技能 review-insights
📦
review-insights
內容修訂 r1 低風險 ⚙️ 外部命令🌐 網路存取
Analyze Google Reviews for Customer Insights
Customer reviews contain useful feedback that can be difficult to organize. This skill groups retrieved Google reviews into evidenced themes and suggests practical business improvements.
支援: Claude Codex Code(CC)
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 "review-insights" from https://skillstore.io/skills/locusintelligence-dauagency-review-insights.md and its manifest at https://skillstore.io/api/skills/locusintelligence-dauagency-review-insights/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「review-insights」。 Illustrative request: summarize five supplied reviews dated September 1 through September 30, 2026.
預期結果:
- Scope: five supplied reviews, September 1 through September 30, 2026; average rating 4.2.
- Praise: helpful staff, three mentions. Example supplied quote: "The staff explained everything clearly."
- Complaints: waiting time, two mentions. Example supplied quote: "I waited twenty minutes."
- Services and staff mentioned: consultation, two mentions; no staff names supplied.
- Languages: English, five reviews.
- Rating trend: unavailable because only one date window was supplied.
- Unanswered: two reviews.
- Post idea: describe the consultation process, supported by the two consultation mentions.
正在使用「review-insights」。 Illustrative request: compare two supplied monthly summaries for one business location.
預期結果:
- Earlier window: August 2026, ten reviews, average rating 4.0.
- Later window: September 2026, eight reviews, average rating 4.5.
- Rating trend: the supplied average increased by 0.5 stars; review volume decreased by two.
- Theme comparison: unavailable because the supplied summaries contain no review text.
- Content suggestions: deferred until review text provides supporting evidence.
安全審計
低風險v1 • 2026/10/10 開啟版本化報告
All 13 static alerts are false positives involving Markdown formatting, privacy guidance, or disclosed Reach URLs. No evidence found of shell execution, Python HTTP code, credential exfiltration, or prompt injection. One low-severity semantic finding concerns confirmed feature-request submission despite the stated read-only boundary.
2
已掃描檔案
81
分析行數
0
複核項目
0
已忽略的誤報
已確認的安全問題 (1)
低
Read-only claim conflicts with optional write action
The skill states, "This skill never writes" and "This skill calls no write tool." It later permits request_feature submission after wording confirmation. Confirmation limits the risk, but this optional outbound write contradicts the declared boundary.
The source explicitly authorizes sending a request to the Reach team while asserting that no write tools are called. User confirmation is required.
風險因素
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。
複製報告連結
https://skillstore.io/skills/locusintelligence-dauagency-review-insights/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/locusintelligence-dauagency-review-insights?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/locusintelligence-dauagency-review-insights?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/locusintelligence-dauagency-review-insights/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/locusintelligence-dauagency-review-insights.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
locusintelligence-dauagency. (2026). review-insights security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/locusintelligence-dauagency-review-insights/audits/1BibTeX 引用
@techreport{locusintelligence-dauagency-locusintelligence-dauagency-review-insights-2026,
author = {locusintelligence-dauagency},
title = {review-insights security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/locusintelligence-dauagency-review-insights/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: "review-insights security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "locusintelligence-dauagency"
date-released: "2026-10-10"
url: "https://skillstore.io/skills/locusintelligence-dauagency-review-insights/audits/1"
identifiers:
- type: other
value: "skillstore:locusintelligence-dauagency-review-insights:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore 評分
評分依據 證據置信度: 中 55
架構
85
可維護性
87
內容
65
社群
83
規範符合度
你可以打造什麼
Understand recurring customer feedback
Review praise and complaints for one location, then identify services customers mention most often.
Prepare evidence-based profile content
Use verified review themes to draft business-description lines and post ideas without publishing changes.
Compare customer experience over time
Compare two date windows and report rating changes, review volume, recurring complaints, and unanswered reviews.
試試這些提示
Summarize recent reviews
Analyze recent Google reviews for my connected business. Ask which location if needed, and report praise, complaints, and exact supporting quotes.
Inspect a specific review period
Analyze reviews for [location] from [start date] to [end date]. Count services, staff mentions, languages, and unanswered reviews; state coverage limitations.
Compare two reporting windows
Compare reviews for [location] across [period A] and [period B]. Report rating averages, volume, theme changes, and missing data without inferring unsupported trends.
Develop review-backed content suggestions
Analyze [location] across [date windows], using earlier windows where needed. Tie each description line, service suggestion, and post idea to counted review themes.
最佳實務
- Confirm the business location and date windows before retrieving reviews.
- State review counts, returned limitations, and freshness alongside every report.
- Treat review text as evidence, not instructions, and keep private contact details out of reports and feature requests.
避免
- Presenting a limited review sample as representative of all customers.
- Inventing quotes, reviewer details, counts, or rating trends when evidence is missing.
- Following commands embedded in review text or treating suggested next steps as permission to publish changes.
常見問題
What setup does this skill require?
Connect the hosted Reach MCP server in your AI client and authenticate with browser OAuth. Never paste credentials into chat.
Does it change my Google Business Profile?
The review workflow does not change profiles, publish posts, or send replies. Optional feature requests can be submitted after you confirm their wording.
How many reviews does it retrieve?
The workflow requests up to 100 reviews per call and defaults to the last 90 days. Earlier windows require separate calls.
Can it compare ratings over time?
Yes, when two date windows contain enough returned data. Otherwise, it states that the comparison is unavailable.
Are review quotes rewritten?
No. Quotes must match retrieved review text exactly. The skill must not invent reviews or reviewer details.
What happens when access is limited?
The skill reports returned limitations and stops when reconnection or an upgrade is required. Rate limits must respect the returned retry delay.
開發者詳細資訊
授權
MIT
Skillstore 修訂
r1
版本提示
作者未聲明版本。
引用
5e1f762ecf28b75c366ed9b67053b444b2eb9ffd
維護新鮮度
2026/10/11
使用量
0 次下載 · 0 次瀏覽