audit-before-i-publish
Audit Your Post Before Publishing
Finished posts can contain unsupported claims, privacy concerns, or unclear structure. This skill reviews the draft and ranks up to three fixes before publication.
使用我的智慧代理安裝
將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。
Review the Skillstore skill "audit-before-i-publish" from https://skillstore.io/skills/prateeks367-audit-before-i-publish.md and its manifest at https://skillstore.io/api/skills/prateeks367-audit-before-i-publish/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。
Agent 可讀資源
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。
測試它
正在使用「audit-before-i-publish」。 Review a finished post containing an unsourced growth figure, an identifiable customer, and a generic closing question.
預期結果:
- Readiness: Revise before publication.
- First: Source or remove the growth figure.
- Second: Confirm customer consent or remove identifying details.
- Third: Remove the closing question unless it invites a specific, relevant response.
- Clean checks: The draft follows one idea and uses readable line breaks.
正在使用「audit-before-i-publish」。 Review a focused post with an attributed statistic, no identifiable third parties, and a direct ending.
預期結果:
- Readiness: Publish as written.
- No changes recommended.
- Clean checks: The opening matches the body, the statistic is attributed, and the ending adds no unnecessary prompt.
- Voice assessment remains qualitative without a connected profile.
安全審計
安全All six static findings are false positives: Markdown tool names are not shell execution, and story and consent checks are not system reconnaissance. No evidence found of prompt injection, credential theft, or data exfiltration in SKILL.md. Optional VoiceMOAT tools are described, including publication with preview and confirmation, but no connector implementation is included.
風險因素
⚙️ 外部命令 (4)
分享與引用此報告
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。
複製報告連結
https://skillstore.io/skills/prateeks367-audit-before-i-publish/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/prateeks367-audit-before-i-publish?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/prateeks367-audit-before-i-publish?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/prateeks367-audit-before-i-publish/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/prateeks367-audit-before-i-publish.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>學術引用 (APA · BibTeX · CFF)
APA 引用
prateeks367. (2026). audit-before-i-publish security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prateeks367-audit-before-i-publish/audits/1BibTeX 引用
@techreport{prateeks367-prateeks367-audit-before-i-publish-2026,
author = {prateeks367},
title = {audit-before-i-publish security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/prateeks367-audit-before-i-publish/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-publish 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-publish/audits/1"
identifiers:
- type: other
value: "skillstore:prateeks367-audit-before-i-publish:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore 評分
評分依據 證據置信度: 中你可以打造什麼
Review a Professional Post
Check a finished LinkedIn post for unsupported claims, a weak opening, and unnecessary paragraphs before sharing it.
Check a Client Story
Review a customer anecdote for attribution, identifiable details, consent concerns, and promises the draft does not support.
Preserve a Personal Voice
Compare a finished draft with supplied writing examples and identify specific lines that sound inconsistent with the author.
試試這些提示
Audit this finished post: [draft]. Say whether you would publish it unchanged and give at most three fixes in priority order.
Audit this draft: [draft]. Review numbers, anecdotes, promises, and identifiable people using this context: [sources and consent details]. Flag missing evidence.
Audit this draft: [draft]. Compare its voice with these posts: [writing samples]. Identify specific mismatched lines without assigning a numerical score.
Audit this LinkedIn draft: [draft], using [sources], [consent context], and [voice samples]. Review each step, rank up to three fixes, and report clean checks. Do not rewrite the whole post or publish it.
最佳實務
- Provide the complete draft, intended platform, and sources for numerical claims.
- Include consent context for identifiable people and writing samples for voice comparison.
- Address the highest-priority issue first and retain passages that passed the review.
避免
- Use the audit to generate a post from nothing.
- Request guaranteed engagement or a numerical voice score without a connected profile.
- Rewrite the entire draft when one targeted change resolves the issue.
常見問題
What should I provide?
Will it rewrite my entire post?
Can it approve a draft without changes?
Does it predict how a post will perform?
Does it verify every claim independently?
What changes with VoiceMOAT?
開發者詳細資訊
作者
prateeks367授權
MIT
Skillstore 修訂
r1
版本提示
作者未聲明版本。
引用
5726d703fd79596f46a4232d911221f962d9af1d
維護新鮮度
2026/10/2
使用量
0 次下載 · 0 次瀏覽
檔案結構
📄 SKILL.md