video-title-optimizer

video-title-optimizer is a skill for Claude Code, Codex from nicepkg/ai-workflow. It costs 52 tokens per session (1,934 once invoked), scanned A, original, MIT.

A workflow for creating and testing alternative titles for YouTube and TikTok videos. It balances clear keywords with curiosity and platform-specific length guidance.

In plain words
What is it for?
Naming videos, improving existing titles, and preparing title variations for comparison.
Why use it?
It helps replace vague or awkward titles with options that explain the topic while giving viewers a reason to click.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/nicepkg/ai-workflow/video-title-optimizer
Any agent
npx skills add nicepkg/ai-workflow --skill video-title-optimizer
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

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 video-title-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicepkg/ai-workflow/video-title-optimizer.svg)](https://agentmods.dev/skills/nicepkg/ai-workflow/video-title-optimizer)
Your own site
<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/video-title-optimizer"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/video-title-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,934 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00052 $0.01934
Opus 5 $0.00026 $0.00967
Sonnet 5 $0.00010 $0.00387
Haiku 4.5 $0.00005 $0.00193

Measured yesterday against content hash 5540efc31a2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

video-title-optimizer 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 yesterday.

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.

workflows/video-creator-workflow/.claude/skills/video-title-optimizer/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Title Optimizer

Create click-worthy titles that rank well and drive views.

Title Anatomy

[POWER WORD] + [TOPIC] + [BENEFIT/CURIOSITY] + [SPECIFICITY]

Example: "INSANE Productivity System That DOUBLED My Output (After Failing 10 Times)"
         [Power]  [Topic]              [Benefit]         [Specificity/Story]

Platform-Specific Guidelines

YouTube (Long-form)

Character Limit: 100 chars (60-70 visible in search)
Optimal Length: 50-60 characters
Keywords: Front-load important keywords
Format: Mix of curiosity + clarity

✅ Good: "I Tried [Thing] for 30 Days - Here's What Happened"
✅ Good: "How I [Achieved Result] (Step-by-Step Guide)"
❌ Bad: "My Video About [Topic] | Part 1 | 2025 | HD"

YouTube Shorts

Character Limit: 100 chars
Optimal: 30-50 characters (shorter is better)
Style: Punchy, immediate hook

✅ Good: "This Trick Changes EVERYTHING"
✅ Good: "Wait for it... 😱"
❌ Bad: "Part 47 of my series on productivity tips"

TikTok

Caption Limit: 4000 chars (but shorter performs better)
Title Portion: First 50-80 chars most important
Hashtags: Include 3-5 relevant hashtags

✅ Good: "The $5 gadget that replaced my $500 setup 😳 #tech #gadgets #fyp"
❌ Bad: "#fyp #foryou #viral #trending #tech #gadget #cool #awesome"

Title Formulas (Proven CTR)

1. Number + Adjective + Keyword + Promise

"7 INSANE Productivity Hacks That Actually Work"
"5 BRUTAL Truths About [Topic] Nobody Tells You"
"12 GENIUS Ways to [Achieve Outcome]"

2. How I + Result + Timeframe

"How I Made $10K in 30 Days as a Beginner"
"How I Lost 20 Pounds Without Dieting"
"How I Learned [Skill] in Just 3 Months"

3. Why + Surprising Claim

"Why [Common Advice] Is Actually Wrong"
"Why I Stopped [Popular Thing] (And You Should Too)"
"Why [Expert/Celebrity] Is Completely Wrong About [Topic]"

4. I Tried X for Y - Result

"I Tried [Thing] for 30 Days - Life Changing Results"
"I Ate [Diet] for a Week - What Happened Shocked Me"
"I Used [Product] for 6 Months - Honest Review"

Read the full file on GitHub · 267 lines

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. yesterday First seen · 267 lines · 52 tokens per session scan A 5540efc31a2b

Subscribe to this mod's changes

video-title-optimizer is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 52 tokens to every session and 1,934 once invoked, about $0.0003 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 2026-09-03.