing a user-visible feature or fix, add exactly one changelog fragment under changelog.d/ (<PR number or branch>.<feat|change|fix|breaking|remove|security|dev>.md; first line project: <key> from the project table in changelog.d/README.md — 14 adapters plus home / scheduler / emulator / notify / tools / settings / update / runtime, no catch-all, pick the nearest per the README; only dev fragments may omit it; then one user-facing sentence of at most 50 characters without project prefix, PR number or signature; python scripts/changelog.py add <type> <project> "<sentence>" creates it, with - as the project for dev). Before writing a fix or change fragment, decide which release introduced the feature you touch: a feature absent from the previous stable release's notes was introduced in the current X.Y.0 cycle (for 5.5.0: Runtime initialization, virtual display, Emulator 2.0, MFW, BetterGI, BAAH, ZZZ-OD, config restore, operator cultivation). Every later fix, maintenance or supplementary change to such a feature (bug fixes, turning something into a prompt, extra hints, default tweaks, layout changes, i18n wiring, cleanup) is beta-only: if the feature's entry is still in the top ## [未发布] section or its fragment is still in changelog.d/, add no fragment and label the PR skip-changelog (describe any wording change in the PR for a maintainer to apply); if it shipped in an earlier beta of the cycle, add the header line beta-only: true so the entry is dropped from the stable roll-up. Sub-features added to it later are beta-only as well: in the stable notes a new adapter is exactly one line (【bgi】新增 bgi 专项) and a new feature is its single introduction entry; fixes and changes to features that shipped in the previous stable are normal. Project keys use the short names bgi (BetterGI) and end (MaaEnd). A PR with several human authors lists them all in the header line author: a, b (the script never reads Co-authored-by). Maintainers may add highlight: true to route an entry into 「本次亮点」 as part of the implementation; do not merely remind the developer. Condense all changes of the PR into that one sentence. Never edit CHANGELOG.md, res/version.json or any version number: they are written only by the release PR. Do not create a commit unless the user explicitly asks for one.
Show full SKILL.md (679 more words)Show less

Routing Rules

Choose sub-skills by task intent.

  1. Task mentions field names, shared terms, schema key consistency: Use mas-schema-naming.
  2. Task touches frontend, src/views, src/components, src/composables, src/router, src/types, src/utils, Vue, TypeScript, Vite, Electron renderer, API composables, forms, validation, or frontend verification: Use mas-frontend-standards.
  3. Task touches UI, layout, style, Ant Design Vue, components, forms, tables, modals, drawers, feedback, loading, empty, error states, drag interactions, dark mode, or visual polish: Use mas-frontend-ui with mas-frontend-standards.
  4. Task implements, fixes, refactors, or reviews repository code: Use mas-code-standards as the baseline, then add the minimum domain-specific mas-* skills. Skip it for read-only work unless code conventions or commit wording are requested.
  5. Task mentions layer ownership, imports, coupling, or where code should live: Use mas-module-boundary.
  6. Task mentions function splitting, signature quality, return/error behavior: Use mas-function-design.
  7. Task mentions endpoint payloads, response model, error contract, websocket payloads: Use mas-api-contract.
  8. Task mentions model structure, typing/defaults/constraints, migration of model fields: Use mas-data-model.
  9. Task mentions adding a new script, script-specific adaptation, task lifecycle, or a specific adapter such as MAA / SRC / MaaEnd / General / Okww / OkNte(异环)/ HSR (M9A is not an adapter: it is a MaaFW flavor, see app/task/M9A/AGENTS.md): Use mas-script-specialized-adapter first, then combine mas-module-boundary, mas-data-model, mas-function-design, and mas-api-contract as needed.
  10. Task mentions commit messages, docstrings, config comments, or project contribution style: Use mas-code-standards for code-style decisions; use the docs site for contribution-process wording.
  11. Task mentions plan schedules, schedule types, PlanConfig, PLAN_BOOK, plan comboboxes, or adding a new plan table: Use mas-plan-schedule.
  12. Task mentions game community sign-in, app/tools/game_sign*, a sign-in platform such as Skland/Miyoushe/Kuro/Taygedo, sign-in credentials or QR login, or sign-in result and notification behavior: Use mas-game-sign.
  13. Task mentions cherry-picking a fix to a release/{version} branch, backporting to a released version, or hot-updating released backend code: Apply the cherry-pick rule in Project Rule Areas before touching git; confirm the commit is small and pure backend by inspecting the files it actually touches.

Combined Execution Order

When multiple concerns appear, apply this order:

  1. mas-frontend-standards, when the task touches frontend code or docs.
  2. mas-frontend-ui, when the task touches UI or user-facing component behavior.
  3. mas-code-standards
  4. mas-module-boundary
  5. mas-data-model
  6. mas-schema-naming
  7. mas-function-design
  8. mas-api-contract
  9. mas-script-specialized-adapter after architecture intake, when the task is a specialized adapter.
  10. mas-plan-schedule
  11. mas-game-sign

Reason: frontend tasks need their engineering and UI constraints loaded before implementation decisions; then establish local conventions, place code correctly, stabilize model structure, then naming, function behavior, and transport contract. Specialized adapters add a mandatory architecture-intake step, plan schedule rules apply when the task touches scheduler registration, and game sign rules apply last because they constrain credential handling and external request behavior inside an already-placed module.

Output Requirements

When using this hub:

  1. State which sub-skills are selected.
  2. Explain why each selected sub-skill is needed.
  3. Apply only the minimum set required by the task.
  4. Keep compatibility-first decisions for legacy modules unless explicitly asked to refactor broadly.
  5. In review tasks, call out where findings follow known maintainer preferences rather than only generic engineering taste.
  6. For Issue/PR body writing, follow the docs site instead of inventing repository-specific text here; the drafting techniques live in the pr skill.
  7. For frontend tasks, state whether mas-frontend-standards and mas-frontend-ui were selected and why.

Review Checklist

  1. Selected sub-skills match the user request scope.
  2. Frontend tasks loaded the correct frontend skill pair.
  3. No layer-boundary violations are introduced.
  4. Shared schema semantics remain canonical.
  5. Function behavior and API contract stay consistent after changes.
  6. Relevant project rules were considered for API, config, script task, frontend task, and contribution-style changes.
  7. Contribution-process details were not duplicated from the docs site except as links or brief reminders.
  8. Every user-visible feature or fix includes exactly one changelog fragment under changelog.d/, and leaves CHANGELOG.md, res/version.json and the version numbers untouched.
  9. Any cherry-pick to a released branch was verified to touch backend files only.
  10. Every external CI action and container image is pinned to a full commit SHA or digest, with an updater-readable version comment where applicable; no mutable reference remains.

© 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

SKILL.md and 1 other file in .agents/skills/mas-skills of AUTO-MAS-Project/AUTO-MAS.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 699de5a

Compare with similar skills

Mas Skills 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 Skills compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mas Skills this skillAUTO-MAS-Project/AUTO-MAS711—~3.6kAutomated safety check: PassAGPL-3.0
System Designopenxlings/xlings6151 repos~328Automated safety check: PassApache-2.0
Deidentifying Multilingual Textmaziyarpanahi/openmed5.5k—~1.7kAutomated safety check: PassApache-2.0
Ariasickn33/agentic-awesome-skills47k1 repos~1.5kAutomated safety check: PassMIT
Reference EngineNoobyGains/godmode109—~5.4kAutomated safety check: PassMIT
Consent Pref Centermukul975/Privacy-Data-Protection-Skills301—~2.1kAutomated safety check: PassApache-2.0

Similar skills

  • System Design

    openxlings/xlings

    Design systems, services, and architectures. An agent skill from openxlings/xlings.

    615 GitHub starsUsed in 1 repo~328 tokens
    Backend & APIsAuto-check passed
  • Deidentifying Multilingual Text

    maziyarpanahi/openmed

    De-identify non-English clinical text on-device with OpenMed by passing lang= and locale= to deidentify().

    5.5k GitHub stars~1.7k tokensUpdated today
    DatabasesAuto-check passed
  • Aria

    sickn33/agentic-awesome-skills

    Designs the data model, API contracts, and structural foundation of the system.

    47k GitHub starsUsed in 1 repo~1.5k tokens
    Backend & APIsAuto-check passed
  • Reference Engine

    NoobyGains/godmode

    A skill your agent uses when building ANYTHING - the universal reference-first system that routes every task to proven reference implementations instead of generating from assumptions.

    109 GitHub stars~5.4k tokensUpdated 7 mo ago
    Backend & APIsAuto-check passed
  • Consent Pref Center

    mukul975/Privacy-Data-Protection-Skills

    Technical architecture guide for building a multi-purpose consent preference center.

    301 GitHub stars~2.1k tokensUpdated 6 mo ago
    Backend & APIsAuto-check passed
  • Da Content

    adobe/skills

    Use this when generating HTML for Adobe Document Authoring (DA, da.live) upload, uploading media binaries to DA, publishing to aem.live, or driving the DA admin API (auth, source PUT…

    197 GitHub stars~2.9k tokensUpdated yesterday
    Backend & APIsAuto-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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    Auto-check passed

Questions about Mas Skills

What does Mas Skills do?

A skill your agent uses when a task needs AUTO-MAS engineering conventions across frontend, UI, code style, schema naming, module boundaries, function design, API contracts, data modeling, script…. Mas Skills is an agent skill from AUTO-MAS-Project/AUTO-MAS. Use when a task needs AUTO-MAS engineering conventions across frontend, UI, code style, schema naming, module boundaries, function design, API contracts, data modeling, script adapters (MAA, SRC, MaaEnd, General, ok-script family such as Okww and OkNte, multi-engine HSR), plan schedules, or game community sign-in.

When should I use Mas Skills?

Mas Skills fits situations like: A task needs AUTO-MAS engineering conventions across frontend; module boundaries; function design; script adapters (MAA.

How do I install Mas Skills in Claude Code?

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

How do I install Mas Skills in Codex?

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

Can I use Mas Skills 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-skills -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-skills, .gemini/skills/mas-skills, .github/skills/mas-skills and .opencode/skills/mas-skills in your project.

What does Mas Skills need to run?

Going by SKILL.md and its folder, Mas Skills needs the command-line tools its instructions call (git and python). Our summary lists: Python 3.

Does Mas Skills access the network?

SKILL.md names 1 domain. As links in the text: doc.auto-mas.top. This is read from the text; nothing was executed.

Is Mas Skills 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 Skills use?

Mas Skills 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 Skills use?

About 3.6k 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 Skills?

Skills that share tags, products or a category with Mas Skills: System Design (openxlings/xlings, 615 stars), Deidentifying Multilingual Text (maziyarpanahi/openmed, 5.5k stars), Aria (sickn33/agentic-awesome-skills, 47k stars) and Reference Engine (NoobyGains/godmode, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mas Skills?

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.