cold-email-reply-scoring
Classify Cold Email Replies and Prioritize Follow-Up
Cold email reply queues mix buying interest, uncertainty, rejection, and automated responses. This skill provides classification rules and routing guidance, with deterministic execution requiring a separate classifier script.
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 "cold-email-reply-scoring" from https://skillstore.io/skills/cmj-hub-cold-email-reply-scoring.md and its manifest at https://skillstore.io/api/skills/cmj-hub-cold-email-reply-scoring/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「cold-email-reply-scoring」。 Reply: Please send a calendar link. What is the price? Received 27 minutes after sending. No routing configuration supplied.
預期結果:
- Suggested category: buy-signal.
- Evidence: explicit calendar and pricing requests.
- Numeric confidence: unavailable without the classifier.
- Recommended routing: request the brand routing configuration before selecting a destination.
正在使用「cold-email-reply-scoring」。 Reply: I am out of office until Monday. Received two minutes after sending.
預期結果:
- Suggested category: auto-reply.
- Evidence: explicit out-of-office language and rapid response timing.
- Recommended routing: exclude from normal reply routing.
正在使用「cold-email-reply-scoring」。 Reply: Maybe later. No additional conversation context supplied.
預期結果:
- Suggested category: neutral, pending review.
- Evidence: delayed interest without a commitment.
- Review required: the short reply lacks enough context for confident interpretation.
- Numeric confidence: unavailable without the classifier.
安全審計
安全All 21 static findings are false positives involving Markdown delimiters or fixed project-relative references. No evidence found of prompt injection, credential theft, or unauthorized data transfer in SKILL.md. The referenced classifier and supporting dependencies are absent from the audited package, so their behavior and safety remain unverified.
風險因素
⚙️ 外部命令 (18)
📁 檔案系統存取 (3)
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/cmj-hub-cold-email-reply-scoring/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/cmj-hub-cold-email-reply-scoring?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/cmj-hub-cold-email-reply-scoring?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/cmj-hub-cold-email-reply-scoring/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/cmj-hub-cold-email-reply-scoring.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
cmj-hub. (2026). cold-email-reply-scoring security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cmj-hub-cold-email-reply-scoring/audits/1BibTeX 引用
@techreport{cmj-hub-cmj-hub-cold-email-reply-scoring-2026,
author = {cmj-hub},
title = {cold-email-reply-scoring security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/cmj-hub-cold-email-reply-scoring/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: "cold-email-reply-scoring security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "cmj-hub"
date-released: "2026-10-03"
url: "https://skillstore.io/skills/cmj-hub-cold-email-reply-scoring/audits/1"
identifiers:
- type: other
value: "skillstore:cmj-hub-cold-email-reply-scoring: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
Prioritize Sales Replies
Identify explicit meeting and pricing requests, then recommend follow-up using the supplied brand routing rules.
Review a Reply Queue
Apply the documented batch workflow when dependencies are available, separating automated replies and uncertain classifications.
Check Campaign Responses
Distinguish interest, delayed decisions, and rejection while retaining evidence for human review.
試試這些提示
Classify this reply using the documented categories: [reply]. Explain the matched signals. Do not invent a numeric score without the classifier.
Assess [reply], received [minutes] after sending, using [routing rules]. Explain the recommended category and route. Report any unavailable dependencies.
Review [replies] for ambiguity, automated responses, and unsubscribe requests. Explain category candidates and flag uncertain cases for human review.
With the reviewed classifier and dependencies available, score [local batch file] using [routing rules]. Summarize results and flag confidence below 0.6.
最佳實務
- Verify the referenced classifier and supporting files before executing the batch command.
- Supply reply timing and brand routing rules, and remove unnecessary personal information from shared examples.
- Review uncertain classifications manually and honor explicit unsubscribe requests.
避免
- Presenting illustrative confidence values or accuracy claims as verified classifier results.
- Assuming routing recommendations automatically send messages or create CRM records.
- Automatically routing ambiguous or non-English replies without human review.