FixKit AI

Loop/Prompt Library / Loops from builders on X

๐Ÿ” Only ping me if it really matters

The AI watches news or official filings about things you care about and only alerts you when something big happens, with a one-line reason.

Use it when: You want to know about important news on a topic or company without reading everything.

๐Ÿ›‘ Stops when: Each check ends with one alert or nothing. Quiet days stay quiet.

Copy this loop

Watch [topic, companies, or ticker symbols] using [news sites, official filing pages]. Check every [6] hours. 'Big enough to alert me' means: [e.g. a major announcement, a new official filing that isn't routine, a big price move]. Ignore routine items and repeats of old news. When something passes the bar, send me: the headline, one line on why it matters, and the link. Never say whether to buy or sell. Stop each check after the alert or 'nothing new'. Send at most [3] alerts a day; bundle the rest into one end-of-day note.

Review every change the agent makes before you keep it. Set a budget or round limit โ€” the prompt includes one.

Found on X ยท by @cruq_ai. Prompt rewritten in plain English by FixKit AI.

More loops like this

One useful thing every night

You give the AI a short mission, and each night it picks one task that moves you closer and leaves it for you to check in the morning.

Two watchers keep your agent healthy

Two separate AI helpers read your main agent's logs, find what broke, and must both agree on a fix before it is used.

Weekly skill cleanup

Once a week, the AI grades every saved skill or saved prompt it uses, removes the dead ones, and merges the repeats.

Overnight drafts that learn from results

Each night the AI drafts tomorrow's post from your content plan, and reads your notes about what worked before it writes the next one.

Split the work, keep only what passes

Splits a big job across several AI helpers working side by side, checks each one's work, and keeps only the work that passes.

Practice a website task until it's reliable

The AI tries a website chore, learns from each failed try, and keeps adjusting until it has steps that work every time.