FixKit AI

Loop/Prompt Library / Loops from builders on X

๐Ÿ” Weekly school grades and missing-work brief

Each week the AI reads your kids' grade reports and sends you a short note about grades and anything missing.

Use it when: You want to catch missing homework early without logging into school sites every day.

๐Ÿ›‘ Stops when: This week's brief is delivered.

Copy this loop

Every [Friday], read the grade and assignment reports I export or paste from the school portal: [paste or folder]. I'll log in myself; don't ask for or type passwords. Use first names only. For each child: grades that changed this week, missing or late assignments with due dates, and anything the teacher noted. Put missing work at the top. Suggest one small action for each missing item (e.g. 'ask about the make-up deadline'). Don't contact teachers or submit anything. Stop after the brief, which should fit on one screen, or after reading [3] children's reports.

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 @MattForsberg. 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.