Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use the correct AWS CLI profile when running AWS commands based on the target environment.
.claude/skills/abdullahkhawer-aws-cli/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -13% | 0% |
When running AWS CLI commands, always pass the --profile flag based on the target environment.
Update the profile map below with your AWS profile names as configured in ~/.aws/config:
| Environment | Profile | |---|---| | Production | <your-prod-profile> | | Staging / Non-Prod | <your-nonprod-profile> |
bashaws <service> <command> --profile <profile> [options]
bash# Production aws s3 ls --profile my-prod-profile # Staging / Non-Prod aws s3 ls --profile my-nonprod-profile
--profile explicitly — never rely on the default profile.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 6,659 | 2,528 | -62% | 1 | 1 | 0% | 1,306 | 567 | -57% | 0 | 0 | — |
case-02 | fail→pass | 5,178 | 2,213 | -57% | 1 | 1 | 0% | 936 | 562 | -40% | 0 | 0 | — |
case-03 | pass→pass | 4,783 | 3,190 | -33% | 1 | 1 | 0% | 851 | 795 | -7% | 0 | 0 | — |
case-04 | pass→pass | 2,390 | 2,107 | -12% | 1 | 1 | 0% | 390 | 479 | +23% | 0 | 0 | — |
case-05 | pass→pass | 16,803 | 2,857 | -83% | 1 | 1 | 0% | 1,184 | 656 | -45% | 0 | 0 | — |
case-06 | fail→pass | 3,330 | 4,322 | +30% | 1 | 1 | 0% | 504 | 998 | +98% | 0 | 0 | — |
case-07 | pass→pass | 3,391 | 2,317 | -32% | 1 | 1 | 0% | 523 | 587 | +12% | 0 | 0 | — |
case-08 | fail→pass | 6,068 | 6,345 | +5% | 1 | 1 | 0% | 1,163 | 1,135 | -2% | 0 | 0 | — |
case-09 | pass→pass | 5,867 | 1,979 | -66% | 1 | 1 | 0% | 1,039 | 467 | -55% | 0 | 0 | — |
case-10 | pass→pass | 5,057 | 2,152 | -57% | 1 | 1 | 0% | 881 | 538 | -39% | 0 | 0 | — |
case-11 | fail→pass | 4,574 | 2,025 | -56% | 1 | 1 | 0% | 649 | 472 | -27% | 0 | 0 | — |
case-12 | fail→pass | 5,888 | 4,110 | -30% | 1 | 1 | 0% | 1,139 | 995 | -13% | 0 | 0 | — |
case-13 | fail→pass | 7,353 | 2,873 | -61% | 1 | 1 | 0% | 1,496 | 690 | -54% | 0 | 0 | — |
case-14 | fail→fail | 2,783 | 2,039 | -27% | 1 | 1 | 0% | 430 | 523 | +22% | 0 | 0 | — |
case-15 | fail→pass | 2,152 | 2,610 | +21% | 1 | 1 | 0% | 347 | 576 | +66% | 0 | 0 | — |
case-16 | pass→pass | 7,662 | 3,687 | -52% | 1 | 1 | 0% | 1,358 | 637 | -53% | 0 | 0 | — |
case-17 | pass→pass | 3,522 | 2,628 | -25% | 1 | 1 | 0% | 697 | 728 | +4% | 0 | 0 | — |
case-18 | pass→pass | 5,760 | 3,725 | -35% | 1 | 1 | 0% | 1,071 | 659 | -38% | 0 | 0 | — |
case-19 | fail→pass | 2,928 | 2,482 | -15% | 1 | 1 | 0% | 502 | 648 | +29% | 0 | 0 | — |
case-20 | fail→fail | 3,044 | 2,326 | -24% | 1 | 1 | 0% | 541 | 589 | +9% | 0 | 0 | — |
case-21 | pass→pass | 5,493 | 2,414 | -56% | 1 | 1 | 0% | 899 | 527 | -41% | 0 | 0 | — |
case-22 | pass→pass | 12,139 | 2,724 | -78% | 1 | 1 | 0% | 711 | 632 | -11% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +36 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.