Update to Reelyze

{
  "description": "Write a short-form video script or generate content ideas, prioritised by what actually drives reach. Use when asked to write a reel script, a hook, a TikTok script, or for ideas on what to post next.",
  "included_files": [],
  "name": "write-reel-script",
  "skill_md_contents": "---\nname: write-reel-script\ndescription: Write a short-form video script or generate content ideas, prioritised by what actually drives reach. Use when asked to write a reel script, a hook, a TikTok script, or for ideas on what to post next.\n---\n\n# Write a reel script\n\n## Tools\n\n| tool | cost | returns |\n|---|---|---|\n| `generate_script(topic, duration_seconds, language)` | paid plan, spends content quota | a full script |\n| `generate_ideas(count, language)` | paid plan, spends content quota | idea list |\n| `find_topics(niche, count, language)` | paid plan; cached reads free | timely, web-searched topics |\n\nThese are **synchronous** and return the result directly, with no job to poll.\n\nThey are much stronger when the person has connected Instagram and tracked\ncompetitors in the Reelyze dashboard, because the generation learns from what\nalready works on their account. They still work from a topic alone. If the\noutput feels generic, that is usually why, and it is worth saying so rather than\nregenerating.\n\n`find_topics` returns a cached result for free; only a `fresh: true` run spends\nthe metered web search, which is capped per billing cycle. Prefer the cached\nread unless the person explicitly wants new topics.\n\n## Write to the reach order, not to a formula\n\nRank every choice in the script by what actually moves distribution, in this\nexact order:\n\n1. **The hook, first 3 seconds.** The biggest single lever by a wide margin.\n2. **Watch time, the rest of the video.** A *separate* lever. A script can win\n   the first 3 seconds and still lose people at 5 to 8 seconds, and low average\n   watch time stops the algorithm expanding reach even though the opening\n   worked. So the script needs a reason to keep watching at 5s, at 10s, and at\n   15s, not only at 0s.\n3. shares\n4. likes\n5. saves\n6. reposts\n7. comments\n\nA script optimised for comments at the expense of the hook is optimised for the\nweakest signal in the list.\n\n## What a usable script contains\n\n- the hook as **exact words**, not a description of a hook\n- on-screen text for the opening, since most viewers are watching muted\n- a named reason to stay at roughly 5 seconds and again near the middle\n- a close that earns a share, which outranks a like\n- a length that matches `duration_seconds`, written to be *said* out loud rather\n  than read\n\nBe concrete and specific. \"Share a personal story\" is not a script. The point of\ngrounding generation in the creator's own posts is to avoid exactly that kind of\noutput, so do not hand it back in the reply.\n\n## Do not\n\n- Do not promise a script will go viral. 7.7% of reels in Reelyze's measured\n  dataset reach 10x the account's follower count, and nothing in a script moves\n  that to a certainty.\n- Do not pad to length. A 30-second script that works beats a 60-second one that\n  drifts, and drift is a watch-time problem.\n- Do not add more than five hashtags. See `fix-reel-hashtags`.\n"
}