Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/goal-convergence
Goal-oriented autonomous loop with external completion oracle. Keeps iterating until verifiable stopping conditions are met, checked by a separate model.
Passed 19 of 21 test cases with the skill, and 4 of 21 without it.
and 24 more in the full report
16 fixed4 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
An item with ID 'tr-402' in the triage inbox needs to be converted into an active autonomous goal. What exact CLI command executes this promotion?
| Checked | Without skill | With skill |
|---|---|---|
| Prompts the exact command /triage act tr-402 goal. | Missed | Passed |
The instructions your model reads when the skill loads.
Goal-oriented autonomous loop with external completion oracle. Based on Addy Osmani's Loop Engineering principle: "Keep going until a verifiable stopping condition holds, with a separate small model checking completion."
/goal command/triage act <id> goalThe model that wrote the code is too nice grading its own homework. A second model (the oracle) with different instructions and READ-ONLY tools catches what the first talked itself into.
Maker (primary model, full tools)
│
▼ produces iteration output
│
Oracle (different model, read-only)
│
├─ ALL conditions pass → CONVERGE (goal done)
├─ Some fail + budget remains → nextHint → LOOP (maker iterates)
└─ Budget exhausted → ESCALATE (triage inbox)
CREATE → ACTIVE → [iterate] → CONVERGED
│
├──── PAUSED (manual /goal pause)
└──── ESCALATED (budget exhausted or repeated failure)
test cases passed, vs 4 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.