Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Video Ad Hook Checker — First 3 Seconds and CTA

    1

    **Video Ad Hook Checker** reads the script as text and measures exactly those points, the same way every time, before anyone records it.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Video Ad Hook Checker — First 3 Seconds and CTA

    Video Ad Hook Checker — First 3 Seconds and CTA

    Example session with this skill installed

    Check the ad script in examples/bakery_fail.json with the video-ad-hook-checker skill. The slot is 10 seconds. Tell me which checks fail and why.

    • Read your context and instructions
    • Compiled the video ad hook

    I ran python3 scripts/hook_checker.py examples/bakery_fail.json (exit code 1). The script fails.

    
    ### bakery-fail
    
    | Check | Result | Detail |
    |---|---|---|
    | hook-fit | FAIL | first line ~8.4 s of a 3.0 s window (21 words), too long to land in the window |
    | hook-terms | FAIL | no product word in the opening window (product: -; audience: -) |
    | claims | WARN | needs evidence: line 2 (best, guaranteed) |
    | cta | FAIL | 2 CTA lines (lines 3, 5), expected 1 |
    | subtitle | FAIL | over 40: line 1 is 109; line 2 is 51; line 4 is 109 |
    | duration | FAIL | ~25.6 s against a 10.0 s target, too long |
    | structure | FAIL | line 4 repeats line 1; speaker written in different ways: Voice, voice |
    | **Overall** | **FAIL** | |
    
    
    Estimated length: ~25.6 s (target 10.0 s)
    

    What this means

    • The first line is a greeting that takes about 8 seconds to say, so the product never appears in the opening window.
    • There are two calls to action (lines 3 and 5), and the first line comes back as line 4.
    • The script is more than twice the 10-second target.
    • Line 2 contains words marked as needing evidence (best, guaranteed). The tool lists them; it cannot say whether they are true.

    Next steps

    1. Rewrite the opening line so the product is named in the first seconds, then run the tool again.
    2. Keep one call to action near the end and remove the repeated line.
    3. Compare the original and the rewrite with --compare examples/bakery_revised.json to see which checks improved.

    Timings are estimates from reading speeds, not audio measurements.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The first seconds of a short video ad are where scripts most often go wrong, and the faults are plain ones: an opening line that takes eight seconds to say, an opening that never names the product, two calls to action, a subtitle line too wide for the screen, a script ten seconds over its slot. Video Ad Hook Checker reads the script as text and measures exactly those points, the same way every time, before anyone records it.

    Give it a script as a plain text file, JSON or a CSV with one script per row, plus (if you know them) the target length and the words that name your product and your audience. It prints a pass/fail table:

    | Check | Result | Detail |
    |---|---|---|
    | hook-fit | PASS | first line ~2.0 s of a 3.0 s window (5 words) |
    | hook-terms | PASS | product: sourdough; audience: busy, mornings |
    | claims | PASS | none of 22 listed words found |
    | cta | PASS | line 5 starts at ~11.2 s of ~12.8 s (88%) |
    | subtitle | PASS | widest line 37 of 40 |
    | duration | PASS | ~12.8 s against a 15.0 s target |
    | structure | PASS | 5 lines, no empty or repeated lines |
    | **Overall** | **PASS** | |
    

    What it does:

    • hook-fit: can the first line be spoken inside the opening window (3 seconds by default)?
    • hook-terms: do your product and audience words appear in what is spoken inside that window?
    • claims: lists the lines that contain words you marked as needing evidence ("best", "guaranteed" and similar; the list is yours to edit)
    • cta: exactly one call-to-action line, starting in the closing part of the script
    • subtitle: no subtitle line wider than your limit; Japanese and other full-width characters count double
    • duration: estimated spoken length against your target seconds
    • structure: empty lines, the opening line repeated later, repeated lines, broken or mixed speaker marks
    • --compare: put a rewrite beside the original and see which checks improved, got worse or stayed the same
    • --timeline for the estimated start and end of every line; --json, --strict and an exit code (0 / 1 / 2) for scripts and agent loops
    • Your own limits in a small JSON settings file; unknown keys are rejected so a typo cannot silently fall back to a default
    • Works with English and Japanese scripts (Latin words and CJK characters are timed separately); a Japanese example is included
    • SKILL.md tells an AI agent when to run it, and lists the questions the tool cannot answer (one promise, does it work with the sound off, three rewrites of the opening) so the agent answers them itself and re-checks every rewrite with the tool

    Honest limits, stated in the README: timings are estimates from reading speeds, not audio measurements; it does not check or claim to meet any ad platform's rules; it promises no results and cannot tell whether a claim is true; the default word lists are short general examples you should edit; it reads text only and never connects to an ad account, a model or the network.

    What is inside

    • SKILL.md, README.md, LICENSE
    • scripts/hook_checker.py
    • tests/test_hook_checker.py (72 tests)
    • examples/: a passing script, a failing script, a rewrite, a Japanese script, a CSV of two scripts, a settings file and the real output of each
    • images/, listing/

    Requirements and safety

    Python 3.9+ and nothing else. The tool makes no network calls, needs no credentials and writes no files. It only reads the file you point it to.

    License

    Personal, non-transferable license for your own projects, including commercial work. No resale or redistribution.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Marketing & SEO.

    Text only: no audio, video or subtitle files are read. Timings are estimates from reading speeds. It does not check ad platform rules or predict results. Default word lists are short examples; edit them.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 4 days ago

    Software
    Python 3.9+

    Permissions

    Terminal / Shell
    Read Files
    Listed4 days ago

    What's inside

    Frequently Asked Questions

    Seven things in a text script: whether the first line fits the opening window (3 seconds by default), whether your product and audience words appear in it, which lines contain words you marked as needing evidence, that there is exactly one call-to-action line near the end, subtitle line width, estimated length against your target, and structure (empty or repeated lines, mixed speaker marks).

    No. It reads text only (TXT, JSON or CSV). Timings are estimates from reading speeds, not audio measurements, so a real voice-over will differ. You can change the speeds in the settings file.

    No. It does not check or claim to meet any ad platform's rules, promises no results, and cannot tell whether a claim is true. It only lists the lines that contain words you marked as needing evidence. A script that passes can still be a poor ad.

    Python 3.9 or newer and nothing else. It makes no network calls, needs no account or credentials, and writes no files; it only reads the script file you point it to.

    Yes for Japanese and English: Latin words and CJK characters are timed separately and full-width characters count double in the subtitle width check. A Japanese example is included. Other scripts such as Arabic, Thai or Hindi are not timed.

    New in Marketing & SEO