Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Mitigate a production incident or urgent regression first, then route to root-cause remediation and a postmortem.
.claude/skills/hoangnguyen0403-incident-hotfix/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -49% | 0% |
> !IMPORTANT] > Mitigate a production incident or urgent regression first, then route to root-cause remediation and a postmortem.
Optional args: slug=<feature>, ticket=<id/url>, mode=interactive|autonomous|channel, channel=<id>, auto_continue=true|false, profile=business|hybrid|technical.
When the user asks to perform this workflow, execute the following steps:
Goal: Stop user-facing harm immediately, then hand off to root-cause discipline instead of debugging live.
deploy-release rollback path and prior deployment report if present.dev-fix for root-cause debugging under the normal Propose -> Approve -> Verify cycle.dev-fix's root-cause-before-code requirement just because mitigation already shipped.verify-work confirms the permanent fix, route to retro-learn for a postmortem.dev-fix.slug, operator_profile (carried, not re-inferred), severity, mitigation applied, stabilization evidence, outcome report, next workflow.md# Incident Hotfix: [Name] ## Severity And Blast Radius ## Mitigation Applied ## Stabilization Evidence | Signal | Before | After | | --- | --- | --- | | [signal] | [value] | [value] | ## Root Cause Handoff ## Outcome Report feature_status: partially_implemented | blocked requirement_trace: BRD-OBJ-* -> REQ-* -> AC-* -> SRS-* -> evidence completed_evidence: []; missing_evidence: []; decision_needed: []; recommended_next_workflow: dev-fix ## Next Workflow dev-fix | verify-work | retro-learn ## Cost Report Call `get_session_cost(workflow="incident-hotfix")` before final handoff.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→pass | 14,360 | 5,862 | -59% | 1 | 1 | 0% | 2,330 | 1,732 | -26% | 0 | 0 | — |
case-07 | pass→pass | 7,052 | 4,841 | -31% | 1 | 1 | 0% | 1,104 | 1,345 | +22% | 0 | 0 | — |
case-01 | fail→pass | 14,317 | 7,150 | -50% | 1 | 1 | 0% | 2,671 | 2,195 | -18% | 0 | 0 | — |
case-02 | pass→pass | 13,642 | 8,805 | -35% | 1 | 1 | 0% | 2,513 | 2,391 | -5% | 0 | 0 | — |
case-03 | fail→pass | 11,538 | 6,934 | -40% | 1 | 1 | 0% | 2,076 | 1,944 | -6% | 0 | 0 | — |
case-04 | pass→pass | 8,595 | 6,096 | -29% | 1 | 1 | 0% | 1,355 | 1,750 | +29% | 0 | 0 | — |
case-05 | pass→pass | 8,417 | 4,762 | -43% | 1 | 1 | 0% | 1,295 | 1,552 | +20% | 0 | 0 | — |
case-06 | pass→pass | 5,244 | 4,711 | -10% | 1 | 1 | 0% | 960 | 1,558 | +62% | 0 | 0 | — |
case-09 | pass→pass | 6,348 | 11,056 | +74% | 1 | 1 | 0% | 1,020 | 2,447 | +140% | 0 | 0 | — |
case-10 | pass→pass | 3,331 | 2,918 | -12% | 1 | 1 | 0% | 513 | 867 | +69% | 0 | 0 | — |
case-11 | fail→pass | 8,343 | 5,444 | -35% | 1 | 1 | 0% | 1,394 | 1,659 | +19% | 0 | 0 | — |
case-12 | fail→fail | 12,436 | 4,892 | -61% | 1 | 1 | 0% | 1,954 | 1,531 | -22% | 0 | 0 | — |
case-13 | pass→pass | 8,885 | 4,157 | -53% | 1 | 1 | 0% | 1,437 | 1,442 | +0% | 0 | 0 | — |
case-14 | pass→pass | 8,449 | 2,207 | -74% | 1 | 1 | 0% | 1,383 | 1,030 | -26% | 0 | 0 | — |
case-15 | pass→pass | 7,757 | 2,421 | -69% | 1 | 1 | 0% | 1,173 | 1,051 | -10% | 0 | 0 | — |
case-16 | pass→pass | 11,072 | 3,328 | -70% | 1 | 1 | 0% | 1,904 | 1,238 | -35% | 0 | 0 | — |
case-17 | pass→pass | 9,021 | 2,216 | -75% | 1 | 1 | 0% | 1,480 | 994 | -33% | 0 | 0 | — |
case-18 | fail→pass | 19,391 | 2,502 | -87% | 1 | 1 | 0% | 2,205 | 1,131 | -49% | 0 | 0 | — |
case-19 | pass→pass | 12,451 | 2,569 | -79% | 1 | 1 | 0% | 2,060 | 1,028 | -50% | 0 | 0 | — |
case-20 | fail→pass | 6,457 | 2,417 | -63% | 1 | 1 | 0% | 1,108 | 1,004 | -9% | 0 | 0 | — |
case-21 | fail→pass | 9,361 | 1,646 | -82% | 1 | 1 | 0% | 1,485 | 909 | -39% | 0 | 0 | — |
case-22 | pass→pass | 11,650 | 2,886 | -75% | 1 | 1 | 0% | 1,846 | 1,227 | -34% | 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 +32 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.