hook-variantslisted
Install: claude install-skill yyert123/miragea-skills
# 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
1. Check `MIRAGEA_API_KEY` is 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.
2. 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.
3. Estimate first (free, no API): `python scripts/hooks.py hooks.txt --dry-run`
4. Render: `python scripts/hooks.py hooks.txt -o hooks_out --budget 3`
5. 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