comment-mining
Skill91 starsChanged 11 days agoMITView on GitHub
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.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- ScrapeAtlas/social-media-agent-skillstheir own version, first seen Nov 15, 2026
- athina-ai/goose-skillstheir own version, first seen Nov 9, 2026
- gooseworks-ai/goose-skillstheir own version, first seen Nov 1, 2026
- fliqrlabs/instagram-creator-skillstheir own version, first seen Nov 1, 2026
- Ootto-AI/claude-content-skillstheir own version, first seen Aug 23, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- gooseworks-ai/goose-skills★ 1.3ksame name
- athina-ai/goose-skills★ 1.3ksame name
- Ootto-AI/claude-content-skills★ 417same name
- ScrapeAtlas/social-media-agent-skills★ 11same name
- fliqrlabs/instagram-creator-skills★ 5same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-channel-riskSkill
- channel-analysisSkill
- competitor-researchSkill
- monetization-researchSkill
- niche-bendingSkill
- niche-finderSkill
- niche-validatorSkill
- niche-watchlistSkill
- reverse-engineer-channelSkill
- script-breakdownSkill
- sponsorship-prospectingSkill
- thumbnail-conceptsSkill
- title-formulasSkill
- trend-reportSkill
- tubelab-mcpSkill
- video-ideationSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 50
If it runs long, cut whole items.
- Very specific: line 55
Do not search without publishedAtFrom and classificationQuality at "neutral" or above, or the results fill with low-effort videos.
- Distinctive: line 56
Do not present a paraphrase as a quote.
- Distinctive: line 57
Do not call something a theme unless it appears under 3 or more videos.
- Distinctive: line 58
Do not rank spam. Book promos and bots often collect many likes.
- Distinctive: line 59
Do not read a quiet comment section as a happy one.
- Distinctive: line 60
Do not treat disabled comments as a finding.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
- 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.
- Fetch comments one video at a time, because parallel fetches overwrite each other. Remove spam, repeated rows and the creator's own replies.
- Group the rest into questions, objections and requests, weighted by likes.
Output Format
# 🗣️ 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
publishedAtFromandclassificationQualityat"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".
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

