agentleFS
aiagentwithdhruvaiagentwithdhruv/skills/title-variants/SKILL.md

title-variants

Skill16 starsChanged 9 months agoMITView on GitHub

Generate title variants for YouTube videos from outlier analysis. Use when user asks to create title variations, generate YouTube titles, or adapt video titles.

  • Reads credentials

3 other projects use a version of this, 3 of them edited.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Title Variant Generation

Goal

Analyze top-performing video titles and generate variants adapted to your niche.

Scripts

  • ./scripts/generate_title_variants.py - Generate variants
  • ./scripts/update_sheet.py - Update sheets

Usage

# Mode A: Update existing sheet with variants
python3 ./scripts/generate_title_variants.py \
  --sheet-url "SHEET_URL" \
  --mode update

# Mode B: Create new sheet with variants
python3 ./scripts/generate_title_variants.py \
  --input .tmp/outliers.json \
  --mode create

How It Works

  1. Analyzes original title's hook, emotional trigger, structure
  2. Adapts to your specific niche (AI agents, automation, etc.)
  3. Generates 3 meaningfully different variants
  4. Keeps under 100 characters (YouTube best practice)

Configuration

USER_CHANNEL_NICHE = "AI agents, automation, LangGraph, CrewAI, agentic workflows"

Output

Three title variants per input, stored in sheet columns:

  • Title Variant 1
  • Title Variant 2
  • Title Variant 3

Schema

Inputs

NameTypeRequiredDescription
sheet_urlstringNoGoogle Sheet with outlier titles to generate variants for
input_filefile_pathNoJSON file with outlier data
modestringYes'update' (existing sheet) or 'create' (new sheet)

Outputs

NameTypeDescription
sheet_urlstringSheet with Title Variant 1/2/3 columns added

Credentials

NameSource
ANTHROPIC_API_KEY.env

Composable With

Skills that chain well with this one: cross-niche-outliers, youtube-outliers

Cost

Claude API (minimal)

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.