Generate with AI

If you already have a GitLab CI pipeline, an AI coding assistant can produce the equivalent Mélodium pipeline in minutes, without you having to learn the language first.

What You Need

Your existing .gitlab-ci.yml file, the agent will read it directly.
An AI coding assistant running locally in your project (Claude Code, Cursor, Zed, or similar).
The Mélodium skill installed in your AI tool. See Install the Mélodium Skill.

Step 1: Make Sure the Migration Reference Is Included

The general Mélodium skill covers the language and project layout. For a GitLab CI migration, the AI also needs skills/melodium/references/gitlab-migration.md, which has the exact treatment patterns for simpleStep, artifact streaming, stage ordering, allow_failure, when: always, and status reporting.

With Claude Code, this comes included automatically once the skill is installed under ~/.claude/skills/melodium, it loads its reference files on demand. With Cursor or Zed, make sure your rule file includes it:


# Cursor
cat skills/melodium/SKILL.md \
    skills/melodium/references/gitlab-migration.md \
    skills/melodium/references/projects.md \
    > .cursor/rules/melodium.md
 
# Zed
cat skills/melodium/SKILL.md \
    skills/melodium/references/gitlab-migration.md \
    skills/melodium/references/projects.md \
    > .rules

Step 2: Ask for the Migration

Your AI agent is already running inside your project and can read your pipeline file directly, so a simple prompt is enough:


Read .gitlab-ci.yml and migrate it to Mélodium.
Generate a complete project under .melodium-ci/ with Compo.toml and .mel files.
Use simpleStep for container jobs, localStep for self-hosted jobs.
Report status back to GitLab using the token and project parameters.

If your pipeline uses include: to pull in local template files, mention their location:


Also read the templates in ci/templates/ that are included by the pipeline.

The AI will produce a ready-to-use Mélodium project: a Compo.toml declaring the right dependencies, one .mel file per pipeline or logical group of jobs, stage ordering expressed as sequential wiring between treatments, parallel instances for parallel: jobs, direct byte-stream artifact passing with no intermediate storage, and GitLab commit status reporting.

Step 3: Review and Adjust

Read through the generated code before running it. The cpu, memory, and storage parameters in simpleStep have generic defaults, adjust them to your actual build requirements. Check that gitlab_token, gitlab_project_id, gitlab_sha, gitlab_ref, and gitlab_pipeline_id are wired to the right entrypoint parameters. The AI merges before_script / after_script into the commands list, but unlike GitLab CI they then share the same shell environment, so verify that matches your intent. Check that filterBlock wiring correctly captures the logic of your original rules: conditions, and that the out_file / in_file names in simpleStep / simpleStepWithInput match the paths your scripts actually write and read.

Concept Reference

If you want to understand what the AI produced, or adjust it yourself, this table shows how GitLab CI concepts map to Mélodium:

GitLab CI	Mélodium
Pipeline (`.gitlab-ci.yml`)	`.mel` treatment
Job	Treatment with `simpleStep` or `localStep`
`image:`	`image` parameter of `simpleStep`
`script:` / `before_script:` / `after_script:`	`commands` list in `simpleStep`
Stage ordering	Sequential wiring between treatments
`needs:` / `dependencies:`	Sequential wiring; artifacts via `data` stream
`artifacts:`	`out_file` + `data` stream; `simpleStepWithInput` to consume
`rules:` / `only:` / `except:`	`filterBlock<void>()` on the trigger
`when: always`	`one<void>()` fan-in of success and failure outputs
`allow_failure: true`	Handle `error` output instead of stopping the chain
`parallel:`	Multiple parallel treatment instances with `one<void>()`
`interruptible: true`	`simpleStepTerminable` variant
Status reporting	`postGitlabState` / `setServiceState`

Full API documentation is at doc.melodium.tech .

Going Further

The generated code is a good starting point, and can be extended with any Mélodium element. For distribution across multiple machines and more advanced parallelisation, see Simple CI/CD Implementation and Advanced CI/CD Implementation.

Reusable Workflows CI/CD Components