Youtube Research
This one hooks into TubeLab's outlier detection API to find YouTube videos that are massively outperforming their channel averages, then runs AI analysis on the top three to extract replicable hook formulas and content structures. You give it direct niche keywords plus adjacent topics the same audience watches, and it pulls videos, transcripts, thumbnails, and generates a report ranked by zScore times recency. The hook formula extraction is the real value here since it's trying to give you actual templates you can adapt, not just vague observations about what worked. Needs both TubeLab and Gemini API keys. Best for content creators doing competitive research or trying to reverse engineer what's working in their space right now.
- skills.sh installs
- 394
- GitHub stars
- 309
- last updated
- Aug 21, 2026
Install
$ npx -y skills add bradautomates/head-of-content --skill youtube-research --agent claude-codeInstalls into .claude/skills of the current project.
Files
YouTube Research
Research high-performing YouTube outlier videos, analyze top content with AI, and generate actionable reports.
Prerequisites
TUBELAB_API_KEYenvironment variable. Get key from https://tubelab.net/settings/apiGEMINI_API_KEYenvironment variable (for video analysis)google-genaiandrequestsPython packages
Workflow
Step 1: Create Run Folder
mkdir -p youtube-research/$(date +%Y-%m-%d_%H%M%S)
Step 2: Get Channel ID
Read .claude/context/youtube-channel.md to get the channel ID.
Step 3: Fetch Channel Videos
python scripts/get_channel_videos.py CHANNEL_ID --format summary
This returns JSON with the channel's video titles and view counts.
Step 4: Analyze Channel
Analyze the channel data to extract:
- keywords: 4 search terms for the channel's direct niche
- adjacent-keywords: 4 search terms for topics the same audience watches
- audience: 2-3 profiles with objections, transformations, stakes
- formulas: Reusable title templates
See references/channel-analysis-schema.md for the full schema and example output.
Step 5: Search for Outliers
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/bradautomates/head-of-content
- Categories
- Frontend Development, Backend & APIs, Data Science & ML
- First seen
- Jun 3, 2026
More from bradautomates/head-of-content
All 4Recommended
More Frontend Development
design-system-starterdavila7/claude-code-templatesCreate and evolve design systems with design tokens, component architecture, accessibility guidelines, and documentation templates. Ensures consistent, scalable393skills.sh installs
systematic-debuggingbobmatnyc/claude-mpm-skillsStep-by-step debugging workflow: reproduce the bug, isolate the failing component, trace to root cause, apply a targeted fix, and verify the fix resolves the is391skills.sh installs
tooluniverse-gene-enrichmentmims-harvard/tooluniverseGene-set enrichment analysis — GO (Biological Process, Molecular Function, Cellular Component), KEGG, Reactome pathway enrichment via clusterProfiler, gseapy, O390skills.sh installs
mcp-server-skillsgocallum/nextjs16-agent-skillsPattern for building MCP servers in Next.js with mcp-handler, shared Zod schemas, and reusable server actions.387skills.sh installs
ln-742-precommit-setuplevnikolaevich/claude-code-skillsConfigures Husky, lint-staged, commitlint, and Python pre-commit hooks. Use when adding Git hook automation to a project.385skills.sh installstheme-factorydavila7/claude-code-templatesToolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fo384skills.sh installs