Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Prepare and verify a staged or production deployment with rollback and smoke checks.
.claude/skills/hoangnguyen0403-deploy-release/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 121% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 145% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 210% | 0% |
> !IMPORTANT] > Prepare and verify a staged or production deployment with rollback and smoke checks.
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: Ship verified work with explicit deployment steps, smoke checks, and rollback criteria.
release_confidence is high, or medium with documented risk; low means NO-GO unless the release owner overrides in writing.publish-notes.retro-learn.slug, release_confidence, release verdict (GO/NO-GO/ROLLED-BACK), smoke check results, rollback path, outcome report, next workflow.md# Deployment Report: [Name] ## Release Verdict GO | NO-GO | ROLLED-BACK ## Release ## Environments ## Commands ## Smoke Checks | Check | Result | Evidence | | --- | --- | --- | | [check] | [PASS/FAIL/BLOCKED] | [evidence] | ## Rollback ## Outcome Report feature_status: implemented | blocked requirement_trace: BRD-OBJ-* -> REQ-* -> AC-* -> SRS-* -> evidence completed_evidence: []; missing_evidence: []; decision_needed: []; recommended_next_workflow: publish-notes | retro-learn ## Next Workflow publish-notes | retro-learn ## Cost Report Call `get_session_cost(workflow="deploy-release")` before final handoff.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-18 | pass→pass | 19,499 | 17,016 | -13% | 1 | 1 | 0% | 3,469 | 3,499 | +1% | 0 | 0 | — |
case-17 | pass→fail | 7,832 | 12,034 | +54% | 1 | 1 | 0% | 1,437 | 3,013 | +110% | 0 | 0 | — |
case-01 | fail→fail | 16,189 | 12,759 | -21% | 1 | 1 | 0% | 2,813 | 3,200 | +14% | 0 | 0 | — |
case-02 | fail→fail | 15,205 | 14,066 | -7% | 1 | 1 | 0% | 2,936 | 3,357 | +14% | 0 | 0 | — |
case-03 | fail→fail | 15,087 | 5,770 | -62% | 1 | 1 | 0% | 2,741 | 1,641 | -40% | 0 | 0 | — |
case-04 | pass→pass | 12,079 | 9,936 | -18% | 1 | 1 | 0% | 2,066 | 2,503 | +21% | 0 | 0 | — |
case-05 | fail→pass | 19,490 | 8,399 | -57% | 1 | 1 | 0% | 1,004 | 2,219 | +121% | 0 | 0 | — |
case-06 | fail→pass | 3,327 | 6,025 | +81% | 1 | 1 | 0% | 675 | 1,655 | +145% | 0 | 0 | — |
case-07 | fail→fail | 17,456 | 17,080 | -2% | 1 | 1 | 0% | 3,070 | 3,374 | +10% | 0 | 0 | — |
case-08 | pass→pass | 13,207 | 9,532 | -28% | 1 | 1 | 0% | 2,410 | 2,725 | +13% | 0 | 0 | — |
case-09 | pass→pass | 5,578 | 7,166 | +28% | 1 | 1 | 0% | 1,017 | 2,079 | +104% | 0 | 0 | — |
case-10 | pass→pass | 13,189 | 9,218 | -30% | 1 | 1 | 0% | 2,170 | 2,380 | +10% | 0 | 0 | — |
case-11 | pass→pass | 10,790 | 11,924 | +11% | 1 | 1 | 0% | 1,883 | 2,843 | +51% | 0 | 0 | — |
case-12 | pass→pass | 10,469 | 8,856 | -15% | 1 | 1 | 0% | 1,743 | 2,280 | +31% | 0 | 0 | — |
case-13 | fail→pass | 19,653 | 9,226 | -53% | 1 | 1 | 0% | 2,996 | 2,451 | -18% | 0 | 0 | — |
case-14 | pass→pass | 11,680 | 12,518 | +7% | 1 | 1 | 0% | 2,034 | 2,797 | +38% | 0 | 0 | — |
case-15 | pass→pass | 9,392 | 8,164 | -13% | 1 | 1 | 0% | 1,653 | 1,926 | +17% | 0 | 0 | — |
case-16 | fail→pass | 11,111 | 11,890 | +7% | 1 | 1 | 0% | 1,961 | 2,228 | +14% | 0 | 0 | — |
case-19 | pass→pass | 11,999 | 6,606 | -45% | 1 | 1 | 0% | 2,033 | 1,844 | -9% | 0 | 0 | — |
case-20 | fail→pass | 2,264 | 3,777 | +67% | 1 | 1 | 0% | 431 | 1,335 | +210% | 0 | 0 | — |
case-21 | pass→pass | 4,394 | 7,900 | +80% | 1 | 1 | 0% | 864 | 2,172 | +151% | 0 | 0 | — |
case-22 | pass→pass | 11,990 | 8,903 | -26% | 1 | 1 | 0% | 1,941 | 2,226 | +15% | 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 +18 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
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.