Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate pragmatic CI/CD pipelines from detected project stack signals — fast baseline generation, repeatable checks, environment-aware deployment stages. Use when setting up CI for a new project, refactoring existing pipelines, or standardizing deployment workflows across multiple repos.
.claude/skills/alirezarezvani-ci-cd-pipeline-builder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -67% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -58% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 1% | 0% |
Tier: POWERFUL Category: Engineering Domain: DevOps / Automation
Use this skill to generate pragmatic CI/CD pipelines from detected project stack signals, not guesswork. It focuses on fast baseline generation, repeatable checks, and environment-aware deployment stages.
lint, test, build, deploy)bashpython3 scripts/stack_detector.py --repo . --format text python3 scripts/stack_detector.py --repo . --format json > detected-stack.json
Supports input via stdin or --input file for offline analysis payloads.
bashpython3 scripts/pipeline_generator.py \ --input detected-stack.json \ --platform github \ --output .github/workflows/ci.yml \ --format text
Or end-to-end from repo directly:
bashpython3 scripts/pipeline_generator.py --repo . --platform gitlab --output .gitlab-ci.yml
test, lint, build).lint/test/build).python3 scripts/stack_detector.py --help--inputpython3 scripts/pipeline_generator.py --help--output| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 1,371 | 4,157 | +203% | 1 | 1 | 0% | 192 | 872 | +354% | 0 | 0 | — |
case-02 | fail→fail | 11,060 | 4,743 | -57% | 1 | 1 | 0% | 2,211 | 949 | -57% | 0 | 0 | — |
case-03 | fail→pass | 14,441 | 4,482 | -69% | 1 | 1 | 0% | 2,546 | 1,301 | -49% | 0 | 0 | — |
case-04 | fail→pass | 20,057 | 2,817 | -86% | 1 | 1 | 0% | 3,612 | 1,200 | -67% | 0 | 0 | — |
case-05 | fail→pass | 12,215 | 2,058 | -83% | 1 | 1 | 0% | 2,357 | 1,062 | -55% | 0 | 0 | — |
case-06 | fail→pass | 15,860 | 2,046 | -87% | 1 | 1 | 0% | 2,576 | 1,075 | -58% | 0 | 0 | — |
case-07 | pass→fail | 15,661 | 9,408 | -40% | 1 | 1 | 0% | 2,365 | 2,461 | +4% | 0 | 0 | — |
case-08 | fail→pass | 13,917 | 12,795 | -8% | 1 | 1 | 0% | 2,393 | 2,419 | +1% | 0 | 0 | — |
case-09 | pass→pass | 14,880 | 7,012 | -53% | 1 | 1 | 0% | 2,087 | 1,987 | -5% | 0 | 0 | — |
case-10 | pass→pass | 14,801 | 9,005 | -39% | 1 | 1 | 0% | 2,419 | 2,315 | -4% | 0 | 0 | — |
case-11 | pass→pass | 16,873 | 12,528 | -26% | 1 | 1 | 0% | 2,302 | 2,780 | +21% | 0 | 0 | — |
case-12 | pass→pass | 11,313 | 7,323 | -35% | 1 | 1 | 0% | 1,807 | 1,961 | +9% | 0 | 0 | — |
case-13 | pass→pass | 22,462 | 15,904 | -29% | 1 | 1 | 0% | 2,890 | 3,582 | +24% | 0 | 0 | — |
case-14 | fail→pass | 11,390 | 9,651 | -15% | 1 | 1 | 0% | 2,255 | 2,698 | +20% | 0 | 0 | — |
case-15 | fail→pass | 9,935 | 2,589 | -74% | 1 | 1 | 0% | 1,792 | 1,150 | -36% | 0 | 0 | — |
case-16 | fail→pass | 10,148 | 6,291 | -38% | 1 | 1 | 0% | 1,760 | 1,638 | -7% | 0 | 0 | — |
case-17 | pass→pass | 6,743 | 1,731 | -74% | 1 | 1 | 0% | 1,229 | 940 | -24% | 0 | 0 | — |
case-18 | fail→fail | 12,532 | 15,596 | +24% | 1 | 1 | 0% | 2,413 | 3,213 | +33% | 0 | 0 | — |
case-19 | fail→fail | 11,268 | 5,142 | -54% | 1 | 1 | 0% | 2,025 | 1,775 | -12% | 0 | 0 | — |
case-20 | fail→fail | 17,019 | 17,300 | +2% | 1 | 1 | 0% | 3,790 | 4,621 | +22% | 0 | 0 | — |
case-21 | fail→fail | 12,189 | 8,191 | -33% | 1 | 1 | 0% | 1,949 | 1,938 | -1% | 0 | 0 | — |
case-22 | fail→pass | 13,261 | 9,833 | -26% | 1 | 1 | 0% | 2,022 | 2,018 | -0% | 0 | 0 | — |
case-23 | fail→pass | 13,356 | 1,953 | -85% | 1 | 1 | 0% | 1,901 | 1,014 | -47% | 0 | 0 | — |
case-24 | fail→pass | 12,388 | 4,898 | -60% | 1 | 1 | 0% | 2,115 | 1,542 | -27% | 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. 24 cases were attempted, and 22 counted toward the lift figure. The other 2 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 +42 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.