Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →raisecornfritter28/priority-check
Grounds the user against their own stated priorities by rating the current chat or project as High, Medium, or Low priority. Built for people who lose hours to FOMO, ADHD-driven hyperfocus, escapism, or just having too much fun on side projects, and want a lightweight signal to stay aware of how they're spending their time and attention.
Passed 18 of 22 test cases with the skill, and 6 of 22 without it.
and 15 more in the full report
13 fixed5 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
===== %%PRIORITY CHECK SETTINGS v1%% high: finance medium: low: run_on_chat_start: false ===== Please run priority-check reset.
| Checked | Without skill | With skill |
|---|---|---|
| Ask for explicit user confirmation before replacing existing priority settings. | Missed | Passed |
| Refrain from asking questionnaire questions prior to user confirmation. | Passed | Passed |
The instructions your model reads when the skill loads.
A grounding tool for people who lose hours to interesting-but-low-value pursuits. It reads the user's defined priority tiers (or helps them define some) and rates the current conversation or project against those tiers, prepended as a single line so it's a reminder, not an interruption.
Built for the kind of person who knows they over-invest in side projects, rabbit holes, or fun-but-pointless work, and wants a lightweight signal -- not a blocker -- to stay grounded. Especially useful for users with ADHD, FOMO-driven attention drift, executive function challenges, or anyone who wants their AI assistant to surface trade-offs rather than enable drift.
The skill is fully self-contained. On first use, it walks the user through a short questionnaire to establish their priority tiers, then generates a paste-ready settings block for their Claude preferences. On subsequent uses, it reads those settings and rates the topic at hand.
The skill accepts one of four commands as part of its invocation. If no command is given, default to chat.
| Command | Behavior |
|---|---|
chat (default) | Rate the current conversation against the user's priority tiers |
project | Rate the current project (if the user is in one) against the priority tiers |
help | Show what the skill does and list the user's current priority settings |
reset | Re-run the questionnaire to redefine priority tiers (asks for confirmation first) |
Examples of how the user may invoke:
chatprojecthelpchat (alias)chatThe skill's configuration lives in the user's preferences (or a project instructions file) inside a clearly delimited block:
=====
%%PRIORITY CHECK SETTINGS v1%%
high: <comma-separated topics>
medium: <comma-separated topics>
low: <comma-separated topics>
test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.