Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →florianbruniaux/rtk-optimizer
Wrap high-verbosity shell commands with RTK to reduce token consumption.
Passed 22 of 22 test cases with the skill, and 6 of 22 without it.
and 14 more in the full report
16 fixed6 passed either way0 still failing0 broke2 errored
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.
I want to inspect the details and description of a GitHub pull request using GitHub CLI. Instead of running standard 'gh pr view', what wrapped command should be run to reduce context payload by ~87%?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends 'rtk gh pr view' for pull request details. | Missed | Passed |
The instructions your model reads when the skill loads.
Purpose: Automatically suggest RTK wrappers for high-verbosity commands to reduce token consumption.
git log → rtk git log (92.3% reduction)git status → rtk git status (76.0% reduction)find → rtk find (76.3% reduction)git diff → rtk git diff (55.9% reduction)cat <large-file> → rtk read <file> (62.5% reduction)pnpm list → rtk pnpm list (82% reduction)pnpm test / vitest run → rtk vitest run (90% reduction)cargo test → rtk cargo test (90% reduction)cargo build → rtk cargo build (80% reduction)cargo clippy → rtk cargo clippy (80% reduction)pytest → rtk python pytest (90% reduction)go test → rtk go test (90% reduction)gh pr view → rtk gh pr view (87% reduction)gh pr checks → rtk gh pr checks (79% reduction)test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.