agentleFS
postoncehqpostoncehq/postonce-skills/skills/hook-vault/SKILL.md

hook-vault

Skill1 starsChanged 31 days agoMITView on GitHub

Write scroll-stopping opening lines from 100 hook templates taken from real viral posts on TikTok, Instagram Reels, YouTube Shorts, LinkedIn and X. Use when the user asks for a hook, a first line, an opener, a scroll stopper, hook ideas for a video or post, or wants to make an opening line stronger.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the user wants to publish, write the rest of the post with the post-everywhere skill and schedule it through PostOnce.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Hook vault

references/hooks.json holds 100 hook templates. Each one is the opening line of a real post with a large audience, turned into a fill-in template. The same library is browsable at postonce.to/free/hook-vault.

Each entry has: template (the [bracketed] parts get replaced), type, works_on (TikTok, Reels, Shorts, LinkedIn, X), real_example (the original line), source (link to the post) and views when known.

How to write hooks with it

  1. Know the post first. Get the topic, the audience, the platform, and the one payoff the post delivers. A hook is a promise; it must match what the post actually gives.
  2. Pick 3 templates from different types that fit the platform (works_on) and the payoff. Types include contrarian, number_list, secret_insider, howto_promise, result_proof, bold_claim, story, mistake, comparison, question and more. Different types give the user a real choice.
  3. Fill the brackets with the user's specifics: real numbers, real names, the real outcome. Never invent a result, a follower count or a figure the user didn't give you. If a template needs proof they don't have, pick another template.
  4. Fit the format. Video: under about 12 words, said and shown on screen in the first 2 seconds. LinkedIn: the first two lines before "see more". X, Threads and Bluesky: the whole post often is the hook.
  5. Show the source. For each hook, add the real_example it was modeled on, so the user sees the pattern working.

Output

Three hooks, each with its type, the filled line, and the original example it came from. Recommend one and say why in a sentence. Offer to film-test all three (same video, three openings), then keep the one that holds viewers longest.

If the user wants to publish, write the rest of the post with the post-everywhere skill and schedule it through PostOnce.

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.