Find what to make next: proven reels to adapt, outliers in a niche, saved inspiration and the creator's own results. Use before scripting, when asked what to post, to judge whether a reference is proven, or to turn saved reels into a short list of ideas.
Installs into .claude/skills of the current project.
Are you the author of Find Ideas?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/alisadiq-ai-find-ideas)
---
name: find-ideas
description: "Find what to make next: proven reels to adapt, outliers in a niche, saved inspiration and the creator's own results. Use before scripting, when asked what to post, to judge whether a reference is proven, or to turn saved reels into a short list of ideas."
---
# Find ideas
Start every reel from evidence: a reference that already worked for someone with a
similar audience, or a result from the creator's own posts. The output is a short
list of ideas, each with its reference, why it's worth copying and the angle that's
true for this creator. Hand the chosen one to `write-script`.
## Where ideas come from
- **References the creator supplies:** a reel URL, a saved post or a screen recording.
- **The creator's saved inspiration:** with FavStash connected, search the stash by
topic, hook pattern or audience problem, and read saved transcripts and on-screen
text instead of guessing them. Saving a new URL keeps it with the rest.
- **Niches and competitors:** recent posts from creators the audience already follows.
Compare each post with that creator's own baseline, not with other accounts.
- **The creator's results:** with FavStash analytics, their own outliers and their
weakest openings are the best guide to the next test.
Without FavStash, work from supplied URLs and transcripts; everything below still applies.
## Is the reference proven?
Call a reference **proven** only against its own creator's baseline: views at least
3× the median of a comparable recent sample of their posts. Record the views,
publish date, capture date and sample size. Without a baseline it is a **format
reference**: useful for structure, not proof that the hook works.
- A high comment count on a comment-to-DM post shows the gate converted, not that
the hook earned reach.
- Performance shows association. Topic, timing and distribution stay confounded.
- Saved content is taste and structure, never factual proof for the creator's claims.
## What to record for each idea
```text
Idea: one line, in the viewer's words
Reference: URL, creator, views vs their median (proven | format | original)
Why it worked: the hook lever, the first frame, the payoff
True for this creator: what they can honestly say or show; what must change
Proof available: footage, screen capture, real numbers (or what's missing)
```
Look at the reference itself when the treatment matters: the first frame, the cuts,
the captions and where sounds land. A transcript alone doesn't show the edit;
`edit-video`'s reference helper samples frames from a URL into an analysis copy.
Give the creator three to five ideas, strongest first, and say which one you'd make.
Rights don't transfer with an idea: adapt the hook, structure and pacing, and make
the video from the creator's own footage.