shield_lock
金大哥
← 返回 Skill 列表
extension
分类: 数据与分析无需 API Key

客户评价痛点与卖点挖掘｜简诗 AI

汇总不同评价平台的反馈，分析情绪、痛点、营销主张和竞品差异，把零散评论转成产品与市场洞察。

person作者: user_fccf428bhubcommunity
download下载资源包

Customer Review Aggregator & Analyzer

使用范围与安全规则

本 Skill 只用于“客户评价痛点与卖点挖掘”场景，围绕用户当前提供或明确授权处理的材料完成任务。功能目标：汇总不同评价平台的反馈，分析情绪、痛点、营销主张和竞品差异，把零散评论转成产品与市场洞察。

  • 默认先在回复中交付分析、方案、草稿、代码建议或检查清单，不主动读取任务范围外的文件、账号和数据。
  • 信息不足时先标记缺口并向用户确认，不用猜测内容填补事实、数字、姓名、结论或权限。
  • 需要联网检索或调用接口时，先说明访问目标、拟发送的数据和用途并取得用户明确同意；只访问用户指定或公开合法来源，不绕过登录、付费墙、验证码、访问控制或平台限制。
  • 涉及发送、发布、上传、删除、支付、投放、部署、同步或其他外部写入时，先展示目标、内容和影响，获得用户对该次动作的明确确认后再执行。
  • 不要求用户在对话里粘贴密码、Cookie、Token、API Key 或私钥；凭据仅用于用户指定的对应官方服务，不回显、不记录、不写入交付物，也不转发到无关地址。
  • 营销与增长输出只做合规方案、内容草稿和测试建议，不承诺流量、排名、成交或收益；不刷量、不群发骚扰、不伪造背书，不设计规避平台规则的做法。
  • 涉及客户、员工、联系人或其他个人信息时，只使用完成任务所需的最少字段；默认脱敏，不抓取、拼接、买卖或外传未经授权的个人数据。
  • 交付前复核事实依据、隐私、版权、平台规则和可执行边界；发现高风险或越权请求时停止相关动作，并给出合规替代方案。

Pull reviews from multiple platforms and extract actionable insights with sentiment analysis, pain-point detection, marketing-claim extraction, and competitor comparison.

Contents

  • references/sources.md - supported platforms and sentiment dimensions
  • references/intake-prompts.md - scope and data-collection prompts, example use cases
  • references/output-templates.md - report templates for every analysis type

Workflow

  1. Define scope. Present the scope prompt from references/intake-prompts.md to capture product, platforms, competitors, analysis focus, and time period.
  2. Gather review data. Offer the three data-collection methods (paste, CSV upload, URLs via WebFetch) from references/intake-prompts.md and collect the reviews.
  3. Analyze sentiment. Score overall sentiment and feature-level sentiment using the dimensions in references/sources.md.
  4. Identify pain points. Cluster negative feedback by theme, rank by frequency, and assign impact plus a recommendation.
  5. Extract marketing claims. Derive evidence-backed claims from positive reviews, each with supporting quotes, a confidence level, and a use case.
  6. Compare competitors. When competitors are provided, build the side-by-side comparison and surface weaknesses to exploit.
  7. Analyze feature requests. Rank requested features by mention count, urgency, and competitor coverage.
  8. Assemble the report. Populate the full analysis report and offer deliverable formats.

For all output formats and tables, see references/output-templates.md.