Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jeremylongshore/lindy-performance-tuning
Optimize Lindy AI agent execution speed, reliability, and cost efficiency.
Passed 20 of 22 test cases with the skill, and 10 of 22 without it.
and 13 more in the full report
11 fixed9 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
In a Lindy workflow, an AI prompt step is currently used to decide which channel to post to, outputting 'Post to the support channel'. We already know all support notifications must go to #support-triage. How should this field be configured to eliminate LLM credit usage?
| Checked | Without skill | With skill |
|---|---|---|
| Recommend using Set Manually mode for the channel field. | Missed | Passed |
| Specify setting the field directly to `#support-triage`. | Passed | Passed |
The instructions your model reads when the skill loads.
Lindy agents execute as multi-step workflows where each step (LLM call, action execution, API call, condition evaluation) adds latency and credit cost. Optimization targets: fewer steps, smaller models, faster actions, tighter prompts.
In the Tasks tab, open a completed task and review:
Common bottlenecks:
| Bottleneck | Symptom | Fix |
|---|---|---|
| Large model on simple task | High credit cost, slow | Switch to Gemini Flash |
| Too many LLM steps | Long total duration | Consolidate into fewer steps |
| Agent Step with many skills | Unpredictable path | Reduce to 2-4 focused skills |
| Knowledge Base over-querying | Multiple KB searches | Increase Max Results per query |
| Sequential when parallel possible | Unnecessary waiting | Use loop with Max Concurrent > 1 |
The single biggest performance lever. Match model to task complexity:
| Task | Recommended Model | Speed | Credits |
test cases passed, vs 10 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.