Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aiskillstore/latency-tracker
Per-call and aggregated latency tracking for MEV infrastructure.
Passed 19 of 23 test cases with the skill, and 5 of 23 without it.
and 21 more in the full report
15 fixed4 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
Provide a minimal TypeScript snippet that starts a liquidation tracking session, executes a Rust hotpath span, and completes the session.
| Checked | Without skill | With skill |
|---|---|---|
| Includes tracker.startE2E with an identifier like 'liq' | Missed | Passed |
| Uses e2e.span to measure internal operations | Missed | Passed |
| Calls e2e.complete at session end | Missed | Passed |
The instructions your model reads when the skill loads.
Per-call and aggregated latency tracking for MEV infrastructure.
Structure spans from e2e_flow down to individual calls.
Wrap operations in tracker.span() calls.
Configure alerts for latency exceeding expected ranges.
e2e_flow (root) ├── rust_hotpath_call (5-15ms) │ └── rpc_eth_call (5-20ms) ├── tx_submit └── tx_confirm (1-15s)
const e2e = tracker.startE2E('liq');
await e2e.span('rust_call', async () => {
test cases passed, vs 5 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.