📦

layer

Name: layer
Author: layerai

Ревизия содержимого r1 Безопасно ⚙️ Внешние команды🌐 Доступ к сети

Generate Game Assets with Layer MCP

Creative teams need to coordinate models, reference files, and costs across asset generation tasks. This skill guides Layer MCP requests from workspace selection to completed assets and style warnings.

Поддерживает: Claude Codex Code(CC)

🥉 77 Бронза

Maintain this Skill? Claim it 🥉 77 Бронза

Установить с помощью моего Агента

Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.

Запрос агента

Review the Skillstore skill "layer" from https://skillstore.io/skills/layerai-layer.md and its manifest at https://skillstore.io/api/skills/layerai-layer/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.

Ресурсы для AI-агентов

Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.

Markdown-детали GET /skills/layerai-layer.md Подписанный manifest GET /api/skills/layerai-layer/manifest Подписанный lockfile GET /api/skills/layerai-layer/lockfile

Протестировать

Использование «layer». Explain the cost decision in the documented four-sprite example.

Ожидаемый результат:

The example estimates four variations at 7 CUs against a balance of 900 CUs.
This single run is below the 20 CU confirmation threshold.
Four distinct sprite prompts require separate runs and approval of the planned sequence cost.

Использование «layer». A trained style did not apply, but the generation completed. Explain the result.

Ожидаемый результат:

The generation completed, but the requested trained style did not apply.
The run still consumes Creative Units.
Report the affected style and the returned warning before presenting the assets.

Использование «layer». A model identifier returns MODEL_NOT_FOUND. What should happen next?

Ожидаемый результат:

Discover available models again in the selected workspace.
Check the replacement model requirements and obtain a new price estimate before execution.
Do not reuse or guess the unavailable identifier.

Аудит безопасности

Безопасно

v1 • 11.10.2026 Открыть версионный отчет

All 71 static findings are false positives: Markdown formatting, expected Layer service access, and unrelated prose matched execution or reconnaissance patterns. No evidence found of prompt injection, credential theft, or unauthorized data transfer in SKILL.md. Actual use requires authenticated external services, reference uploads when requested, and paid generation with documented spending confirmations.

Просканировано файлов

153

Проанализировано строк

Пункты проверки

Ложные срабатывания проигнорированы

Факторы риска

Последний завершенный статический и семантический аудит не обнаружил подтвержденных проблем безопасности. Это не доказывает отсутствие побочных эффектов у навыка.

Аудитор:: codex

Поделиться и цитировать этот отчет

Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.

Открыть версионный отчет

Копировать ссылку на отчёт

https://skillstore.io/skills/layerai-layer/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Значок Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/layerai-layer/security.svg)](https://skillstore.io/skills/layerai-layer?utm_source=security_passport_badge)

Значок HTML

<a href="https://skillstore.io/skills/layerai-layer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/layerai-layer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Встраиваемая карточка

<iframe src="https://skillstore.io/embed/skills/layerai-layer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Академические ссылки (APA · BibTeX · CFF)

Цитата APA

layerai. (2026). layer security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/layerai-layer/audits/1

Цитата BibTeX

@techreport{layerai-layerai-layer-2026,
  author = {layerai},
  title = {layer security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/layerai-layer/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "layer security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "layerai"
date-released: "2026-10-11"
url: "https://skillstore.io/skills/layerai-layer/audits/1"
identifiers:
  - type: other
    value: "skillstore:layerai-layer:audit:1"
    description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Средний

Архитектура

Сопровождаемость

Контент

Сообщество

Соответствие спецификации

Что вы можете построить

Produce Sprite Variations

Create variations of a building sprite prompt after selecting a suitable model and reviewing the estimated workspace cost.

Maintain a Trained Visual Style

Apply workspace reference sets across asset requests and identify any styles that fail to apply.

Coordinate Creative Production

Prepare reference files, estimate a sequence budget, and track image or video generation through completion.

Попробуйте эти промпты

Discover a Suitable Model

In [workspace], find a model for [asset type] and check its requirements. Report available options without starting generation.

Generate a Costed Batch

Create four variations of [sprite prompt] in [workspace]. Estimate cost first, apply the spending gate, and return completed asset links.

Use References and Trained Styles

Use [reference file] and [trained style] in [workspace] for [asset]. Estimate first, report style warnings, and obtain required approval before execution.

Plan a Multi-Run Production Sequence

Plan separate runs for [asset list] in [workspace]. Present total estimated cost for approval, reuse file identifiers, and monitor results and style degradation.

Лучшие практики

Confirm the paying workspace, discover models for the task, and review their requirements before preparing a run.
Estimate every run and present planned sequence totals before obtaining required approval, even when negative balances are allowed.
Reuse generated file identifiers, follow returned polling intervals, and report reference style warnings accurately.

Избегать

Guessing model identifiers or filtering out suitable models with unnecessary capability settings.
Executing without an estimate or treating negative balance permission as approval to bypass spending confirmation.
Treating batch variations as distinct assets or reporting degraded reference styles as successfully applied.

Часто задаваемые вопросы

What must I connect before using this skill?

Connect your MCP client to the documented Layer endpoint, complete OAuth, and select an accessible workspace. Connection instructions are in a separate skill.

Which asset types does the guidance cover?

It covers model selection for images, video, 3D meshes, and audio. Specialized craft guidance refers to related skills.

When is spending confirmation required?

Single runs above 20 CUs require explicit approval. Planned sequences require presenting their total cost for agreement before starting.

Can one batch create several different assets?

A batch creates variations of one prompt, with sizes from 1 to 16. Distinct prompts require separate runs.

How are reference files provided?

Local files use signed upload URLs. Public files use the import tool, while completed assets reuse their existing file identifiers.

Does a completed run guarantee that my trained style applied?

No. Check degradation warnings during estimation, execution, and polling. A successful run can still omit the requested style and consume credits.

Сведения для разработчиков

Автор

layerai

Лицензия

MIT

Ревизия Skillstore

Примечание о версии

Автор не указал версию.

Репозиторий

https://github.com/layerai/skills/tree/315d06db6f760160b26293fd867ac759942e2106/skills/layer

Ссылка

d4f0bfa8bc3ba02d68c38df2d1ed444e3fd84fc2

Актуальность поддержки

11.10.2026

Использование

0 загрузок · 0 просмотров

Структура файлов

📄 SKILL.md