Install any skill in seconds. Free to start, no credit card required.
Get Started Free →okhp3/okhp3-evidence-standard
Classify consequential claims as confirmed, inferred, proposal, or unknown and keep those tiers visible.
Passed 18 of 22 test cases with the skill, and 7 of 22 without it.
and 19 more in the full report
13 fixed5 passed either way2 still failing2 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.
We found an explicit environment variable setting `MAX_WORKERS=32` inside `/etc/gunicorn/prod.conf`. Format this finding into our claim structure.
| Checked | Without skill | With skill |
|---|---|---|
| Classifies the `MAX_WORKERS=32` finding under the Confirmed tier. | Missed | Passed |
| Cites `/etc/gunicorn/prod.conf` as the exact local path in the evidence field. | Passed | Passed |
The instructions your model reads when the skill loads.
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Return one row per consequential claim with claim, tier, evidence,
consequence_if_false, and next_check. Use UNKNOWN when a check did not
run. Cite the exact local path, tool result, or source identifier when one is
available.
Use four tiers:
INFERRED or ASSUMPTION when the context does not already make that clear.When sources conflict, show both claims and their tiers before recommending a resolution. Do not resolve by confidence, detail, timestamp, version label, or majority vote alone.
Move tiers in both directions. Upgrade a claim when direct evidence arrives. Downgrade it when the stated check did not run or the cited source does not support it. Agreement among builds that have already read one another is a consistency signal, not independent corroboration.
End reconciliations and handoffs with remaining unknowns and the next check that could resolve them. Classification does not grant permission to edit, publish, move, or delete the underlying material.
Built by Jamie Hill · OverKill Hill P³ Published at github.com/OKHP3 Part of the OKHP3/skillz Agent Skill library. MIT License -- free to use, fork, and adapt. A nod to the source is appreciated.
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.