Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interactive wizard to design an SLO with SLI, target, error budget, and burn-rate alerts
.claude/skills/alirezarezvani-slo-design/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 9% | 0% |
Step through SLO design using the slo-architect skill. Produces an SLO definition, computes error budget + multi-window burn-rate alerts, and runs the reviewer to catch common bugs.
/slo-design
/slo-design --service checkout-svc --sli-type request-success-rate --target 99.9bashSKILL=engineering/slo-architect/skills/slo-architect # Step 1: gather inputs (service, sli-type, target, window, owner) # Step 2: render SLO definition python "$SKILL/scripts/slo_designer.py" \ --service "$SERVICE" \ --sli-type "$SLI_TYPE" \ --target "$TARGET" \ --window-days "$WINDOW_DAYS" \ --owner "$OWNER" \ --policy-doc "$POLICY_DOC" \ --format json > .slo.json # Step 3: compute error budget + burn-rate alerts python "$SKILL/scripts/error_budget_calculator.py" \ --target "$TARGET" \ --window-days "$WINDOW_DAYS" # Step 4: render the markdown SLO for peer review python "$SKILL/scripts/slo_designer.py" \ --service "$SERVICE" \ --sli-type "$SLI_TYPE" \ --target "$TARGET" \ --window-days "$WINDOW_DAYS" \ --owner "$OWNER" \ --policy-doc "$POLICY_DOC" # Step 5: validate against the reviewer echo "=== After saving the SLO, run slo_review.py against the doc ==="
A markdown SLO definition with:
slo-architect skill installed.slo.json written for use with downstream tools (chaos-engineering blast radius, etc.)slo_review.py checks| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 27,413 | 17,695 | -35% | 1 | 1 | 0% | 5,855 | 4,568 | -22% | 0 | 0 | — |
case-02 | fail→fail | 20,657 | 22,970 | +11% | 1 | 1 | 0% | 4,229 | 5,368 | +27% | 0 | 0 | — |
case-03 | fail→fail | 27,395 | 5,432 | -80% | 1 | 1 | 0% | 5,638 | 879 | -84% | 0 | 0 | — |
case-04 | fail→fail | 13,954 | 9,521 | -32% | 1 | 1 | 0% | 2,957 | 2,639 | -11% | 0 | 0 | — |
case-05 | fail→pass | 7,723 | 4,459 | -42% | 1 | 1 | 0% | 1,420 | 1,404 | -1% | 0 | 0 | — |
case-06 | fail→pass | 7,359 | 2,432 | -67% | 1 | 1 | 0% | 1,130 | 1,023 | -9% | 0 | 0 | — |
case-07 | pass→pass | 13,494 | 16,879 | +25% | 1 | 1 | 0% | 2,566 | 4,181 | +63% | 0 | 0 | — |
case-08 | fail→fail | 12,089 | 7,264 | -40% | 1 | 1 | 0% | 2,001 | 1,806 | -10% | 0 | 0 | — |
case-09 | pass→pass | 9,647 | 4,830 | -50% | 1 | 1 | 0% | 1,617 | 1,488 | -8% | 0 | 0 | — |
case-10 | pass→pass | 11,932 | 8,599 | -28% | 1 | 1 | 0% | 1,931 | 1,968 | +2% | 0 | 0 | — |
case-11 | fail→pass | 8,094 | 2,826 | -65% | 1 | 1 | 0% | 1,370 | 1,078 | -21% | 0 | 0 | — |
case-12 | fail→pass | 6,789 | 2,307 | -66% | 1 | 1 | 0% | 1,083 | 971 | -10% | 0 | 0 | — |
case-13 | pass→pass | 4,947 | 3,678 | -26% | 1 | 1 | 0% | 769 | 1,105 | +44% | 0 | 0 | — |
case-14 | fail→pass | 4,334 | 2,213 | -49% | 1 | 1 | 0% | 822 | 895 | +9% | 0 | 0 | — |
case-15 | pass→pass | 7,462 | 3,199 | -57% | 1 | 1 | 0% | 1,174 | 1,128 | -4% | 0 | 0 | — |
case-16 | fail→pass | 11,466 | 3,979 | -65% | 1 | 1 | 0% | 2,136 | 1,312 | -39% | 0 | 0 | — |
case-17 | fail→pass | 8,061 | 1,676 | -79% | 1 | 1 | 0% | 1,430 | 794 | -44% | 0 | 0 | — |
case-18 | fail→pass | 8,222 | 1,719 | -79% | 1 | 1 | 0% | 1,453 | 864 | -41% | 0 | 0 | — |
case-19 | fail→pass | 10,235 | 6,804 | -34% | 1 | 1 | 0% | 1,708 | 1,685 | -1% | 0 | 0 | — |
case-20 | pass→pass | 8,598 | 8,878 | +3% | 1 | 1 | 0% | 1,884 | 2,563 | +36% | 0 | 0 | — |
case-21 | pass→fail | 6,820 | 7,443 | +9% | 1 | 1 | 0% | 1,363 | 1,972 | +45% | 0 | 0 | — |
case-22 | pass→pass | 3,867 | 4,796 | +24% | 1 | 1 | 0% | 747 | 1,469 | +97% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +36 percentage points is the difference between those two pass rates over the 21 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
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.