Skip to main content
skill CX Codex

comment-mining · tubelabhq — Claude Code skill: what it does, how to install

The comment-mining Claude Code skill mines YouTube comments for audience questions, objections, and requests in their own words. It requires the TubeLab MCP.

MIT ★ 288 updated 2026-11-15

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add TubeLabHQ/youtube-research-skills
/plugin install youtube-research@tubelab
Open on GitHub

What comment-mining does

The skill collects YouTube comments and sorts them into questions, objections, and requests from the audience. Likes determine priority, while original wording stays separate from the skill's interpretation.

Its default scope is 10 to 15 videos: supplied videos, a channel's latest uploads, or standout results for a topic. Comments are fetched one video at a time because parallel fetches overwrite each other. Spam, duplicates, and creator replies are removed before grouping. The report includes themes, quoted comments, video links, and follow-up video ideas. TubeLab MCP must be available.

What it helps with

  • map audience questions across YouTube comments
  • rank objections and requests by comment likes
  • remove spam and creator replies from audience research
  • turn recurring comment themes into video ideas

Example prompts for the agent

  • Mine the comments on these videos and group the audience's questions, objections, and requests: [links].
  • Review the channel's latest videos and show the most liked audience requests in their original wording.
  • Find recurring themes in the comments for this topic, then suggest follow-up video ideas linked to those themes.

How to install comment-mining

1Plugin marketplace

/plugin marketplace add TubeLabHQ/youtube-research-skills
/plugin install youtube-research@tubelab

This installs the whole youtube-research plugin with all its skills

2Skills CLI (Vercel)

npx skills add TubeLabHQ/youtube-research-skills --skill comment-mining -a claude-code

3Manually: put the files in place

~/.claude/skills/comment-mining/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/comment-mining/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about comment-mining

How do I install comment-mining in Claude Code?

Add the marketplace with /plugin marketplace add TubeLabHQ/youtube-research-skills, then install the plugin with /plugin install youtube-research@tubelab.

What does comment-mining do?

It gathers YouTube comments, removes spam, duplicates, and creator replies, then groups the remaining audience input into questions, objections, and requests weighted by likes.

What does comment-mining need to work?

The skill requires the TubeLab MCP. Video searches use publishedAtFrom and classificationQuality set to neutral or higher.

Source text

SKILL.md · MIT
---
name: comment-mining
description: Use when the user wants to know what a YouTube audience asks, wants or complains about in the comments, in their own words. Requires the TubeLab MCP.
license: MIT
metadata:
  author: tubelab
  version: "5.0"
  requires: tubelab-mcp
---

# Comment Mining

## Overview

What the audience asks, objects to and wants next, in their own words. Likes are votes: a question with 900 likes is 900 people asking. Quotes stay word for word, and your reading of them goes on its own line.

## Workflow

1. Clarify scope only if needed. Default to 10 to 15 videos: the ones given, or else the channel's latest (its best if asked), or else a topic's top outliers. Finding videos by topic costs one search.
2. Fetch comments one video at a time, because parallel fetches overwrite each other. Remove spam, repeated rows and the creator's own replies.
3. Group the rest into questions, objections and requests, weighted by likes.

## Output Format

```markdown
# 🗣️ Voice of Audience: {channel, topic or videos}

- **Biggest ask:** {one sentence, with likes and number of videos}
- **Sample:** {n} videos, {n} comments

## 🧵 Themes
1. **{Theme}**
   - {n} videos · {total likes} likes
   - "{best quote}" · [{video}]({video url})
   - **What it means:** {one sentence}

| Comment (verbatim) | Type | Likes | Video (link) |
|---|---|---:|---|

## 💬 Their Words
- "{phrase}" · {n} times

## 💡 Video Ideas
1. **{Title}** · {the theme it answers}
```

- Length: about 700 words. Five themes, eight comments, three ideas.
- Language: plain words and short, complete sentences. Nothing compressed.
- Bullets: one fact each, under 25 words, except quotes and verbatim titles. No extra sections or bullets.
- If it runs long, cut whole items. Never cut quotes, and never squeeze sentences.
- Links: link every video, channel, moment, brand and offer you cite, built from IDs, handles and links in the data. Never guess one.

## Common Pitfalls

- Do not search without `publishedAtFrom` and `classificationQuality` at `"neutral"` or above, or the results fill with low-effort videos.
- Do not present a paraphrase as a quote.
- Do not call something a theme unless it appears under 3 or more videos. Under one video, it is a reaction to that video.
- Do not rank spam. Book promos and bots often collect many likes.
- Do not read a quiet comment section as a happy one. Top comments skew positive.
- Do not treat disabled comments as a finding. Say "no data".

© tubelab · MIT · TubeLabHQ/youtube-research-skills

Similar skills

All skills for Marketing and content →

comment-mining by other authors comes first.

comment-mining ScrapeCreators comment-mining mines public social media comments to uncover audience questions, objections, content ideas, and buying intent. CX Codex +1 2,000installs extracting-youtube-comments-for-research apidojo extracting-youtube-comments-for-research is a Claude Code skill that pulls YouTube comments and analyzes sentiment, questions, and viewer pain to show what an audience writes under a video. CX Codex +1 942installs scraping-youtube-comments apidojo scraping-youtube-comments pulls comments, likes, and reply counts from YouTube videos using Apify. Useful for audience feedback and sentiment analysis. CX Codex +1 925installs ig-comment Jakeschincariol ig-comment is a Claude Code skill that writes comments on other people's Instagram posts and reels. It produces human responses with a specific point of view instead of bot chatter. CX Codex +1 1,700installs reply-and-comment-writer social-media-skills reply-and-comment-writer — a Claude Code skill that drafts replies to comments, DMs, and comments on other people's posts. It loads brand-profile.md and voice.md first, so every draft matches the brand voice. CX Codex +1 1,300installs comment-strategy vivy-yi comment-strategy is a skill for planning Xiaohongshu replies, answering questions, addressing objections, sustaining discussion, and guiding interested commenters toward a purchase. CX Codex +1 172installs li-comment Jake Schincariol li-comment generates human-sounding comments for LinkedIn posts from specific angles instead of generic praise, with no auto-posting. CX Codex +1 ★ 3,812repo stars

From the same set23

The whole set →
validator validator — a Claude Code subagent that scores YouTube niches by market size, saturation, and profit potential. It can assess one niche or a shortlist of up to three and return a go-or-no-go verdict. CX Codex ★ 288repo stars monetization-team The monetization-team Claude Code subagent finds what similar YouTube channels sell and which brands sponsor them. It also helps brands identify channels to sponsor. CX Codex ★ 288repo stars packaging-team The packaging-team Claude Code subagent creates YouTube title ideas and thumbnail concepts from examples that are already getting clicks. Request titles, thumbnails, or both for one video. CX Codex ★ 288repo stars niche-scout The niche-scout Claude Code subagent finds breakout YouTube channels and ranks ten niche ideas. It handles niche discovery, faceless channel concepts, and requests to track emerging channels. CX Codex ★ 288repo stars channel-analysis The channel-analysis Claude Code skill examines a YouTube channel’s positioning, strong points, and possible obstacles. It compares recent uploads with the channel’s median views and outlines experiments to try next. CX Codex +1 ★ 288repo stars competitor-research competitor-research — a Claude Code skill that finds YouTube channels competing for the same viewers and compares them with a target channel. It surfaces topics where rivals get stronger results. CX Codex +1 ★ 288repo stars script-breakdown The script-breakdown Claude Code skill maps the structure of YouTube videos and helps outline scripts. It responds to requests to inspect a hook, a beat sheet, or videos from a channel or niche. CX Codex +1 ★ 288repo stars title-formulas This Claude Code skill develops YouTube title formulas from a topic or draft. It runs for title ideas, formula research, or a rewrite. CX Codex +1 ★ 288repo stars

Project sponsors

Companies that keep this analytics open