Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    YouTube Comment Insights: Questions, Gaps and Next Video Ideas

    1

    Turn a video's comments into decisions: unanswered viewer questions, content gaps, sentiment, feedback themes, loyal commenters, evidence-backed video ideas and reply drafts for you to approve.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    YouTube Comment Insights: Questions, Gaps and Next Video Ideas

    YouTube Comment Insights: Questions, Gaps and Next Video Ideas

    Example session with this skill installed

    I exported the comments of my latest tutorial video to comments.json (the video is titled 'Build a REST API in Python'). Tell me what viewers think, which questions I should answer first, and what my next videos should be. Put it in REPORT.md.

    • Read your context and instructions
    • Compiled the youtube comment insights

    REPORT.md: 8 comments, mostly positive with one criticism about length and one audio complaint. Unanswered questions by likes: JWT authentication (57 likes), cloud deployment (33), environment variables in deployment (19). Content gaps: authentication and deployment (asked repeatedly, not in the title). Ideas: 'Add JWT authentication to your Python API' and 'Deploy your Python API to the cloud', each with quoted comments. Reply drafts for the top 3 questions, for approval. Loyal commenters: two viewers who commented twice.

    REPORT.md

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Comments are the cheapest audience research a channel has. Most tools stop at a sentiment pie chart; the useful outputs are unanswered questions (answer them, then make the next video about them), content gaps (what viewers ask that the video did not cover) and who your regulars are.

    What your agent does with it

    • Collects comments within quota with the YouTube Data API (pagination, replies, disabled comments, terms-of-service hygiene, monitoring new uploads).
    • Analyses deterministically (comment_insights.py, JSON or CSV in): totals and activity by day, top keywords, questions ranked unanswered-first by likes, feedback categories (praise, criticism, requests, confusion, technical issues), lexicon sentiment with negation handling, loyal commenters, and content gaps (frequent question terms missing from the title).
    • Classifies with an LLM in validated batches (sentiment score, intent, topic), with the lexicon as a fallback.
    • Generates content ideas backed by quoted comments and reply drafts for the top unanswered questions, for a human to approve (auto-replying gets channels flagged).
    • Produces a report: what viewers loved, what confused them, the questions to answer now, and 3–5 ideas with evidence.

    Included: SKILL.md, comment_insights.py (standard library), and an eval case with a sample comments file.

    Part of the Production AI Agents series. Pair with AI Short Video Production and LinkedIn Content Autopilot.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Social Media.

    The lexicon sentiment is English-only and a floor; use an LLM for other languages, sarcasm and slang. Replying to comments needs OAuth as the channel and should stay human-approved. Does not cover YouTube Analytics (watch time, retention).

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    Software
    Python 3.10+
    Optional
    YouTube Data API keyLLM for classification

    Permissions

    File Scopes

    Your
    project
    folder
    (reads
    exported
    comments
    writes
    reports)

    comment_insights.py analyses an exported file offline and makes no network calls.

    Listed1 day ago

    What's inside

    Frequently Asked Questions

    Not for the analysis: export comments to JSON or CSV and run the script. Collecting comments automatically uses a YouTube Data API key.

    No. It drafts replies for you to approve; automated mass replies read as spam and can get a channel flagged.

    Questions, keywords, activity and loyal commenters work in any language that uses spaces; the built-in sentiment lexicon is English, so use the LLM step for other languages.

    New in Social Media