← Back to Skills Marketplace
Review Miner
by
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
144
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install review-miner
Description
从评论、评价和反馈中提炼卖点、痛点、反对意见与应删除的话术。；use for reviews, voice-of-customer, marketing workflows；do not use for 造假好评, 泄露用户身份.
Usage Guidance
This skill appears to be what it claims: a local review-mining/audit tool implemented in Python that uses bundled templates and a spec. Before running: (1) Only pass intended inputs (comments CSV, text files) — do not point the tool at system or secret-bearing directories. (2) If your input contains PII or sensitive customer data, desensitize it first (SKILL.md also recommends this). (3) Inspect scripts/run.py yourself if you will run it in an environment with sensitive files; the script reads files recursively when given a directory and can include many file types. (4) The skill does not call external networks or request credentials, but treat outputs that surface potential secrets as sensitive. (5) For production use, run the script in a controlled workspace and review results before any automated publishing or system changes.
Capability Assessment
Purpose & Capability
Name/description (提炼卖点/痛点/反对意见) align with provided files: a resources spec, template, examples, and a Python script that performs CSV/text/directory audits and emits structured markdown. Requiring only python3 is proportionate.
Instruction Scope
SKILL.md instructs running the local Python script or falling back to bundled templates; it warns about privacy and not to fake reviews. The included script supports file, CSV, directory, pattern, and skill-audit modes and will read many text file types recursively when given a directory. That behavior is useful for directory-audit use cases but expands scope beyond strictly 'comments CSV' inputs — users should avoid pointing it at broad system directories or sensitive locations.
Install Mechanism
No install spec; this is instruction+script only and relies on the system python3. Nothing is downloaded or extracted from external URLs and no package registries are referenced.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The script does not attempt to read environment secrets or require external API keys.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent presence or modify other skills. The tool is local and only runs when invoked.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install review-miner - After installation, invoke the skill by name or use
/review-miner - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of review-miner skill.
- Extracts key selling points, pain points, objections, and phrases to avoid from reviews, feedback, and ratings.
- Provides structured output for marketing and Voice-of-Customer analysis.
- Includes safeguards against generating fake reviews or exposing user identities.
- Compatible with Darwin, Linux, and Windows (requires python3).
- Offers both a review-draft and actionable checklist; highlights info gaps and compliance concerns.
- Utilizes local templates and spec files for output formatting if environment restricts execution.
Metadata
Frequently Asked Questions
What is Review Miner?
从评论、评价和反馈中提炼卖点、痛点、反对意见与应删除的话术。；use for reviews, voice-of-customer, marketing workflows；do not use for 造假好评, 泄露用户身份. It is an AI Agent Skill for Claude Code / OpenClaw, with 144 downloads so far.
How do I install Review Miner?
Run "/install review-miner" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Review Miner free?
Yes, Review Miner is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Review Miner support?
Review Miner is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Review Miner?
It is built and maintained by vx：17605205782 (@52yuanchangxing); the current version is v1.0.0.
More Skills