Loop/Prompt Library / Loops from builders on X
🔁 Tune a skill until the AI uses it
If the AI won't use one of your saved skills when it should, you tweak the skill's description and replay the same message until it picks it up every time.
Use it when: You made a saved skill or tool, but the AI ignores it.
🛑 Stops when: The AI picks the skill [3] times in a row for your test messages, or the round limit is hit.
Copy this loop
My skill [name] should be used when I say things like: [3 example messages]. It is NOT for: [2 examples]. Here's its current description: [paste]. Each round: suggest one change to the description (clearer 'use when' words, fewer vague words). I'll save it and replay the example messages in a fresh session, then tell you which ones picked the skill. Keep a table of each version and its results. Make sure it doesn't start firing on the 'NOT for' examples. Stop when all examples work [3] times in a row, or after [6] rounds.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @bcherny. 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.