agentleFS
moses607moses607/socialforge/skills/youtube-title-lab/SKILL.md

youtube-title-lab

Skill3 starsChanged 4 months agoMITView on GitHub

On YouTube nothing else runs until the title/thumbnail combo wins the click — not the intro, not the retention edit, not the algorithm. The title and thumbnail are not two labels for the same idea; they are two halves of ONE curiosity gap. The thumbnail carries emotion and visual stakes (a face, a result, a contrast); the title carries the specifics and the promise. When they repeat each other you waste half your real estate; when they complete each other…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never brainstorm one angle.

    line 10
  2. Distinctive:

    If the title and thumbnail text say the same noun, kill one and reload.

    line 23
  3. Distinctive:

    Every pair opens exactly ONE curiosity gap.

    line 53
  4. Distinctive:

    If the promise isn't literally true and paid off in the first 30 seconds, rewrite it — a click you can't keep costs you the next ten.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

name: youtube-title-lab description: Generates and stress-tests YouTube title + thumbnail-text PAIRS engineered for click-through, treating the combo as one hook instead of two separate assets. It runs 10-15 titles across five angles, pairs finalists with a ≤3-word thumbnail concept, and applies curiosity-vs-spoiler and clickbait-vs-honest checks so retention and trust survive the click. Use when packaging a video, writing YouTube titles or thumbnails, or improving CTR. Trigger on "title ideas", "thumbnail text", "improve my CTR", or "package this video". Works with any capable model.

YouTube Title Lab

On YouTube nothing else runs until the title/thumbnail combo wins the click — not the intro, not the retention edit, not the algorithm. The title and thumbnail are not two labels for the same idea; they are two halves of ONE curiosity gap. The thumbnail carries emotion and visual stakes (a face, a result, a contrast); the title carries the specifics and the promise. When they repeat each other you waste half your real estate; when they complete each other the viewer needs to click to close the loop. Every choice below optimizes the gap, then guarantees the video actually pays it off.

1. Generate 10-15 titles across 5 angles

Never brainstorm one angle. Force at least two titles per angle so you compare hooks, not phrasings: 1. Curiosity — open a loop, withhold the payoff: "I Tried X for 30 Days. Nobody Warned Me." 2. Result/proof — lead with the concrete outcome + number: "How I Got 10k Subs With 4 Videos." 3. Contrarian — attack the consensus: "Stop Warming Up Before You Lift." 4. How-to/utility — clean promise, front-loaded keyword: "Fix Slow WiFi in 60 Seconds." 5. Story/stakes — personal, high-consequence: "This Mistake Cost Me $12,000." Constraints on every option: ≤60 characters (mobile truncates ~40-50), front-load the hook word in the first 1-3 words, one specific number or proper noun where possible, no title-case keyword stuffing.

2. Pair each finalist with a thumbnail-text concept (≤3 words)

Take your top 3-4 titles. For each, write the thumbnail text that completes — never echoes — it. Rule of division of labor: - Title says the specific promise → thumbnail says the emotional stakes ("$12,000" title → thumbnail: "MY BIGGEST MISTAKE"). - Title asks the question → thumbnail shows the shocking answer-teaser, not the answer. - Thumbnail carries ONE readable idea at arm's length on a phone: ≤3 words, high contrast, one focal face or object. If the title and thumbnail text say the same noun, kill one and reload. State, for each pair, the single curiosity gap it opens in the viewer's head.

3. Run the two guardrails

- Curiosity vs. spoiler: Does the pair reveal the payoff? If the viewer already has the answer, there's no click. Move the reveal from the packaging into the first 30 seconds. - Clickbait vs. honest: Is the promise literally true and delivered early in the video? If not, CTR spikes then retention and trust collapse — the algorithm punishes the session. Every gap must be a withheld truth, never a false one.

Output template

VIDEO: <one-line topic>

RANKED PAIRS
1. Title: "<≤60 chars>"  (angle: <curiosity/result/contrarian/how-to/story>, <N> chars)
   Thumbnail text: "<≤3 words>"
   Gap it opens: <the exact question left in the viewer's mind>
   Honest? <yes — where the video pays it off>

2. ...
3. ...

RUNNER-UP TITLES (unpaired): <2-3 lines>
PICK: #<n> — <one-line why it wins the click>

Platform variants

- Shorts: thumbnail is irrelevant; first 2 words + first frame ARE the hook. Skip pairing, punch the opening line. - Search-driven (how-to/review): keyword must lead the title; trade some curiosity for exact-match clarity. - Browse/suggested-driven: maximize the gap; emotion and stakes outrank keywords.

Rules

- Title and thumbnail must never state the same noun — they divide the hook, they don't repeat it. - Every pair opens exactly ONE curiosity gap; two gaps is noise, zero is a spoiler. - Front-load the hook in the first 1-3 words; assume the last third is truncated on mobile. - One specific number or proper noun beats five vague adjectives — cut "amazing", "ultimate", "insane". - Thumbnail text is ≤3 words, readable at thumbnail size, or it doesn't exist. - If the promise isn't literally true and paid off in the first 30 seconds, rewrite it — a click you can't keep costs you the next ten.

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.