audit-before-i-tweet
Review Your Tweet Before Publishing
Short tweets can lose context, overstate claims, or expose identifiable people. This skill checks a finished draft and ranks up to three fixes before publishing.
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 "audit-before-i-tweet" from https://skillstore.io/skills/prateeks367-audit-before-i-tweet.md and its manifest at https://skillstore.io/api/skills/prateeks367-audit-before-i-tweet/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
「audit-before-i-tweet」を使用しています。 Ready to post: Our tool cuts support costs by 50% for everyone. Evidence: one four-week customer pilot.
期待される結果:
- Fix 1: Replace 'for everyone' with the scope of the single customer pilot.
- Fix 2: Name the source for the 50% figure and verify how support costs were measured.
- Clean check: The subject is clear without surrounding context.
- Decision: Revise the claim before posting.
「audit-before-i-tweet」を使用しています。 Final review: We moved our weekly planning meeting from Monday to Tuesday. For our team, that leaves Monday free for focused work.
期待される結果:
- Clean checks: The subject is clear, and 'for our team' preserves the claim's scope.
- Clean checks: No numerical result or identifiable outside person appears in the draft.
- Voice: No reference posts were supplied, so personal voice consistency remains unverified.
- Decision: I would post this as written.
セキュリティ監査
安全All five static findings are false positives: four identify Markdown tool names, and one misclassifies editorial guidance as system reconnaissance. No evidence found of command execution, credential access, exfiltration, or prompt injection in SKILL.md. Optional VoiceMOAT publishing is described with a preview and one-time confirmation; its implementation is not included.
リスク要因
⚙️ 外部コマンド (4)
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/prateeks367-audit-before-i-tweet/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdownバッジ
[](https://skillstore.io/skills/prateeks367-audit-before-i-tweet?utm_source=security_passport_badge)HTMLバッジ
<a href="https://skillstore.io/skills/prateeks367-audit-before-i-tweet?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/prateeks367-audit-before-i-tweet/security.svg" alt="Skillstore security assessment" loading="lazy"></a>埋め込みカード
<iframe src="https://skillstore.io/embed/skills/prateeks367-audit-before-i-tweet.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
prateeks367. (2026). audit-before-i-tweet security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prateeks367-audit-before-i-tweet/audits/1BibTeX形式の引用
@techreport{prateeks367-prateeks367-audit-before-i-tweet-2026,
author = {prateeks367},
title = {audit-before-i-tweet security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/prateeks367-audit-before-i-tweet/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: "audit-before-i-tweet security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "prateeks367"
date-released: "2026-10-02"
url: "https://skillstore.io/skills/prateeks367-audit-before-i-tweet/audits/1"
identifiers:
- type: other
value: "skillstore:prateeks367-audit-before-i-tweet: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
Check a product announcement
Review an announcement for unclear subjects, unsupported numbers, and missing qualifiers before posting.
Review a client-related anecdote
Check whether readers could identify a client or misinterpret a professional story.
Prioritize final editorial fixes
Review a finished brand tweet, preserve its voice, and return no more than three prioritized changes.
これらのプロンプトを試す
Audit this finished tweet before I post it: [draft]. Rank up to three fixes and say whether you would post it unchanged.
Review [draft] for unsupported claims and identifiable people. Use [sources] as context, and tell me what still needs verification.
Audit [draft] as a standalone screenshot. Compare it with [full thought] to find unintended readings or lost qualifiers. Rank only necessary fixes.
Audit [draft] against [my published posts]. If VoiceMOAT is connected, use its voice profile and scoring. Rank fixes; do not publish without confirmation.
ベストプラクティス
- Provide a finished draft and supporting sources for numbers or factual claims.
- Supply the original thought when shortening may have removed important qualifiers.
- Use your own published posts as voice references and review every suggested change before publishing.
回避
- Requesting a new tweet from an empty brief instead of submitting a completed draft.
- Treating the review as a performance forecast or guaranteed factual verification.
- Rewriting the entire tweet when a small correction would resolve the issue.
よくある質問
Does this skill write tweets from scratch?
What does the audit check?
How many fixes will I receive?
Will it predict engagement or give a score?
Do I need VoiceMOAT?
Does it publish automatically?
開発者情報
作成者
prateeks367ライセンス
MIT
Skillstore リビジョン
r1
バージョンに関する注意
作者はバージョンを宣言していません。
参照
5726d703fd79596f46a4232d911221f962d9af1d
メンテナンスの新しさ
2026/10/2
利用状況
0 ダウンロード · 0 閲覧
ファイル構成
📄 SKILL.md