Skills Plugins MCP Prompt Model 博客 我的中心

cobol-modernization

End-to-end COBOL to Java migration workflow. Handles build setup, mainframe dependency removal, and code migration with test validation.

DeepseekModel Curated skill Quality Excellent · 78 v1.0.0

Get

https://deepseekmodel.com/api/download.php?id=openhands-extensions-plugins-cobol-modernization-skills-cobol-modernization-skill-md&format=skill
Download .skill Standard format with system_prompt and model_config, ready for any agent framework
The actual content of the system_prompt field in the .skill file.
name cobol-modernization description End-to-end COBOL to Java migration workflow. Handles build setup, mainframe dependency removal, and code migration with test validation. license MIT compatibility Requires GnuCOBOL, Java 11+, Maven/Gradle, Python 3.13 with uv triggers ["cobol modernization","cobol to java","cobol migration","mainframe migration"] End-to-end workflow for migrating COBOL codebases to Java. Overview This plugin orchestrates a multi-phase COBOL modernization project: Build Setup — Configure compilation for both COBOL and Java, create test fixtures Mainframe Planning — Document transformations needed to remove mainframe dependencies Mainframe Removal — Convert CICS/VSAM code to standard COBOL Java Migration — Translate standardized COBOL to idiomatic Java Prerequisites GnuCOBOL compiler ( cobc ) Java 11+ with Maven or Gradle Python 3.13 with uv LLM API key (Anthropic or OpenAI) Quick Start export LLM_API_KEY= "your-api-key" export LLM_MODEL= "anthropic/claude-3-5-sonnet-20241022" uv run python -m lc_sdk_examples.cobol_modernization --src-path /path/to/cobol/project PowerShell equivalent for the environment setup: $env:LLM_API_KEY = "your-api-key" $env:LLM_MODEL = "anthropic/claude-3-5-sonnet-20241022" uv run python -m lc_sdk_examples.cobol_modernization --src-path C:\path\to\cobol\project Workflow Phases Phase 1: Build Setup See ../build-setup/SKILL.md Creates the foundation for the migration: COBOL compilation environment (GnuCOBOL) Java project structure (Maven/Gradle + JUnit 5) Test fixtures with golden outputs from COBOL execution Outputs: build_notes.md — Build instructions test-fixtures/ — Input/output test data test_manifest.json — Test case mapping Phase 2: Mainframe Planning See ../mainframe-planning/SKILL.md Creates a transformation guide without modifying code: Maps CICS/VSAM constructs to standard COBOL equivalents Documents error handling replacements Identifies UI operations to stub Output: mainframe_dependency_removal_plan.md Phase 3: Mainframe Removal See ../mainframe-removal/SKILL.md Applies the transformation guide: Replaces EXEC CICS commands with file I/O Adds FILE STATUS checking Stubs BMS/screen operations Verification: Code compiles with GnuCOBOL Runs with test fixtures Phase 4: Java Migration See ../to-java-migration/SKILL.md Translates to idiomatic Java: Proper Java conventions (not literal translations) JUnit tests using golden outputs COBOL references in comments Done when: All code compiles All JUnit tests pass No TODOs or stubs remain Output Structure your-project/ ├── .lc-sdk/ │ ├── initial_batch_graph.json │ ├── fixed_batch_graph.json │ └── mainframe_dependency_removal_plan.md ├── test-fixtures/ │ ├── inputs/ │ └── expected_outputs/ ├── test_manifest.json ├── src/main/java/ └── src/test/java/ Troubleshooting See ../../references/troubleshooting.md for common issues and solutions.
Keywords that activate this skill. Click one to copy it.

This skill does not provide trigger words.

The downloaded .skill package contains the following fields.
Field Description
formatFormat tag (skill/v1)
skill_idUnique skill ID
nameSkill name
versionVersion
descriptionDescription
categoryCategories (array)
trigger_wordsTrigger words
tagsTags
sourceSource
source_urlSource URL (this page)
exported_atExported at (set per download)
system_promptSystem prompt body
model_configModel config: provider / model / temperature / max_tokens / top_p
examplesExamples
install_guideImport guide for Coze / Dify / Claude / custom frameworks
The same skill can be exported in different platform formats.
.skill Standard format with system_prompt and model_config, ready for any agent framework Download
.skillpro Enhanced format with scripts, tools, dependencies and hooks Download
.json Plain JSON export with system_prompt and model parameters only Download
Coze Markdown with frontmatter, for Coze platform import Download
Dify Dify DSL, import directly after creating an app Download

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。