Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →okhp3/okhp3-nfl-fantasy-picks
Select NFL fantasy players, DFS lineups, salary-cap rosters, waiver priorities, or trade targets under a scoring and budget system.
Passed 19 of 22 test cases with the skill, and 14 of 22 without it.
and 3 more in the full report
6 fixed13 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to run the local transparent small-roster optimizer fixture located in the repository to view a sample lineup output. Which command line invocation reproduces the small roster example?
| Checked | Without skill | With skill |
|---|---|---|
| Specify running scripts/calculate-fantasy-lineup.py with examples/fantasy-example.json. | Missed | Passed |
The instructions your model reads when the skill loads.
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Optimize NFL fantasy decisions under scoring, roster, salary, and risk constraints. A player is not valuable merely because they are among the best players. The relevant question is how much usable fantasy production they provide relative to cost, replacement value, uncertainty, positional scarcity, and roster construction.
| In scope | Out of scope |
|---|---|
| Season-long and DFS fantasy decisions | Sportsbook betting or wagering recommendations |
| Salary, points, replacement value, and roster optimization | Current facts without a verified source and as-of date |
| Player projections with floor, ceiling, and uncertainty | Guaranteed outcomes or certainty language |
Before ranking players, identify:
If the user does not provide these, state the assumptions and do not present a universal ranking as authoritative.
Use a constrained value model rather than raw projected points alone:
fantasy value = projected points - replacement baseline
cost efficiency = fantasy value / salary or roster cost
decision value = expected value adjusted for uncertainty, scarcity, and constraints
test cases passed, vs 14 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.