migration · datawithbaraa — Claude Code skill for migration planning
A Claude Code skill that plans the move from legacy jobs and tables to a new platform. It lays out migration scenarios, acceptance criteria, a parallel run, and rollback.
MIT ★ 106 updated 2026-11-06
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills
/plugin install data-engineering@data-with-baraaWhat migration does
The skill examines a legacy estate of jobs and tables, then produces a migration plan. Its input can be a folder, an inventory, or documentation. For each job, it describes inputs, logic, and outputs, maps lineage, assesses risk and value, and flags jobs that are no longer active.
The plan identifies what to keep, compares target platforms against requirements, and assigns a migration approach to each job. It groups work into waves and scenarios, sets acceptance thresholds, and covers the parallel run, history load, cutover, rollback, and retirement of old jobs. Open decisions are marked for the data engineer. The skill does not move data or jobs; it only plans the migration.
What it helps with
- inventory legacy jobs and tables
- assess the risk and value of each job
- compare target platforms against requirements
- plan migration waves, parallel runs, and rollback
Example prompts for the agent
- Create a migration plan for the files in
legacy/etl. - Review this job inventory and propose a migration order.
- Build migration scenarios from this documentation and define acceptance criteria.
How to install migration
1Plugin marketplace
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills/plugin install data-engineering@data-with-baraaThis installs the whole data-engineering plugin with all its skills
2Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill migration -a claude-code3Manually: put the files in place
~/.claude/skills/migration/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/migration/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill migration -a codex2Manually: put the files in place
.agents/skills/migration/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill migration -a cursor2Manually: put the files in place
.cursor/skills/migration/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install DataWithBaraa/claude-code-data-engineering-skills skills/migration2Manually: put the files in place
.github/skills/migration/SKILL.md1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill migration -a gemini-cli2Platform CLI
gemini skills install https://github.com/DataWithBaraa/claude-code-data-engineering-skills --path skills/migrationManually: put the files in place
.devin/skills/migration/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about migration
How do I install migration in Claude Code?
Add the marketplace with /plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills, then install the plugin with /plugin install data-engineering@data-with-baraa.
What does the migration skill do?
It reviews legacy jobs and tables and produces a plan for moving them to a new platform. The plan covers scenarios, acceptance criteria, a parallel run, and rollback; the skill does not perform the migration.
What can I provide as input to migration?
A folder containing the legacy estate, its inventory, or its documentation. The plan also draws on knowledge of the target platform.
Source text
SKILL.md · MIT
--- name: migration description: Use when an old estate of jobs and tables has to move to a new platform, to inventory it, rate it, and write the migration plan with scenarios, acceptance numbers, the parallel run and the rollback. argument-hint: "[old estate]" --- # Migration The job: from the old estate to a migration plan with scenarios, acceptance numbers, a parallel run and a rollback. It plans, it migrates nothing. Input: the folder, the inventory or the documentation of the old estate. ## Steps 1. Inventory the old estate: jobs, tables, schedules, owners, consumers. 2. Explain every job in three plain lines: inputs, logic, output. 3. Draw the lineage of the old estate. 4. Rate each job: risk, size, value, dead or alive. 5. Propose the cut list, with the reason for each. 6. Gather the requirements for the new platform. 7. Compare at least two target platforms on the requirements. 8. Propose the migration type per job: lift and shift, re-platform, re-engineer. 9. Design the target: where each kept job lands. 10. Map old to new, one row per old output. 11. Propose the order, in waves, the smallest proven one first. 12. Three scenarios: best, expected, worst, with effort and risk. 13. Define the acceptance numbers, per output, with the tolerance. 14. Plan the parallel run: old and new side by side, every output compared, for how long, before the cutover. 15. Plan the history load, the cutover, the rollback and the decommission of the old jobs. 16. Write the migration plan, decisions marked open for the data engineer. ## Output One migration plan: the inventory and its ratings, the cut list, the target, the waves, the scenarios, the acceptance numbers, the parallel run, the cutover and the rollback, with the open decisions marked. ## Reads - the old estate, the knowledge of the new platform ## Writes - the migration plan ## Never - Never migrates anything: it plans.
© Data With Baraa · MIT · DataWithBaraa/claude-code-data-engineering-skills
Similar skills
All skills for Data and databases →migration by other authors comes first.