Install any skill in seconds. Free to start, no credit card required.
Get Started Free →DevOps for CI/CD, containers, Kubernetes, and Terraform. Use when building pipelines, containerizing apps, managing clusters, provisioning cloud infra, deploying with blue- green/canary, or handling infrastructure incidents.
.claude/skills/borghei-senior-devops/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 292% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -53% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 142% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -14% | 0% |
The agent generates CI/CD pipelines, scaffolds Terraform infrastructure, and manages deployments with strategy selection, health checks, and rollback support.
Before generating pipelines or infra, confirm these inputs. If any is unknown or vague, ASK — do not assume:
terraform_scaffolder)Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
| Tool | Purpose | Command | |------|---------|---------| | pipeline_generator.py | Analyze a project and generate a CI/CD pipeline config (GitHub Actions, GitLab CI, Jenkins, CircleCI) | python scripts/pipeline_generator.py <project-path> --json | | terraform_scaffolder.py | Scaffold a Terraform module structure with state config | python scripts/terraform_scaffolder.py <target-path> --json | | deployment_manager.py | Produce a deployment plan with health checks and rollback | python scripts/deployment_manager.py <target-path> --json |
All tools support --verbose/-v, --json for machine-readable output, and --output/-o for file writing.
Load the reference that matches the task — keep this file lean and pull detail on demand:
| Skill | Integration | |-------|-------------| | senior-secops | Security scanning in CI/CD, container image scanning, compliance checks | | senior-architect | Infrastructure design decisions, service topology | | senior-backend | Application containerization, health endpoints, config management | | code-reviewer | Terraform plan review, pipeline config review | | incident-commander | Incident escalation, postmortem, rollback procedures |
Last Updated: June 2026 Version: 2.2.0
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | fail→pass | 20,419 | 26,391 | +29% | 1 | 1 | 0% | 1,635 | 6,414 | +292% | 0 | 0 | — |
case-12 | fail→fail | 20,376 | 17,907 | -12% | 1 | 1 | 0% | 3,482 | 4,224 | +21% | 0 | 0 | — |
case-18 | pass→pass | 4,930 | 7,865 | +60% | 1 | 1 | 0% | 898 | 2,369 | +164% | 0 | 0 | — |
case-01 | fail→pass | 22,722 | 5,126 | -77% | 1 | 1 | 0% | 4,007 | 1,892 | -53% | 0 | 0 | — |
case-02 | fail→fail | 19,951 | 30,073 | +51% | 1 | 1 | 0% | 3,858 | 7,047 | +83% | 0 | 0 | — |
case-03 | fail→fail | 22,627 | 31,800 | +41% | 1 | 1 | 0% | 4,141 | 7,071 | +71% | 0 | 0 | — |
case-04 | fail→pass | 10,389 | 19,069 | +84% | 1 | 1 | 0% | 1,964 | 4,753 | +142% | 0 | 0 | — |
case-05 | fail→pass | 18,307 | 5,513 | -70% | 1 | 1 | 0% | 3,262 | 1,972 | -40% | 0 | 0 | — |
case-06 | fail→pass | 14,219 | 7,361 | -48% | 1 | 1 | 0% | 2,585 | 2,224 | -14% | 0 | 0 | — |
case-07 | fail→pass | 12,231 | 20,967 | +71% | 1 | 1 | 0% | 2,359 | 5,486 | +133% | 0 | 0 | — |
case-08 | fail→fail | 17,346 | 24,585 | +42% | 1 | 1 | 0% | 3,423 | 5,716 | +67% | 0 | 0 | — |
case-09 | fail→pass | 16,896 | 26,203 | +55% | 1 | 1 | 0% | 3,290 | 6,122 | +86% | 0 | 0 | — |
case-10 | fail→pass | 16,100 | 6,316 | -61% | 1 | 1 | 0% | 2,622 | 2,030 | -23% | 0 | 0 | — |
case-13 | fail→pass | 19,194 | 21,204 | +10% | 1 | 1 | 0% | 4,208 | 5,576 | +33% | 0 | 0 | — |
case-14 | fail→fail | 14,374 | 19,782 | +38% | 1 | 1 | 0% | 2,465 | 4,321 | +75% | 0 | 0 | — |
case-15 | fail→pass | 9,058 | 19,392 | +114% | 1 | 1 | 0% | 1,471 | 4,383 | +198% | 0 | 0 | — |
case-16 | fail→pass | 21,087 | 7,948 | -62% | 1 | 1 | 0% | 3,963 | 2,355 | -41% | 0 | 0 | — |
case-17 | fail→pass | 15,005 | 23,219 | +55% | 1 | 1 | 0% | 2,840 | 5,763 | +103% | 0 | 0 | — |
case-19 | pass→pass | 4,016 | 5,915 | +47% | 1 | 1 | 0% | 744 | 2,031 | +173% | 0 | 0 | — |
case-20 | pass→pass | 3,713 | 9,176 | +147% | 1 | 1 | 0% | 718 | 2,731 | +280% | 0 | 0 | — |
case-21 | pass→pass | 4,729 | 9,888 | +109% | 1 | 1 | 0% | 839 | 2,890 | +244% | 0 | 0 | — |
case-22 | fail→fail | 22,211 | 29,846 | +34% | 1 | 1 | 0% | 3,479 | 5,934 | +71% | 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 +55 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.