Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate platform-specific CI/CD pipeline configurations for GitHub Actions, GitLab CI, Jenkins, and Azure DevOps with build, test, and deploy stages.
.claude/skills/williamzujkowski-ci-cd-pipeline-generator/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 9 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 85% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 116% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 167% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 130% | 0% |
Trigger conditions:
Use this skill when you need a complete, platform-optimized CI/CD pipeline configuration file with build, test, security, and deploy stages.
Before execution, verify:
NOW_ET = 2025-10-26T01:33:56-04:00 (NIST/time.gov semantics, America/New_York)platform is one of: github-actions, gitlab-ci, jenkins, azure-devopstech_stack contains valid language identifiersstages object specifies at minimum: build and test configurationsNOW_ET; verify documentation links currentAbort conditions:
Token budget: ≤2k tokens
Scope: Generate basic CI/CD pipeline for common tech stacks with standard build, test, and deploy stages.
Steps:
Decision point: If requirements include multi-environment deployments, advanced security gates, or custom integrations → escalate to T2.
Token budget: ≤6k tokens
Scope: Multi-environment pipelines with advanced security, approval gates, and performance optimization.
Steps:
Sources cited (accessed 2025-10-26T01:33:56-04:00):
Token budget: ≤12k tokens
Scope: Enterprise-grade pipelines with compliance automation, custom plugins, and advanced orchestration.
Steps:
Additional sources (accessed 2025-10-26T01:33:56-04:00):
Platform selection guidance:
Stage configuration:
Escalation conditions:
Abort conditions:
Required outputs:
json{ "pipeline_config": { "type": "object", "properties": { "platform": "string (github-actions|gitlab-ci|jenkins|azure-devops)", "file_path": "string (.github/workflows/ci.yml, .gitlab-ci.yml, Jenkinsfile)", "content": "string (complete pipeline configuration)", "language": "string (yaml|groovy)" } }, "setup_guide": { "type": "markdown", "properties": { "secrets_required": ["array of secret names and descriptions"], "variables_required": ["array of variable names and defaults"], "setup_steps": "string (step-by-step setup instructions)" } } }
Quality guarantees:
Example: GitHub Actions pipeline for Node.js application
yaml# .github/workflows/ci.yml name: CI Pipeline on: push: branches: [main, develop] pull_request: branches: [main] jobs: build-and-test: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: actions/setup-node@v4 with: node-version: '20' cache: 'npm' - run: npm ci - run: npm run lint - run: npm test -- --coverage - run: npm run build security-scan: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: aquasecurity/trivy-action@master with: scan-type: 'fs' severity: 'CRITICAL,HIGH'
Token budgets:
Safety checks:
Auditability:
Determinism:
Official Documentation (accessed 2025-10-26T01:33:56-04:00):
Best Practices (accessed 2025-10-26T01:33:56-04:00):
Templates (in repository /resources/):
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,124 | 14,449 | +19% | 1 | 1 | 0% | 3,213 | 5,953 | +85% | 0 | 0 | — |
case-02 | pass→pass | 16,397 | 19,376 | +18% | 1 | 1 | 0% | 3,830 | 6,874 | +79% | 0 | 0 | — |
case-03 | fail→pass | 16,240 | 16,331 | +1% | 1 | 1 | 0% | 4,106 | 6,376 | +55% | 0 | 0 | — |
case-04 | fail→pass | 10,455 | 11,356 | +9% | 1 | 1 | 0% | 2,493 | 5,375 | +116% | 0 | 0 | — |
case-05 | fail→pass | 8,725 | 10,572 | +21% | 1 | 1 | 0% | 1,979 | 5,279 | +167% | 0 | 0 | — |
case-06 | pass→pass | 16,289 | 15,277 | -6% | 1 | 1 | 0% | 2,847 | 6,195 | +118% | 0 | 0 | — |
case-07 | pass→pass | 8,559 | 13,322 | +56% | 1 | 1 | 0% | 1,985 | 5,830 | +194% | 0 | 0 | — |
case-12 | fail→fail | 15,446 | 14,955 | -3% | 1 | 1 | 0% | 3,499 | 6,213 | +78% | 0 | 0 | — |
case-08 | pass→pass | 11,991 | 10,773 | -10% | 1 | 1 | 0% | 2,501 | 5,094 | +104% | 0 | 0 | — |
case-09 | pass→pass | 13,770 | 12,742 | -7% | 1 | 1 | 0% | 2,768 | 5,652 | +104% | 0 | 0 | — |
case-10 | pass→pass | 10,469 | 17,056 | +63% | 1 | 1 | 0% | 2,356 | 6,852 | +191% | 0 | 0 | — |
case-11 | fail→fail | 7,127 | 6,829 | -4% | 1 | 1 | 0% | 1,500 | 3,982 | +165% | 0 | 0 | — |
case-13 | fail→fail | 15,517 | 14,133 | -9% | 1 | 1 | 0% | 3,357 | 5,968 | +78% | 0 | 0 | — |
case-14 | fail→pass | 9,107 | 7,207 | -21% | 1 | 1 | 0% | 1,817 | 4,176 | +130% | 0 | 0 | — |
case-15 | pass→pass | 10,525 | 10,898 | +4% | 1 | 1 | 0% | 2,354 | 4,922 | +109% | 0 | 0 | — |
case-16 | pass→pass | 12,861 | 17,060 | +33% | 1 | 1 | 0% | 2,947 | 6,870 | +133% | 0 | 0 | — |
case-17 | fail→pass | 4,528 | 11,042 | +144% | 1 | 1 | 0% | 924 | 5,220 | +465% | 0 | 0 | — |
case-18 | fail→pass | 8,347 | 2,897 | -65% | 1 | 1 | 0% | 1,935 | 3,191 | +65% | 0 | 0 | — |
case-19 | fail→pass | 7,583 | 5,707 | -25% | 1 | 1 | 0% | 1,459 | 3,683 | +152% | 0 | 0 | — |
case-20 | pass→pass | 8,957 | 14,564 | +63% | 1 | 1 | 0% | 1,836 | 5,947 | +224% | 0 | 0 | — |
case-21 | pass→pass | 9,723 | 10,056 | +3% | 1 | 1 | 0% | 2,119 | 4,973 | +135% | 0 | 0 | — |
case-22 | pass→pass | 8,885 | 6,102 | -31% | 1 | 1 | 0% | 1,817 | 4,021 | +121% | 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.