layer-reference-sets
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.
自分のエージェントでインストール
このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。
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.エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。
エージェントが読めるリソース
AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。
テストする
「layer-reference-sets」を使用しています。 We have an approved character image and need six images this week. Should we train?
期待される結果:
Use the approved character image as a reference first. Training is not the initial recommendation for this small, short project.
「layer-reference-sets」を使用しています。 Our style collection contains twelve consistent pieces and eight pieces with different rendering. We will reuse it for months.
期待される結果:
- 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.
「layer-reference-sets」を使用しています。 A trained style looks weak with a pinned model, and the estimate reports degradation. Should I raise the weight?
期待される結果:
- 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.
セキュリティ監査
安全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.
リスク要因
このレポートを共有・引用
バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。
レポートリンクをコピー
https://skillstore.io/skills/layerai-layer-reference-sets/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdownバッジ
[](https://skillstore.io/skills/layerai-layer-reference-sets?utm_source=security_passport_badge)HTMLバッジ
<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>埋め込みカード
<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>学術引用 (APA · BibTeX · CFF)
APA形式の引用
layerai. (2026). layer-reference-sets security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/layerai-layer-reference-sets/audits/1BibTeX形式の引用
@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"
Skillstore スコア
このスコアの理由 証拠の信頼度: 中作成できるもの
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.
これらのプロンプトを試す
I need [asset count] assets for [project duration] using [approved artwork]. Recommend a reference image or trained reference set, and explain the choice.
Review [supplied images] for [subject or style]. Recommend exclusions, useful variation, separate sets, and the appropriate training category. Do not upload anything yet.
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.
Analyze [contribution report] and [run settings] for [reference sets]. Explain degradation, model compatibility, and weight effects. Recommend a revised estimate before any new spend.
ベストプラクティス
- 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.
回避
- 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.