Agent Portability Checker
by Rian O'Leary
Audit and auto-fix agent skills to remove platform lock-in and ensure cross-platform compatibility.
Free
Works with the AI tools you already use
See it in action
You say
Audit the github-growth-tracker skill for platform lock-in and fix any hardcoded paths you find.
Your agent does
AUDIT REPORT: github-growth-tracker ❌ scripts/tracker.py:28: Hardcoded ~/.clawhub/ path found. ✅ Auto-fixed: Replaced with $SKILL_DATA_DIR. ⚠️ Warning: Script uses 'gh' CLI; ensure target agent has GitHub CLI installed. 🔧 XDG Fallback: Added ~/.config/tracker/ support.
About this skill
What it does
The Agent Portability Checker is a developer tool designed to audit agent skills for platform lock-in. It scans your codebase for hardcoded paths, platform-specific dependencies, and rigid environmental assumptions that prevent your skills from running across different agent environments like Claude Code, OpenClaw, or Codex.
Why use this skill
Building skills that only work on one platform limits your reach and creates technical debt. This skill automates the tedious process of finding and fixing "platform leaks." It's significantly more reliable than manual prompting because it follows a rigorous 8-point checklist—including XDG fallback standards and headless OAuth compliance—that generic AI models often overlook.
Supported tools
- Standard Python-based agent skills
- XDG Base Directory Specification compliance
- Cross-platform path resolution (os.path/pathlib)
- Multi-channel formatting (Slack, Discord, WhatsApp)
What the output looks like
The skill provides a structured audit report flagging specific line numbers for hardcoded paths, missing environment variable support, and platform-specific CLI dependencies. When in 'fix' mode, it automatically refactors paths to use dynamic environment variables like $SKILL_DATA_DIR.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
17 installs
Downloaded by developers to date
Free forever
No account required to browse
More reviews for Rian O'Leary5.0(2)
Feedback buyers left on other skills by the same creator.
Trust & safety
Security scanned
Verified clean 4 months ago
- Free to download with an account
Frequently Asked Questions
Popular in AI Agents & LLM Ops
agentic-workflow
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
prompt-engineer
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
skill-creator
The "Skill for building Skills": Automate creating, testing, and optimisation of custom workflows.