Навыки layer-reference-sets
📦

layer-reference-sets

Ревизия содержимого r1 Безопасно ⚙️ Внешние команды

Curate and Apply Layer Reference Sets

Inconsistent datasets and incompatible models can weaken a trained style while still consuming Creative Units. This skill guides curation, training choices, weight tuning, and contribution checks before generation.

Поддерживает: Claude Codex Code(CC)
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-reference-sets" from https://skillstore.io/skills/layerai-layer-reference-sets.md and its manifest at https://skillstore.io/api/skills/layerai-layer-reference-sets/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-reference-sets.md Подписанный manifest GET /api/skills/layerai-layer-reference-sets/manifest Подписанный lockfile GET /api/skills/layerai-layer-reference-sets/lockfile

Протестировать

Использование «layer-reference-sets». We have an approved character image and need six images this week. Should we train?

Ожидаемый результат:

Use the approved character image as a reference first. Training is not the initial recommendation for this small, short project.

Использование «layer-reference-sets». Our style collection contains twelve consistent pieces and eight pieces with different rendering. We will reuse it for months.

Ожидаемый результат:

  • Keep the twelve consistent pieces and exclude the eight with different rendering.
  • Use the general category for an overall aesthetic rather than a single subject.
  • Estimate training costs before starting and request confirmation above 20 Creative Units.
  • Estimate generation with automatic model selection and inspect reference set contributions before spending.

Использование «layer-reference-sets». A trained style looks weak with a pinned model, and the estimate reports degradation. Should I raise the weight?

Ожидаемый результат:

  • Check which reference set degraded and why.
  • Remove the pinned model or choose a compatible model, then request a new estimate.
  • Weight changes will not affect a set applied only as reference images or prompt text.
  • Do not report the trained LoRA as applied when the contribution report indicates otherwise.

Аудит безопасности

Безопасно
v1 • 11.10.2026 Открыть версионный отчет

All 24 static findings are false positives: Markdown tool names, category labels, a user-requested installation example, and model-selection guidance. No evidence found of shell backtick execution, system reconnaissance, prompt injection, or unauthorized data transfer. The documented workflow uses Layer uploads and paid training or generation, with estimates and confirmation above 20 Creative Units.

1
Просканировано файлов
111
Проанализировано строк
0
Пункты проверки
0
Ложные срабатывания проигнорированы

Факторы риска

⚙️ Внешние команды (23)
SKILL.md:15 SKILL.md:16 SKILL.md:17 SKILL.md:21 SKILL.md:30 SKILL.md:52 SKILL.md:53 SKILL.md:61 SKILL.md:64 SKILL.md:66 SKILL.md:78 SKILL.md:79 SKILL.md:82 SKILL.md:83 SKILL.md:92 SKILL.md:94 SKILL.md:95 SKILL.md:96 SKILL.md:98 SKILL.md:99 SKILL.md:100 SKILL.md:107 SKILL.md:108
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
Оценка безопасности

Копировать ссылку на отчёт

https://skillstore.io/skills/layerai-layer-reference-sets/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-reference-sets/security.svg)](https://skillstore.io/skills/layerai-layer-reference-sets?utm_source=security_passport_badge)

Значок HTML

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

Встраиваемая карточка

<iframe src="https://skillstore.io/embed/skills/layerai-layer-reference-sets.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-reference-sets security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/layerai-layer-reference-sets/audits/1

Цитата BibTeX

@techreport{layerai-layerai-layer-reference-sets-2026, author = {layerai}, title = {layer-reference-sets security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/layerai-layer-reference-sets/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-reference-sets 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-reference-sets/audits/1" identifiers: - type: other value: "skillstore:layerai-layer-reference-sets:audit:1" description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Средний
55
Архитектура
85
Сопровождаемость
87
Контент
65
Сообщество
83
Соответствие спецификации

Что вы можете построить

Maintain a studio style

Select consistent artwork, choose the general category, and plan a reusable reference set for ongoing team generation.

Build a character library

Separate subjects into reference sets and vary poses, angles, and expressions while preserving each character design.

Investigate weak style results

Review contribution warnings, model selection, and weight settings before spending on another generation.

Попробуйте эти промпты

Choose whether to train 
I need [asset count] assets for [project duration] using [approved artwork]. Recommend a reference image or trained reference set, and explain the choice.
Curate a training set 
Review [supplied images] for [subject or style]. Recommend exclusions, useful variation, separate sets, and the appropriate training category. Do not upload anything yet.
Plan a controlled training workflow 
Plan training for [approved dataset]. Estimate costs before paid actions and request confirmation above 20 Creative Units. Check contributions before generation and report missing tools.
Diagnose degraded style application 
Analyze [contribution report] and [run settings] for [reference sets]. Explain degradation, model compatibility, and weight effects. Recommend a revised estimate before any new spend.

Лучшие практики

  • Curate consistent, clean artwork and vary only the attributes that should change.
  • Match each set to one subject or style and select its training category deliberately.
  • Inspect price estimates and contribution reports before spending, and confirm actions above 20 Creative Units.

Избегать

  • Pad a dataset with inconsistent images or mix unrelated subjects into one reference set.
  • Pin a model without checking reference set compatibility, then treat weak output as a weight problem.
  • Treat weight as a binary setting or claim a degraded set applied successfully.

Часто задаваемые вопросы

What does this skill provide?
It provides guidance for Layer reference set decisions, dataset curation, training categories, weight tuning, and degradation diagnosis.
Can I use it with Claude, Codex, or Claude Code?
The report lists all three tools as supported. Executing the workflow still requires access to the relevant Layer tools.
When should I train instead of using a reference image?
Train for a look reused over months or a growing subject library. Try an approved reference image for smaller, short projects.
Which training category should I choose?
Choose character, object, scene, or effect for that specific intent. Use general for an overall aesthetic across subjects.
Does raising weight always strengthen the style?
No. Weight affects LoRA application only. It is ignored when a set contributes reference images or prompt text.
Can a degraded run still cost Creative Units?
Yes. A degraded run can succeed and still cost Creative Units. Check contribution reports on the estimate before generation.

Сведения для разработчиков

Автор

layerai

Лицензия

MIT

Ревизия Skillstore

r1

Примечание о версии

Автор не указал версию.

Репозиторий

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

Ссылка

ee0fcd6d9de455c669ab56b791cc7ead7b94348e

Актуальность поддержки

11.10.2026

Использование

0 загрузок · 0 просмотров

Структура файлов

📄 SKILL.md