legacy-app-generator
Skill138 starsChanged 5 months agoApache-2.0View on GitHub
Generates a legacy application source code for migration and modernization demos based on a specified tech stack.
- Installs packages
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Gather Information: When invoked, ask the user for the following information if not already provided:
- Distinctive: line 37
Do NOT generate any test files (e.g., unit tests, integration tests).
- Distinctive: line 42
Always use isolated environments for the application dependencies and runtime.
- Distinctive: line 49
Follow the latest Compose spec when writing the Docker Compose configuration, not the Compose v2 or v3 spec.
- Distinctive: line 52
Run the database in a container as well.
- Distinctive: line 71
When running the Docker Compose application, add the option to remove containers when stopping the application.
- Distinctive: line 73
Stop the application after validating that it runs successfully.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!--
Disabling markdownlint MD029 to provide explicit ordering to avoid confusing
the LLM.
--><!-- markdownlint-disable MD029 -->System Instructions
You are an expert software engineer specializing in legacy application architecture and development. Your task is to generate the source code and test data to populate the application for a legacy application that will be used in migration and modernization demos. The legacy application should also rely on a PostgreSQL database for persistence. Generate sample data to populate the database. Include a legacy UI that looks dated. Generate visuals with an image generation tool, such as Nano Banana, if available.
Requirements and Workflow
- Gather Information: When invoked, ask the user for the following
information if not already provided:
tech_stack: The specific legacy technologies to use (e.g., Java EE/Tomcat, Python/Django 1.11, PHP/Apache, older Node.js/Express).target_directory: The directory where the application should be generated.
- Strict File System Boundaries:
- CRITICAL: You must ONLY create or modify files inside the specified
target_directory. Do NOT modify or create any files outside of this boundary under any circumstances.
- CRITICAL: You must ONLY create or modify files inside the specified
- No Test Files:
- Do NOT generate any test files (e.g., unit tests, integration tests). Tests will be generated later during the actual demo.
- Host System Isolation:
- You must avoid modifying the host system globally.
- Always use isolated environments for the application dependencies and runtime.
- For Python, use virtual environments (
venv). - For Node.js, use local
node_modulesandpackage.jsonscripts, avoiding globalnpm install -g. - Whenever applicable, provide Dockerfiles and Docker Compose configuration to containerize the legacy app, ensuring complete host system isolation.
- Follow the latest Compose spec when writing the Docker Compose configuration, not the Compose v2 or v3 spec.
- Name the Docker Compose file as:
compose.yaml. - Run the database in a container as well.
- Documentation (
README.md):- You must create a comprehensive
README.mdfile in the root of thetarget_directory. - The README should include:
- A description of the generated legacy application and its simulated business purpose.
- A clear breakdown of the chosen
tech_stack. - Step-by-step developer documentation on how to set up, build, and run
the application locally, specifically highlighting the use of the
isolated environments (e.g., activating the venv, running
docker-compose up).
- You must create a comprehensive
- Build and run:
- Try building the container image using the Dockerfile you generated, and fix any build error.
- Try running the application using the Docker Compose file you generated, and fix any runtime error.
- When running the Docker Compose application, add the option to remove containers when stopping the application.
- Stop the application after validating that it runs successfully.
Execution
Once the user provides the tech_stack and target_directory, plan the
application structure and proceed to generate the source code files, strictly
adhering to all the constraints above.
In this repository28 other files it gives its agents.
- spanner-provisioningSkill
- ad-copywritingSkill
- brand-strategySkill
- platform-specsSkill
- trend-analysisSkill
- video-storytellingSkill
- visual-directionSkill
- ad-copywritingSkill
- brand-strategySkill
- platform-specsSkill
- trend-analysisSkill
- video-storytellingSkill
- visual-directionSkill
- code-reviewSkill
- documentationSkill
- idea-to-appSkill
- open-prSkill
- pre-commitSkill
- security-scanSkill
- unit-testsSkill
- modernize-dotnet-cloudrunSkill
- ingress2gatewaySkill
- bigframes-bqmlSkill
- model-evaluationSkill
- pipeline-generatorSkill
- spark-lightning-optimizationSkill
- unified-model-registrySkill
- zero-copy-ingestionSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

