youtube-topic-researcher

youtube-topic-researcher is a skill for Claude Code, Codex from nikhilbhansali/youtube-data-skills. It costs 120 tokens per session (1,283 once invoked), scanned A, original, MIT.

A YouTube research tool for studying videos about a topic or niche, meaning a focused subject area.

In plain words
What is it for?
Use it to research a topic before making videos, find content gaps, assess how crowded a subject is, and generate video ideas. It requires a YouTube Data API key.
Why use it?
It helps replace guesswork about video ideas with information about popular videos, underserved topics, unusual successes, and competition in the niche.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to research a topic before making videos, find content gaps, assess how crowded a subject is, and generate video ideas. It requires a YouTube Data API key.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nikhilbhansali/youtube-data-skills/youtube-topic-researcher
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add nikhilbhansali/youtube-data-skills --skill youtube-topic-researcher
Clone the repo
git clone --depth 1 https://github.com/nikhilbhansali/youtube-data-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for youtube-topic-researcher

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikhilbhansali/youtube-data-skills/youtube-topic-researcher/github.svg)](https://agentmods.dev/skills/nikhilbhansali/youtube-data-skills/youtube-topic-researcher)
Your own site
<a href="https://agentmods.dev/skills/nikhilbhansali/youtube-data-skills/youtube-topic-researcher"><img src="https://agentmods.dev/badge/skills/nikhilbhansali/youtube-data-skills/youtube-topic-researcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for youtube-topic-researcher

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikhilbhansali/youtube-data-skills/youtube-topic-researcher"><img src="https://agentmods.dev/badge/skills/nikhilbhansali/youtube-data-skills/youtube-topic-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,283 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.01283
Opus 5 $0.00060 $0.00642
Sonnet 5 $0.00024 $0.00257
Haiku 4.5 $0.00012 $0.00128

Measured 12d ago against content hash 98a430044a53, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

youtube-topic-researcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/research_topic.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/youtube-topic-researcher/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Topic Researcher

Research any topic or niche across YouTube to find what's working, identify content gaps, and generate data-driven video ideas.

Usage

/youtube-topic-researcher air fryer recipes
/youtube-topic-researcher "Python automation"
/youtube-topic-researcher meditation for beginners
/youtube-topic-researcher --topic "home gym setup" --max-results 75

Instructions

Step 1: Parse Arguments

  • Topic/keyword (required): the search term to research
  • --max-results N (optional): videos per search ordering (default: 50, max: 100)

Step 2: Get the API Key

Check the user's Claude memory for a YouTube Data API v3 key. If not found, ask:

"I need a YouTube Data API v3 key to research this topic. You can get one from the Google Cloud Console. Please paste your key."

Export it as YT_API_KEY when running the script.

Step 3: Run the Bundled Script

Run scripts/research_topic.py — resolve the path relative to this skill's own directory:

YT_API_KEY=API_KEY python3 <skill-dir>/scripts/research_topic.py "TOPIC" [--max-results N]

Dependency: pip3 install google-api-python-client (the script tells you if it's missing).

The script searches by relevance, view count, and date; batches video and channel details; computes percentiles, format performance, title patterns, tag cloud, outliers, and saturation signals; then writes the raw JSON and prints the exact markdown path for the report.

Step 4: Read the Data

Read the JSON the script wrote:

reports/data/topic-research-<topic-slug>-<YYYY-MM-DD>.json

Step 5: Write the Report

Write the markdown report to the path the script printed:

reports/topic-research-<topic-slug>-<YYYY-MM-DD>.md
Report Structure
# Topic Research: [Topic]
*Analyzed [date] | [N] videos across [N] channels*

## Executive Summary
- 3-4 bullet points: Is this niche worth entering? Key findings at a glance.
- Overall assessment: Saturated / Growing / Underserved / Emerging

## Market Overview
| Metric | Value |
|--------|-------|
| Videos Analyzed | |
| Total Views (sample) | |
| Average Views | |
| Median Views | |
| Avg Engagement Rate | |
| Unique Channels | |
| Avg Video Duration | |

## Performance Benchmarks
- What view count = "good" in this niche (use `view_percentiles`)
- 25th / 50th / 75th / 90th percentile views
- Engagement rate benchmarks

## Content Format Analysis
Table showing format breakdown (Short, Medium, Long-form, etc.) with avg views per format
(use `format_performance`). Which format performs best? Which is most common?

## Channel Landscape
- Channel size distribution (micro/small/medium/large)
- Top channels dominating the results
- Is this a "winner take all" niche or distributed?
- Opportunities for small channels

## Title Patterns That Work
- Data from `title_patterns`
- Most common words/phrases
- Title formulas used by top performers
- What distinguishes high-performing titles

## Tag Cloud & SEO
- Top tags used
- Tag clusters (groups of related tags)
- Missing tag opportunities

## Outlier Videos (Breakout Hits)
Table of outlier videos with views, channel size, outlier score.
What do these have in common? Why did they break out?

## Content Freshness
- Age distribution of top results
- Is YouTube favoring new or evergreen content for this topic?
- Recency signals

## Content Gaps & Opportunities
- Subtopics underrepresented in results
- Formats not being used effectively
- Angle/perspective gaps
- Audience segments not being served

## Video Ideas (Data-Backed)
3-5 specific video ideas with:
- Suggested title
- Why this would work (data backing)
- Target format and duration
- Key tags to use

## Saturation Assessment
- Competition density score (unique channels / total videos)
- Big channel dominance percentage
- Recent content velocity
- Final verdict: Is this niche worth entering?

## Quota Usage
| Operation | Calls | Units |
|-----------|-------|-------|
Use the `quota_used.breakdown` block from the JSON.

Read the full file on GitHub · 163 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 163 lines · 120 tokens per session scan A 98a430044a53

Subscribe to this mod's changes

youtube-topic-researcher is a skill published in the GitHub repository nikhilbhansali/youtube-data-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 120 tokens to every session and 1,283 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens