技能 messaging-performance-analyzer

📦

messaging-performance-analyzer

Name: messaging-performance-analyzer
Author: sentdm

內容修訂 r1 安全 ⚙️ 外部命令

Diagnose Messaging Performance

Delivery data is difficult to interpret when statuses, channels, and webhook evidence disagree. This skill builds reliable cohorts and identifies the strongest supported cause.

支援: Claude Codex Code(CC)

🥈 80 銀級

Maintain this Skill? Claim it 🥈 80 銀級

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。

智能體請求

Review the Skillstore skill "messaging-performance-analyzer" from https://skillstore.io/skills/sentdm-messaging-performance-analyzer.md and its manifest at https://skillstore.io/api/skills/sentdm-messaging-performance-analyzer/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。

Markdown 詳情 GET /skills/sentdm-messaging-performance-analyzer.md 已簽名 manifest GET /api/skills/sentdm-messaging-performance-analyzer/manifest 已簽名 lockfile GET /api/skills/sentdm-messaging-performance-analyzer/lockfile

測試它

正在使用「messaging-performance-analyzer」。 Analyze an SMS export with 1,200 routed messages and 720 delivered messages.

預期結果:

Primary diagnosis: the largest observed loss is between routing and delivery. Verify compliance, opt-out, and provider error evidence for the affected cohort.

正在使用「messaging-performance-analyzer」。 Explain why delivered messages are missing from our customer database.

預期結果:

Delivery status is healthy in Sent.
Customer-side callbacks are incomplete.
Check webhook subscriptions, event history, and endpoint response failures next.

正在使用「messaging-performance-analyzer」。 Compare WhatsApp and SMS campaign results.

預期結果:

Report delivery for both channels, but report READ only as WhatsApp engagement. Keep counts, rates, exclusions, and cohort definitions visible.

安全審計

安全

v1 • 2026/9/11 開啟版本化報告

All 57 static findings are false positives caused by Markdown code formatting, documentation terminology, Python docstrings, and ordinary error handling. The script only reads a user-selected CSV or JSON file, computes local statistics, and prints results; no prompt injection, command execution, network access, or malicious intent was found.

已掃描檔案

1,252

分析行數

複核項目

已忽略的誤報

最近一次完成的靜態與語意稽核未偵測到已確認的安全發現。這並不能證明該 Skill 沒有副作用。

審計單位: codex

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。

開啟版本化報告

複製報告連結

https://skillstore.io/skills/sentdm-messaging-performance-analyzer/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/sentdm-messaging-performance-analyzer/security.svg)](https://skillstore.io/skills/sentdm-messaging-performance-analyzer?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/sentdm-messaging-performance-analyzer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sentdm-messaging-performance-analyzer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/sentdm-messaging-performance-analyzer.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

sentdm. (2026). messaging-performance-analyzer security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sentdm-messaging-performance-analyzer/audits/1

BibTeX 引用

@techreport{sentdm-sentdm-messaging-performance-analyzer-2026,
  author = {sentdm},
  title = {messaging-performance-analyzer security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/sentdm-messaging-performance-analyzer/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: "messaging-performance-analyzer security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "sentdm"
date-released: "2026-09-11"
url: "https://skillstore.io/skills/sentdm-messaging-performance-analyzer/audits/1"
identifiers:
  - type: other
    value: "skillstore:sentdm-messaging-performance-analyzer:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore 評分

評分依據證據置信度: 中

架構

可維護性

內容

社群

規範符合度

你可以打造什麼

Investigate delivery drops

Compare channel funnels, isolate the largest transition loss, and identify the evidence needed for a reliable diagnosis.

Debug missing webhook events

Distinguish message delivery problems from webhook configuration, subscription, or endpoint failures.

Review campaign performance

Measure delivery and engagement by profile, template, country, channel, and time window.

試試這些提示

Summarize a delivery export

Analyze this Sent MDR export. Report counts by channel and latest status, then identify the largest supported delivery issue.

Compare campaign periods

Compare these two campaign periods by channel, profile, template, and country. Show count and rate changes, then state the strongest supported explanation.

Diagnose webhook gaps

Sent shows delivered messages, but our database lacks callbacks. Compare status, activity, webhook history, subscriptions, and endpoint responses before naming the cause.

Build an escalation diagnosis

Analyze this multi-channel incident using explicit activity histories only. Reconcile all groups, quantify anomalies, rank hypotheses, and prepare one evidence-based escalation recommendation.

最佳實務

Define the cohort by time, profile, template, channel, country, and recipient segment before calculating rates.
Use Sent message identifiers and explicit activity histories for transition analysis.
Report counts with rates, retain unknown records, and end with one evidence-based verification step.

避免

Do not infer missing lifecycle stages from a latest-status snapshot.
Do not combine SMS, WhatsApp, and RCS before checking each channel separately.
Do not label traffic as carrier filtered without a stable baseline and sufficient evidence.