agentleFS
viknesh20-20viknesh20-20/claude-code-tool-kit/.claude/skills/convert-code/SKILL.md

convert-code

Skill7 starsChanged 6 months agoMITView on GitHub

Converts code between programming languages while preserving logic, error handling, and idiomatic patterns. Use when migrating modules between languages or frameworks.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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
  1. Distinctive:

    Read the source file completely

    line 13
  2. Distinctive:

    All functions, classes, and types

    line 15
  3. Distinctive:

    Don't transliterate — convert to idiomatic target code:

    line 24
  4. Distinctive:

    If no direct equivalent exists, note it and implement the functionality

    line 39
  5. Distinctive:

    Write the converted file with proper formatting

    line 65
  6. Distinctive:

    Add a header comment noting the source and conversion

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Code Conversion

Instructions

Step 1: Analyze Source Code

  1. Read the source file completely
  2. Identify:
    • All functions, classes, and types
    • External dependencies and their equivalents in the target language
    • Error handling patterns
    • Async/concurrent patterns
    • Data structures and their representations
    • Tests (if present)

Step 2: Map Language Idioms

Don't transliterate — convert to idiomatic target code:

Source PatternTarget Equivalent
Python list comprehensionJava streams / Go slices / Rust iterators
JS Promise.allPython asyncio.gather / Go goroutines+WaitGroup / Rust tokio::join
Python dictGo map / Rust HashMap / Java Map
JS destructuringGo multiple returns / Python tuple unpacking
Python decoratorJava annotation / Go middleware / Rust macro
C# LINQPython generators / JS array methods / Rust iterators
Ruby blocksPython context managers / Go defer / Rust closures

Step 3: Handle Dependencies

For each import/dependency in the source:

  1. Find the equivalent package/library in the target ecosystem
  2. If no direct equivalent exists, note it and implement the functionality
  3. Map API calls to the target library's conventions

Step 4: Convert Error Handling

Different languages handle errors differently:

LanguagePattern
Pythontry/except, raise
JavaScript/TypeScripttry/catch, throw, Promise rejection
GoMultiple return values (value, error)
RustResult<T, E>, Option<T>, ? operator
Java/C#try/catch, checked/unchecked exceptions
Rubybegin/rescue/ensure
Elixir{:ok, value} / {:error, reason} tuples

Convert error handling to the idiomatic pattern of the target language.

Step 5: Convert Types

Map type systems:

  • Dynamic → Static: Infer and add explicit types
  • Static → Dynamic: Simplify but add runtime checks where safety-critical
  • Generics: Map to target language's generic system
  • Null safety: Map Optional/Maybe/Option patterns appropriately

Step 6: Generate Output

  1. Write the converted file with proper formatting
  2. Add a header comment noting the source and conversion
  3. Include all necessary imports
  4. Preserve comments (translate them to the target language's convention)
  5. Generate a companion test file if tests existed in the source

Step 7: Conversion Notes

Document:

  • Patterns that couldn't be directly converted and the approach taken
  • Dependencies that have no direct equivalent
  • Behavioral differences to be aware of
  • Performance characteristics that differ between implementations

Rules

  • Idiomatic over literal — code should look like it was written by a native developer
  • Preserve behavior — the converted code must do the same thing
  • Preserve tests — convert tests too, not just implementation
  • Flag risks — note where behavior might differ (floating point, string encoding, concurrency)
  • Don't assume — if unsure about a language feature, ask rather than guess

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.