hook-variants
Skill0 starsChanged 2 days agoMITView on GitHub
Render several opening-hook variants of a voiceover in the same voice so creators can A/B test the first 3 seconds of a YouTube Short, TikTok, Reel or ad. One hook per line in, equally loud trimmed WAVs plus a manifest with real spoken length, words per second and an over-budget flag out. Use when the user asks for alternative hooks, intro variations, A/B test openings, or "which hook is shortest/punchiest". Voice by Miragea (saved or cloned voice); stdlib Python + ffmpeg.
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- OpenArt-AI/skillstheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- OpenArt-AI/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- llms.txtllms.txt
- audiogram-clipsSkill
- auto-brollSkill
- remotion-narrationSkill
- screen-recording-voiceoverSkill
- shorts-voiceoverSkill
- ugc-video-adsSkill
- video-captionsSkill
- video-dubbingSkill
- video-to-shortsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Very specific: line 23
Check MIRAGEA_API_KEY is set (never print it).
- Distinctive: line 26
If the user gave a topic but no hooks, write 4-6 hooks of 5-10 words: a bold claim, a question, a number, a mistake, a "stop doing X".
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Hook variants
The first seconds decide whether a viewer stays. This skill voices every candidate hook in the same voice, trims dead air, matches loudness (-14 LUFS by default) and measures the real spoken length, so variants are compared fairly and dropped straight into an editor or ad test.
When to use
- "Give me 5 hook options for this Short and voice them."
- "Which of these intros fits in 3 seconds?"
- "Make A/B versions of the opening line in my voice."
Steps
- Check
MIRAGEA_API_KEYis set (never print it). Voice:MIRAGEA_VOICE_ID, or a public clip URL of the user's own voice with its exact words (MIRAGEA_REF_URL,MIRAGEA_REF_TEXT). Only clone a voice the user owns or may use. - If the user gave a topic but no hooks, write 4-6 hooks of 5-10 words: a bold claim, a question, a number, a mistake, a "stop doing X". Save one per line.
- Estimate first (free, no API):
python scripts/hooks.py hooks.txt --dry-run - Render:
python scripts/hooks.py hooks.txt -o hooks_out --budget 3 - Report each hook with its seconds, flag any over budget, and suggest a tighter rewrite for those.
Output
hooks_out/hook_01.wav ... and hooks_out/manifest.json, sorted shortest first:
{"id","text","words","seconds","words_per_sec","over_budget","file"}.
Why not other tools
| Typical TTS app / hook generator | hook-variants | |
| Voice | Stock voices | Your saved or cloned voice |
| Fair comparison | Different loudness and silence per take | Edge silence trimmed, all at -14 LUFS |
| Length check | Guessed from text | Measured from the rendered audio, with budget flag |
| Batch | One line at a time | All variants in one command |
| Cost to try | Paid per seat | Free, MIT; --dry-run costs nothing |
FAQ
- Why is a hook over budget? Over ~8 words rarely fits 3 s. Cut filler words first.
- Mono or stereo? Whatever Miragea returns, resampled to 48 kHz for video editors.
- Errors come with a hint (missing key, no voice, quota). Nothing is written for a failed hook.
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
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.

