writingmate-mcp
Compare AI Models and Generate Media
Choosing and testing AI models across separate services takes time. Writingmate connects an MCP host to model discovery, text comparison, image generation, and video 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 "writingmate-mcp" from https://skillstore.io/skills/writingmate-writingmate-mcp.md and its manifest at https://skillstore.io/api/skills/writingmate-writingmate-mcp/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
「writingmate-mcp」を使用しています。 Compare two available text models for a concise product announcement.
期待される結果:
- Selected model IDs: example-text-a and example-text-b.
- Model A was more concise and followed the requested structure.
- Model B provided stronger supporting detail but exceeded the target length.
- Recommendation: Model A for the final announcement.
「writingmate-mcp」を使用しています。 Create a square product image with a white background and no text.
期待される結果:
Generated one 1024 by 1024 image with the selected image model. The returned asset is ready for review.
「writingmate-mcp」を使用しています。 Generate an eight-second landscape video and report its final status.
期待される結果:
Started the video job, retained its generation ID, and polled at reasonable intervals. The final asset is returned after successful completion.
セキュリティ監査
安全Most findings are false positives caused by Markdown backticks, fenced examples, documentation links, and a documented Codex configuration path. Three low-severity findings are confirmed because setup connects an MCP host to Writingmate's remote endpoint, where submitted prompts and generation inputs leave the local environment. No prompt injection, covert command execution, credential exposure, or malicious system access was found.
機能レビュー項目 (3)
これらは、このスキルに期待される可能性のある実際のローカル機能であるため、レビューが必要ですが、確認済みの悪意ある動作としてはカウントされません。
リスク要因
⚙️ 外部コマンド (32)
🌐 ネットワークアクセス (9)
📁 ファイルシステムへのアクセス (2)
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/writingmate-writingmate-mcp/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdownバッジ
[](https://skillstore.io/skills/writingmate-writingmate-mcp?utm_source=security_passport_badge)HTMLバッジ
<a href="https://skillstore.io/skills/writingmate-writingmate-mcp?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/writingmate-writingmate-mcp/security.svg" alt="Skillstore security assessment" loading="lazy"></a>埋め込みカード
<iframe src="https://skillstore.io/embed/skills/writingmate-writingmate-mcp.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
writingmate. (2026). writingmate-mcp security audit report (audit version 1) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/writingmate-writingmate-mcp/audits/1BibTeX形式の引用
@techreport{writingmate-writingmate-writingmate-mcp-2026,
author = {writingmate},
title = {writingmate-mcp security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/writingmate-writingmate-mcp/audits/1},
note = {Author version 1.0.0}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "writingmate-mcp security audit report (audit version 1)"
version: "1.0.0"
type: report
authors:
- name: "writingmate"
date-released: "2026-07-28"
url: "https://skillstore.io/skills/writingmate-writingmate-mcp/audits/1"
identifiers:
- type: other
value: "skillstore:writingmate-writingmate-mcp: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
Evaluate Text Models
Run the same task across available models, preserve each response, and compare results using task-specific criteria.
Create Campaign Media
Generate an image or video from a detailed brief while preserving composition, size, and exclusion requirements.
Add Multi-Model Tools
Connect an MCP host to model discovery and generation tools without integrating each provider separately.
これらのプロンプトを試す
List the text models available to my Writingmate account. Group them by capability and show each exact model ID.
Compare two available text models on this task: [task]. Use the same prompt and settings, then recommend one with brief evidence.
Find an available image model and create a [size] image of [subject] with [composition]. Preserve these exclusions: [exclusions].
Compare three available models for [campaign brief]. Use the strongest result to generate one image, then request approval before starting a video.
ベストプラクティス
- Call list_models before selection and use only exact model IDs returned by the server.
- Use identical prompts and supported settings when comparing model responses.
- Confirm costs and data sensitivity before large batches or regulated content transfers.
回避
- Do not invent model IDs or silently replace a failed model.
- Do not claim that text or media was generated without a successful tool result.
- Do not expose Developer Keys in prompts, public files, screenshots, or issue reports.
よくある質問
What do I need to use this skill?
How does authentication work?
How does the skill choose a model?
Can I send sensitive information?
How many images can one request create?
How are video requests handled?
開発者情報
作成者
writingmateライセンス
MIT
作者バージョン
v1.0.0
Skillstore リビジョン
r1
参照
ca0af473cd6616aacb957aeb71f8d4b90acedb3a
メンテナンスの新しさ
2026/7/28
利用状況
0 ダウンロード · 0 閲覧
ファイル構成
📄 SKILL.md