Define how unsupervised work is judged before it runs. Use when work will run without a human watching, optimizing toward something.
79%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./hope/skills/target/SKILL.mdSuccess is defined before the run, not by it. Build the contract by invoking each named skill with the Skill tool where its condition holds:
cheat-museum.md, then hunt false passes specific to this contract.Each open false pass judge finds re-enters as an amendment — back through the drafting and anchoring conditions above — until the verdict stands.
Hand it back as short bullets, one part per line: each part the drafting named, the dry-run value recorded, each cheap false pass closed. It locks only when judge's verdict stands and the user locks it.
Two things stay open for the human alone, before the run starts: capping the spend with a disposable key, since the contract bounds correctness and only the key bounds cost; and watching the first cycle to see the run use what the contract names.
If the running work later games the contract, the cheat is a bug in the contract: amend it here and rerun from the last honest point.
A human will watch each step → no contract needed; proceed with the decided path. Success cannot be made mechanical → the work is not ready to run unsupervised — say so and stop.
saadshahd/moo.md
c263dea
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.