Guide · Agent skill
How to use the Oracle-to-PostgreSQL Master Migration Plan agent skill
Updated · written with AI from the project's own documentation and checked against our catalogue data
This agent skill tells an AI coding agent to scan a .NET solution, decide which projects contain Oracle code or settings, and save a structured Markdown migration plan to your repository. It is for engineering leads and developers who are starting a multi-project Oracle-to-PostgreSQL migration and need a project inventory first. After this guide you will know what the skill does, how to install it, how to trigger it, and what to check before and after it runs.
Oracle-to-PostgreSQL Master Migration Plangithub/awesome-copilot · MIT Download the skill Quick start
- 1Confirm your solution file. Make sure a .sln or .slnx file is in the workspace root. The skill asks you to choose if there are several.
- 2Install the skill. Unzip the downloaded ZIP into ~/.claude/skills/ or a project's .claude/skills/ folder, or upload it under Settings → Capabilities → Skills in the Claude apps.
- 3Make a natural request. Ask the agent to create a master migration plan or to find which projects contain Oracle dependencies.
- 4Review the classifications. Read the classified project list and change any MIGRATE, SKIP, ALREADY_MIGRATED or TEST_PROJECT labels that look wrong.
- 5Adjust the migration order. Check that shared libraries come before the projects that depend on them, and edit the order if needed.
- 6Check the plan file. Open .github/oracle-to-postgres-migration/Reports/MasterMigrationPlan.md and confirm the counts and inventory table match your solution.
What is an agent skill and what does this one do?
An agent skill is a folder containing a SKILL.md file with instructions that an AI agent loads when a request matches the skill's description. This skill is a single file, SKILL.md, and it is designed for .NET solutions that use Oracle databases and are planned to move to PostgreSQL.
When triggered, the agent finds the .sln or .slnx file in the workspace root, lists the .csproj projects it references, and classifies each one. Non-test projects are checked for Oracle indicators: Oracle.ManagedDataAccess or Oracle.EntityFrameworkCore NuGet references in .csproj or packages.config, Oracle connection strings in appsettings.json, web.config or app.config, and code such as OracleConnection, OracleCommand or OracleDataReader.
- MIGRATE: has Oracle interactions that need conversion
- SKIP: no Oracle indicators, such as UI-only or shared utility projects
- ALREADY_MIGRATED: a -postgres or .Postgres duplicate exists and appears processed
- TEST_PROJECT: handled by the testing workflow
How do you install the skill?
Option 1: download the ZIP from this page and unzip it into your personal skills folder at ~/.claude/skills/, or into a project's .claude/skills/ folder if you want the skill available only in that repository. The skill folder should contain SKILL.md.
Option 2: in the Claude apps, upload the ZIP under Settings → Capabilities → Skills.
How do you trigger the skill with a natural request?
The agent loads the skill when your request matches its description. Phrases that fit the description include starting a multi-project Oracle-to-PostgreSQL migration, creating a migration inventory, or assessing which .NET projects contain Oracle dependencies. You do not need to name the skill, but naming it is a reliable way to make sure it runs.
- Create a master migration plan for this solution to move from Oracle to PostgreSQL.
- Which projects in this .NET solution contain Oracle dependencies?
- Make a migration inventory for our Oracle to PostgreSQL move.
What happens during a run?
The skill follows four steps. The agent discovers projects in the solution, classifies each one, asks you to confirm the classifications and migration order, and then writes the plan file. You can change any classification or ordering before the file is finalized.
The plan is saved to .github/oracle-to-postgres-migration/Reports/MasterMigrationPlan.md. It contains a solution summary with counts, a project inventory table, and a migration order. The order places shared or foundational libraries before the projects that depend on them. If you use an external tool such as ora2pg, the template notes that the schema and DDL phase can be skipped when PostgreSQL DDL artifacts already exist.
.github/oracle-to-postgres-migration/Reports/MasterMigrationPlan.mdWhat do you need before running it?
You need a .NET solution file (.sln or .slnx) in the workspace. The agent needs read and write access to the repository so it can save the plan under .github/oracle-to-postgres-migration/. If several solution files exist, the agent will ask which one to use.
The skill runs no scripts and makes no network calls, according to its listed requirements. It only reads project files and writes the Markdown plan.
- A .NET solution file (.sln or .slnx) in the workspace
- Read and write access to the repository
- Runs scripts: no
- Uses network: no
What should you check and watch out for?
Review the classification list before confirming. The skill decides from file contents and names, so a project that uses Oracle indirectly may be marked SKIP, and a utility that only mentions Oracle in a comment may be marked MIGRATE. Correct these during the confirmation step.
The skill writes files into your repository. If the decision to migrate is still open, wait, because the plan file adds clutter. It is also not suited to a single small project, where a manual check is faster, or to non-.NET codebases.
- Check every classification, especially projects marked SKIP
- Commit or review the generated file like any other change
- Do not use it for codebases that are not .NET
What people use it for
- Listing every project in a large .NET solution and marking which ones need Oracle-to-PostgreSQL work
- Finding which projects reference Oracle.ManagedDataAccess or Oracle.EntityFrameworkCore packages
- Locating Oracle connection strings in appsuttings.json, web.config or app.config files across projects
- Producing a migration order for shared data access libraries and their dependent projects
- Creating a structured plan file that other migration tools or skills can read
Frequently asked questions
Is the Oracle-to-PostgreSQL master migration plan skill free?
The skill is published under the MIT licence in the github/awesome-copilot repository. The source says nothing about pricing, so check the page and your Claude plan for any costs of the apps themselves.
How do I install an agent skill?
Download the ZIP, then unzip it into ~/.claude/skills/ for personal use or a project's .claude/skills/ folder for one repository. You can also upload the ZIP in the Claude apps under Settings → Capabilities → Skills.
What does the skill need to run?
It needs a .NET solution file with a .sln or .slnx extension in the workspace, and read and write access to the repository so it can save the plan file. It runs no scripts and uses no network.
Does this skill work with non-.NET projects?
No. It only looks for .sln and .csproj structures and Oracle .NET packages, so Java, Python or other codebases are outside its scope.
Can I use this instead of checking projects by hand?
For a large solution with many projects, the skill gives you a structured inventory faster. For a single small project, a manual check is usually quicker, and the skill is not designed for that case.
What if the skill classifies a project incorrectly?
The agent presents the list and asks you to confirm it before writing the file, so you can change any classification then. Review projects marked SKIP especially closely, since indirect Oracle use may be missed.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
Use this skill if you are starting a multi-project Oracle-to-PostgreSQL migration in a .NET solution and need a project inventory with a dependency-aware order. Skip it for single small projects, non-.NET codebases, or teams that have not yet decided to migrate, since it writes plan files into the repository.
Download the skill