mcpField
S
script-generator

script-generator

github.com/transilienceaiDevelopment600165 installsUpdated 13w ago
Repository

About script-generator

Script Generator creates optimized, syntax-validated scripts in Python, PowerShell, or Bash, but never runs them. It is intended for requests involving longer scripts, multiple targets, or repeated connections and authentication.

Key features

  1. 01Python, PowerShell, and Bash generation
  2. 02Concurrent handling of multiple targets
  3. 03Reuse of sessions and authentication
  4. 04Syntax validation before delivery
  5. 05Per-operation errors and I/O timeouts
  6. 06Credentials kept out of hardcoded script values

Use cases

  1. 01Generate a script for operations across multiple hosts
  2. 02Automate repeated HTTP requests with a reused session
  3. 03Create a script with repeated authentication handshakes

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/transilienceai/communitytools --skill script-generator

After installing, type/script-generatorin Claude Code to confirm it loaded.

Details

From the project README

Script Generator

Generates optimized, syntax-validated scripts on demand. Never executes scripts.

When to Use

  • Scripts exceed ~30 lines
  • Parallel operations on multiple targets
  • Multi-library patterns (impacket + ldap3, pypsrp + concurrent.futures)
  • Repeated auth handshakes or connection setup

Request Format

LANGUAGE: python3 | powershell | bash
TASK: What the script should accomplish
TARGETS: IPs, hostnames, URLs
CREDENTIALS: user, pass, hash, domain, certs
AVAILABLE_LIBRARIES: What's installed
OUTPUT_FORMAT: stdout format, file writes
CONSTRAINTS: timeout, no destructive ops, output directory
CONTEXT: (optional) Prior output, errors, what failed

Optimization

  • Multiple targets → concurrent.futures.ThreadPoolExecutor

  • 3 HTTP requests to same host → requests.Session

  • Repeated auth → single auth, reuse session/token
  • Prefer high-level libraries (impacket, ldap3, requests)

Output

Write to OUTPUT_DIR/artifacts/<task_name>.<ext>. Return:

SCRIPT_PATH: OUTPUT_DIR/artifacts/task_name.py
LANGUAGE: python3
VALIDATION: PASSED
EXECUTION: python3 OUTPUT_DIR/artifacts/task_name.py
DEPENDENCIES: impacket, concurrent.futures (stdlib)

Rules

  • Never execute scripts — only generate, optimize, validate
  • Per-operation error handling — no bare except:
  • Timeout enforcement on all I/O
  • Validate syntax before returning
  • No secrets hardcoded — credentials as variables at top

Comments

Markdown supported