agentleFS
formulahendryformulahendry/agent-skill-code-runner/.github/skills/code-runner/SKILL.md

code-runner

Skill16 starsChanged 11 months agoMITView on GitHub

Run code snippets in 30+ programming languages including JavaScript, Python, TypeScript, Java, C, C++, Go, Rust, Ruby, PHP, and more. Use when the user wants to execute code, test algorithms, verify output, run scripts, or check code behavior. Supports both interpreted and compiled languages.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. fastclaw-ai/fastclaw★ 1.4ksame name
    2. TaiMaBenJi/taima-skills★ 1same name
    3. yanggujun/open-axle★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 12
  2. Distinctive:

    ⚠️ Important for AI Agents: Use stdin to avoid escaping issues with quotes, backslashes, and special characters.

    line 74
  3. Distinctive:

    If there are errors (stderr), explain what went wrong

    line 124
  4. Very specific:

    Use cmd /c for batch scripts

    line 130
  5. Very specific:

    Use #!/usr/bin/env shebang for portable scripts

    line 137
  6. Distinctive:

    Consider running in a sandboxed environment for untrusted code

    line 169

≈ “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 Runner Skill

This skill enables you to run code snippets in multiple programming languages directly from the command line.

When to Use This Skill

Use this skill when:

  • The user wants to run or execute a code snippet
  • Testing algorithm implementations or logic
  • Verifying expected output of code
  • Running quick scripts or one-liners
  • Checking syntax or runtime behavior
  • Demonstrating code functionality

Supported Languages

The following languages are supported (requires the interpreter/compiler to be installed):

LanguageCommandFile Extension
JavaScriptnode.js
TypeScriptts-node.ts
Pythonpython.py
Javajava (compile & run).java
Cgcc (compile & run).c
C++g++ (compile & run).cpp
Gogo run.go
Rustrustc (compile & run).rs
Rubyruby.rb
PHPphp.php
Perlperl.pl
Lualua.lua
RRscript.r
Swiftswift.swift
Kotlinkotlin.kts
Scalascala.scala
Groovygroovy.groovy
Dartdart.dart
Juliajulia.jl
Haskellrunhaskell.hs
Clojureclojure.clj
F#dotnet fsi.fsx
C#dotnet script.csx
PowerShellpwsh.ps1
Bashbash.sh
Batchcmd /c.bat
CoffeeScriptcoffee.coffee
Crystalcrystal.cr
Elixirelixir.exs
Nimnim compile --run.nim
OCamlocaml.ml
Racketracket.rkt
Schemescheme.scm
Lispsbcl --script.lisp

See references/LANGUAGES.md for detailed language configuration.

How to Run Code

Step 1: Identify the Language

Determine the programming language from:

  • User's explicit request (e.g., "run this Python code")
  • File extension if provided
  • Code syntax patterns

Step 2: Execute Using the Runner Script

⚠️ Important for AI Agents: Use stdin to avoid escaping issues with quotes, backslashes, and special characters.

Recommended Method (stdin):

echo "<code>" | node scripts/run-code.cjs <languageId>

Alternative Method (CLI argument - for simple code only):

node scripts/run-code.cjs <languageId> "<code>"

Example - JavaScript:

echo "console.log('Hello, World!')" | node scripts/run-code.cjs javascript

Example - Python:

echo "print('Hello, World!')" | node scripts/run-code.cjs python

Example - Java (multi-line):

echo "public class Test {
    public static void main(String[] args) {
        System.out.println(\"Hello from Java!\");
    }
}" | node scripts/run-code.cjs java

Example - Multi-line code from variable:

# In bash
CODE='import math
print("Pi:", math.pi)
print("Result:", math.factorial(5))'
echo "$CODE" | node scripts/run-code.cjs python

# In PowerShell (inline here-string)
@"
import math
print("Pi:", math.pi)
print("Result:", math.factorial(5))
"@ | node scripts/run-code.cjs python

Step 3: Return Results

  • Show the output (stdout) to the user
  • If there are errors (stderr), explain what went wrong
  • Suggest fixes for common errors

Platform Notes

Windows

  • Use cmd /c for batch scripts
  • PowerShell scripts require pwsh or powershell
  • Path separators use backslash \

macOS / Linux

  • Bash scripts work natively
  • Swift available on macOS
  • Use #!/usr/bin/env shebang for portable scripts

Error Handling

Common issues and solutions:

  1. Command not found: The language interpreter is not installed or not in PATH
    • Suggest installing the required runtime
    • Provide installation instructions
  2. Syntax errors: Code has syntax issues
    • Show the error message
    • Point to the line number if available
  3. Runtime errors: Code runs but fails during execution
    • Display the stack trace
    • Explain the error type
  4. Timeout: Code takes too long (default: 30 seconds)
    • Warn about infinite loops
    • Suggest optimizations

Security Considerations

⚠️ Important: Running arbitrary code can be dangerous. Always:

  1. Review the code before execution
  2. Be cautious with code that:
    • Accesses the file system
    • Makes network requests
    • Executes system commands
    • Modifies environment variables
  3. Consider running in a sandboxed environment for untrusted code

Examples

Example 1: Run a JavaScript calculation

echo "console.log(Array.from({length: 10}, (_, i) => i * i))" | node scripts/run-code.cjs javascript

Output: [0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

Example 2: Run Python with imports

echo "import math; print(math.factorial(10))" | node scripts/run-code.cjs python

Output: 3628800

Example 3: Test a Go function

echo 'package main; import "fmt"; func main() { fmt.Println("Hello from Go!") }' | node scripts/run-code.cjs go

Output: Hello from Go!

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.