Loop/Prompt Library / Loops from builders on X
🔁 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.
Use it when: Your agent has piled up lots of skills, saved prompts, or instructions and you don't know which ones still help.
🛑 Stops when: Every skill is marked keep, merge, or remove, and you have a short report. Nothing is deleted without your OK.
Copy this loop
Look at every skill (or saved prompt) in [folder]. For each one, tell me: how often it was used in the last [30] days, whether it worked when used, and whether another skill does the same job. Grade each one: keep, improve, merge with [other], or remove. Show your proof for each grade. Do not delete or merge anything yet. Give me a one-page report, then wait for my OK. After I approve, make only the changes I approved and show me the before and after. Stop after one pass through the list. Repeat next week.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @AntoineRSX. 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.
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.
Make the AI run your checks
Writes down the checks you normally do by hand, so the AI runs them after every change and must fix any failure before it moves on.