Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sharpdeveye/accelerate
Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.
Passed 9 of 16 test cases with the skill, and 13 of 16 without it.
0 fixed13 passed either way4 still failing5 broke
Tokens, turns and time describe resource use, not a dollar price.
The instructions your model reads when the skill loads.
Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the context-management reference in the agent-workflow skill for window optimization and budget strategies.
Make the workflow faster and cheaper without sacrificing quality. Measure before and after.
Measure current performance:
Current metrics:
Latency (p50): ___ms
Latency (p95): ___ms
Cost per request: $___
Token usage (avg): ___ input / ___ output
Error rate: ___%
Reduce Token Usage
Model Cascading
Caching
test cases passed, vs 13 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.