mgiovani/ai-arsenal / skills/ci-generate
ci-generate
VerifiedGenerate a production-ready CI/CD pipeline config (GitHub Actions, GitLab CI, CircleCI, or Jenkins) by discovering the project's actual stack, test/build commands, and dependencies. Use when setting up CI for a new project, adding a missing workflow file, or asked to create/generate a pipeline, workflow, or `.gitlab-ci.yml`/`Jenkinsfile`. Not for writing a Dockerfile itself (see docker-init), this only wires CI stages around one. Not for running existing CI checks locally (use ci-local), this skill only authors the pipeline file itself.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.9 KB |
| evals/evals.json | config | 3.3 KB |
| evals/trigger-eval.json | config | 2.3 KB |
| references/platform-patterns.md | markdown | 19.4 KB |
evals/trigger-eval.json
View on GitHub[
{"query": "we don't have any CI set up yet, can you generate a GitHub Actions workflow for this repo", "should_trigger": true},
{"query": "set up a .gitlab-ci.yml for our python project", "should_trigger": true},
{"query": "ci-generate circleci --deploy vercel", "should_trigger": true},
{"query": "we need a Jenkinsfile for this repo, can you create one", "should_trigger": true},
{"query": "add a security scan and deploy stage to our existing github actions workflow", "should_trigger": true},
{"query": "our monorepo needs a proper CI pipeline with matrix testing across node versions", "should_trigger": true},
{"query": "generate a pipeline that lints, tests, builds and deploys to aws", "should_trigger": true},
{"query": "can you wire up .circleci/config.yml with the actual test command from our package.json", "should_trigger": true},
{"query": "we're missing a workflow file, github actions isn't running anything on PRs", "should_trigger": true},
{"query": "create a ci/cd config for this project, auto-detect the stack please", "should_trigger": true},
{"query": "write a Dockerfile for this Node app so we can containerize it", "should_trigger": false},
{"query": "implement the new checkout flow feature end to end", "should_trigger": false},
{"query": "our GitHub Actions build is failing, can you debug why the test job errors out", "should_trigger": false},
{"query": "run a security review of the whole codebase before we ship", "should_trigger": false},
{"query": "write tests for the payment retry logic, coverage is too low", "should_trigger": false},
{"query": "create a PR for these changes with a conventional commit message", "should_trigger": false},
{"query": "update the README to reflect the new deployment process", "should_trigger": false},
{"query": "help me cut a release and bump the version with a changelog", "should_trigger": false},
{"query": "refactor the build scripts in package.json to remove duplication", "should_trigger": false},
{"query": "inject the Next.js framework docs into our CLAUDE.md", "should_trigger": false},
{"query": "our CI quota ran out for the month, run the GitHub Actions checks locally on my machine instead", "should_trigger": false},
{"query": "verify this branch passes the same lint/test/build steps CI would, without pushing", "should_trigger": false}
]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |