Review Analyzer Skill

What it does

When your agent uses it

• Tasks that involve E-commerce operations
• Tasks that involve Messaging and chat bots
• Tasks that involve CSV and tabular files

Example prompts

• “/review-analyzer-skill”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): bash

What it can do on your machine

Read from SKILL.md and the folder at commit 0e8f684. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Analyzer Skill loads about 1.1k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 169 tokens; SKILL.md has 185 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~169

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from buluslan/review-analyzer-skill at commit 0e8f684, republished under its MIT licence (© buluslan). 185 words, ~1,122 tokens.

name

review-analyzer-skill

description

review-analyzer-skill是由buluslan（公众号：新西楼.AI）研发的电商评论深度分析Skill（VOC 客户之声分析），他会帮你把一堆产品评论变成一份能落地的决策依据——22 维 AI 打标提炼用户画像、痛点和真实需求，输出 15 章深度洞察报告和可视化看板，从差评里挖出产品优化机会点、从好评里找到爆款基因。 更多跨境电商 AI 实战内容，请关注公众号「新西楼.AI」。 Deep-dive e-commerce review & VOC analysis: 22-dimension AI tagging, 15-chapter insight report with anomaly signal cards, 6 themed visualization dashboards, CSV-primary multi-source input (SellerSprite optional), Feishu sync. 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 / 创建可视化分析看板 / 通过卖家精灵获取评论数据（可选增强；CSV为主源）/ 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、卖家精灵、sellersprite。 NOT for 关键词调研/选品雷达类任务（那些有专门工具）。

allowed-tools

bash

author

Buluu@新西楼.AI

license

MIT

metadata.category

ecommerce

metadata.version

2.2.1

pip install pandas jinja2 requests python-dotenv tqdm

# 方式1: 本地CSV文件（主源，推荐——覆盖全、正文完整）
python3 main.py "reviews.csv" --llm agent --max-reviews 100 --creator "AI Assistant"

# 方式2: 从卖家精灵获取（可选增强，输入ASIN快速预览；agent 模式同样支持，prepare 会先拉数）
python3 main.py --source sellersprite --asin B001OAXE0S --site US --llm agent --max-reviews 100 --creator "AI Assistant"

# 1) 准备（Python：加载数据、分批、写 prompt；卖家精灵源会先拉数）
python3 main.py "<CSV路径>" --llm agent --max-reviews <N> --template <T> --creator "<署名>" [--feishu-sync]
# 卖家精灵源: python3 main.py --source sellersprite --asin <ASIN> --site US --llm agent --max-reviews <N> --creator "<署名>"
# 输出 workdir（{输出目录}/agent_work_{ASIN}/）与待办批次清单后退出

# 2) 宿主 Agent 自己打标：逐个读 {workdir}/tagging/batch_XXX_prompt.md，
#    严格按 prompt 指令打标，把 JSON 数组结果写到同名 batch_XXX.json

# 3) 推进：python3 main.py --resume <workdir>
#    → 生成 report_prompt.md 后退出；宿主 Agent 读取它，
#      严格按照 prompt 指令撰写完整 15 章报告，把全文 Markdown 写到 {workdir}/report_draft.md

# 4) 收尾：python3 main.py --resume <workdir>
#    → 输出 MD/CSV/HTML看板/飞书

© buluslan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 91 other files (references, assets) in the repository root of buluslan/review-analyzer-skill.

• SKILL.md
• .env.example
• .gitignore
• LICENSE
• README.en.md
• README.md
• assets/banner.jpg
• docs/PYTHON_UPGRADE.md
• examples/README.md
• examples/output_sample/README.md
• examples/output_sample/insights_report_sample.md
• examples/output_sample/reviews_labeled_sample.csv
• examples/output_sample/visual_report_sample.html
• examples/reviews_sample.csv
• main.py
• references/csv_format.md
• … and 76 more

Open the folder on GitHubat commit 0e8f684