Automated summary
This agent analyzes e-commerce customer reviews (a local CSV or Amazon data pulled via Sorftime) and produces a 22-dimension labeled dataset, an insight report and, optionally, an HTML dashboard plus a Feishu document sync.
Strengths
- End-to-end, repeatable pipeline: collection, 22-dimension tagging, insight report and visualization from a single Python command.
- Guided question-by-question workflow (data source, review volume, Feishu sync, dashboard theme, signature) that avoids silent assumptions.
- Six HTML dashboard themes built on a shared base, matching different reporting contexts (executive, analytics, technical).
- Built-in Sorftime ingestion and Feishu sync, with CSV and Markdown outputs you can reuse outside the tool.
Limitations
- Requires external Python packages (pandas, jinja2, requests, tqdm) and, for some modes, a Sorftime API key or an authenticated lark-cli.
- The interactive flow explicitly relies on the AskUserQuestion tool, so it runs more smoothly in Claude Code than in other agents.
- Documentation is slightly inconsistent on report length (14 chapters stated, 13 in the output table) and the internal logic of the tag dimensions is not described.
Use it to turn a batch of Amazon reviews or a CSV of comments into an insight report and a presentation-ready dashboard quickly.
Avoid it when you need bespoke statistical modeling or a fully custom tagging schema, since it enforces its own 22 dimensions and report format.
Security analysis
CautionNo destructive, obfuscated, or credential-exfiltrating instructions appear in the SKILL.md; commands are standard python3 invocations for a data-analysis workflow. However it leverages bash, unpinned pip installs, network access (Sorftime/requests), secret handling via dotenv, and cloud writes through lark-cli, all legitimate but powerful. Hence caution rather than safe.
- •Uses bash to run pip install with unpinned packages (pandas, jinja2, requests, python-dotenv, tqdm), enabling potential supply-chain drift
- •Delegates core execution to an external main.py not included/auditable in the skill bundle
- •Requires an API key (Sorftime) via environment/.env and performs network calls to a third-party data source
- •Feishu sync relies on an externally authenticated lark-cli, meaning the skill can write to linked cloud documents
Examples
Analyse le fichier reviews_airpods.csv, limite à 100 avis, génère le rapport et le tableau de bord avec le thème premium-gold, sans synchronisation Feishu.Récupère les avis de l'ASIN B001OAXE0S sur le site US via Sorftime, analyse 300 avis, puis synchronise le rapport et les graphiques dans un document Feishu.Analyse ces avis clients et extrais le profil utilisateur, les principaux points de douleur et les opportunités produit, en style dark-tech pour une revue technique.name: review-analyzer-skill version: 2.0.0 author: Buluu@新西楼 description: | Agent 原生的电商评论深度分析工具 V2.0。 支持22维度智能标签、14章深度洞察报告、6套主题可视化看板(共享基座+玻璃拟态)、Sorftime平台数据对接、飞书文档同步。
当用户需要以下功能时触发:
- 分析电商产品评论(Amazon等平台)
- 从评论中提取用户画像、痛点和VOC(客户之声)
- 生成产品洞察报告和机会点分析
- 创建专业的可视化分析看板(6套主题可选)
- 通过Sorftime获取产品评论数据
- 将分析结果同步到飞书文档
触发关键词:电商评论分析、评论分析、竞品分析、用户洞察、VOC分析、产品优化、市场调研、评论数据挖掘、Sorftime license: MIT allowed-tools:
- bash
Review Analyzer Skill V2.0 — Agent 原生版
AI驱动的电商评论深度分析工具,Agent原生设计,任何主流AI Coding Agent均可运行。
核心特性
- 22维度智能标签系统: 人群/场景/功能/质量/服务/体验/市场/情感
- 14章深度洞察报告: 洞察总览→用户画像→卖点痛点→改进建议→行动仪表盘→数据附录
- 6套主题可视化看板: 共享基座架构,玻璃拟态质感(Premium Gold / Dark Tech / Linear Minimal / PostHog Analytics / Stripe Executive / Warm Editorial)
- Sorftime数据对接: 通过MCP/API/CLI获取亚马逊产品评论数据
- 飞书完整同步: 文档 + 画板图表一键同步到飞书
快速开始
环境准备
pip install pandas jinja2 requests python-dotenv tqdm
数据输入方式
# 方式1: 本地CSV文件(原有方式)
python3 main.py "reviews.csv" --max-reviews 100 --creator "AI Assistant"
# 方式2: 从Sorftime获取数据
python3 main.py --source sorftime --asin B001OAXE0S --site US --max-reviews 100 --creator "AI Assistant"
工作流程
第一步:收集参数
❗ 必须使用 AskUserQuestion 工具依次收集,严禁跳过或猜测用户意图。
Q1: 数据来源(必须)
- "本地CSV文件(上传文件路径)"
- "Sorftime平台获取(需要API Key,输入ASIN即可)"
Q1.5: Sorftime字段选择(仅当选择Sorftime时) 展示可用字段清单,必选字段已锁定(标题、正文、星级),推荐字段可勾选。
Q2: 分析数量(必须)
- "100条 (推荐) - 平衡速度与质量"
- "300条 - 更全面分析"
- "全部 - 分析所有评论"
Q3: 飞书同步(必须)
- "仅生成本地文件"
- "同步到飞书文档(需要lark-cli已安装且已认证)"
Q4: 可视化模板(可选)
- "否 — 不需要生成可视化HTML" — 跳过HTML看板生成
- "使用默认模板 (premium-gold)" — 直接使用默认模板
- "我想选择模板" — 展示以下6种可用模板:
| 模板 | 风格 | 适用场景 | |------|------|---------| | premium-gold | 金色奢华风 | 品牌展示、高管汇报 | | posthog-analytics | 暖色分析风 | 数据分析、团队内部分享 | | stripe-executive | 翡翠企业风 | 金融企业、投资决策 | | linear-minimal | 极简蓝白风 | 产品评审、简洁汇报 | | dark-tech | 暗色科技风 | 技术评审、数据密集场景 | | warm-editorial | 暖纸编辑风 | 阅读分享、团队协作文档 |
Q5: 报告署名(⚠️ 仅当 Q4 选择了模板(非"否")时才触发此问题)
- "默认:AI Assistant"
- "我想自定义署名"
第二步:执行分析
# 本地CSV模式(最小参数)
python3 main.py "<CSV文件路径>" \
--max-reviews <数量> \
--feishu-sync <true|false>
# 本地CSV模式(完整参数,含自定义模板和署名)
python3 main.py "<CSV文件路径>" \
--max-reviews <数量> \
--template <模板名> \
--creator "<署名>" \
--feishu-sync <true|false>
# Sorftime模式
python3 main.py \
--source sorftime \
--asin <ASIN> \
--site US \
--max-reviews <数量> \
--feishu-sync <true|false>
第三步:展示结果
| 输出文件 | 内容 |
|---------|------|
| 评论采集及打标数据_{ASIN}.csv | 22维度标签数据 |
| 分析洞察报告_{ASIN}.md | 13章深度洞察报告 |
| 可视化洞察报告_{ASIN}.html | 可视化看板(可选,用户选择模板时生成) |
| 飞书文档(可选) | 完整报告 + 画板图表 |
参考资料
- CSV格式要求: references/csv_format.md
- 22维度标签: references/tag_system.md
- 故障排除: references/TROUBLESHOOTING.md
作者
Buluu@新西楼
- GitHub: @buluslan
- 主项目: review-analyzer
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/review-analyzer-skill-v2-0-ms47vog4/download' --output '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md.part' && mv '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md.part' '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md' && test -s '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/review-analyzer-skill' && cp -R '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4' '.claude/skills/review-analyzer-skill'Cursor
test -f '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md' && test -s '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/review-analyzer-skill' && cp -R '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4' '.cursor/skills/review-analyzer-skill'Codex
test -f '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md' && test -s '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/review-analyzer-skill' && cp -R '.skill-downloads/review-analyzer-skill-v2-0-ms47vog4' '.agents/skills/review-analyzer-skill'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/review-analyzer-skill-v2-0-ms47vog4'openskills read 'review-analyzer-skill-v2-0-ms47vog4'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/review-analyzer-skill-v2-0-ms47vog4/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Create Interactive Maps with kepler.gl
Data & AI
Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.
Agent-Driven Parameter Optimization
Data & AI
Guide for optimizing configurable systems with a measurable objective, using bounded trials and evidence-based recommendations.
ICP Visitor Outreach
Data & AI
Identify signed-up users matching the ideal customer profile but stalled, and draft personalized outreach to re-engage them.