スキル tech-writing-proofread
📦
tech-writing-proofread
コンテンツリビジョン r1 安全 ⚙️ 外部コマンド
Proofread English Technical Documents
Technical drafts can contain language errors and inconsistent terminology that make instructions harder to follow. This skill provides specific corrections, reasons, and issue counts while preserving the authorial voice.
対応: Claude Codex Code(CC)
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。
エージェントリクエスト
Review the Skillstore skill "tech-writing-proofread" from https://skillstore.io/skills/alapha888-tech-writing-proofread.md and its manifest at https://skillstore.io/api/skills/alapha888-tech-writing-proofread/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
「tech-writing-proofread」を使用しています。 The system call the callback. Examples are available on github.
期待される結果:
- 1. [Grammar] Original: The system call the callback. Suggestion: The system calls the callback. Reason: Singular subject requires calls.
- 2. [Proper noun] Original: github. Suggestion: GitHub. Reason: Use official product casing.
- Statistics: 2 items; grammar 1, proper noun 1.
「tech-writing-proofread」を使用しています。 Register a callback function. The callback function handles errors. The callback handles completion. Simply invoke the handler.
期待される結果:
- 1. [Terminology] Original: The callback handles completion. Suggestion: The callback function handles completion. Reason: Use the most frequent term consistently.
- 2. [Style] Original: Simply invoke the handler. Suggestion: Invoke the handler. Reason: Remove filler.
- Statistics: 2 items; terminology 1, style 1.
セキュリティ監査
安全v1 • 2026/10/6 バージョン別レポートを開く
All six static findings are false positives caused by Markdown backticks and plain-text example fences. No evidence found of executable commands, data exfiltration, or prompt injection in SKILL.md.
1
スキャンされたファイル
57
解析済み行数
0
レビュー項目
0
誤検知を無視
リスク要因
⚙️ 外部コマンド (6)
最新の完了済み静的・セマンティック監査では、確認済みのセキュリティ検出事項は見つかりませんでした。これは、スキルに副作用がないことを証明するものではありません。
監査者: codex
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/alapha888-tech-writing-proofread/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdownバッジ
[](https://skillstore.io/skills/alapha888-tech-writing-proofread?utm_source=security_passport_badge)HTMLバッジ
<a href="https://skillstore.io/skills/alapha888-tech-writing-proofread?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/alapha888-tech-writing-proofread/security.svg" alt="Skillstore security assessment" loading="lazy"></a>埋め込みカード
<iframe src="https://skillstore.io/embed/skills/alapha888-tech-writing-proofread.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
alapha888. (2026). tech-writing-proofread security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/alapha888-tech-writing-proofread/audits/1BibTeX形式の引用
@techreport{alapha888-alapha888-tech-writing-proofread-2026,
author = {alapha888},
title = {tech-writing-proofread security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/alapha888-tech-writing-proofread/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: "tech-writing-proofread security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "alapha888"
date-released: "2026-10-06"
url: "https://skillstore.io/skills/alapha888-tech-writing-proofread/audits/1"
identifiers:
- type: other
value: "skillstore:alapha888-tech-writing-proofread: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 55
アーキテクチャ
85
保守性
87
コンテンツ
65
コミュニティ
83
仕様準拠
作成できるもの
Review a README
Find language errors, inconsistent product casing, and unclear procedural wording before publishing repository documentation.
Check an API reference
Review terminology, grammatical precision, acronym expansion, and parallel headings without changing technical claims.
Polish a technical tutorial
Identify filler words, sentence errors, and inconsistent instructions while preserving a conversational voice.
これらのプロンプトを試す
Proofread a short passage
Proofread this English technical passage: [paste text]. Return an Original / Suggestion / Reason checklist and issue counts.
Review README instructions
Proofread this README in one pass: [paste README]. Check grammar, product casing, inline code formatting, and numbered steps. Preserve the existing voice.
Check API terminology
Review this API reference: [paste reference]. Build a terminology list and flag inconsistent names, nonparallel headings, and unexpanded acronyms. Mark uncertain claims [verify].
Audit a complete tutorial
Proofread this complete tutorial: [paste tutorial]. Check all six review categories, preserve its conversational tone, and avoid paragraph rewrites. Cite lines or short quotes. End with category counts.
ベストプラクティス
- Provide the complete document so terminology and tone can be checked consistently.
- Identify whether the draft is a tutorial, API reference, blog post, or README.
- Review each suggestion and confirm items marked [verify] before applying changes.
回避
- Requesting complete paragraph rewrites instead of specific proofreading suggestions.
- Treating suspected factual errors as verified corrections.
- Requesting repeated polishing passes without a defined stopping point.
よくある質問
What kinds of documents does this skill review?
It reviews English technical documents, including READMEs, tutorials, API references, and technical blog drafts.
Does it rewrite my document?
No. It provides specific corrections and reasons while preserving the existing voice and avoiding complete paragraph rewrites.
Does it check technical accuracy?
It flags suspected factual errors for verification. It does not establish technical correctness or silently change uncertain claims.
How does it handle inconsistent terminology?
It identifies multiple names for the same concept and recommends the most frequent form in the document.
What does the output include?
An Original / Suggestion / Reason checklist, line numbers or short quotes, verification flags, and issue counts by category.
Which AI tools are supported?
The report lists Claude, Codex, and Claude Code as supported tools.