1

    cross-agent-skill-porting-with-gemini

    by Markus Isaksson

    Convert skills from Grok, Claude, and Cursor into optimized, native Gemini CLI adapters.

    Updated May 2026
    Security scanned
    One-time purchase
    Copilot

    $8

    One-time purchase

    30-day refund guarantee

    Secure checkout via Stripe

    Included in download

    • Translate platform-specific XML or .mdc rules into Gemini-native adapters.
    • Extract a portable 'logic core' from existing skills for multi-agent use.
    • file_read, file_write automation included
    • Ready for Copilot
    • Instant install

    Sample Output

    A real example of what this skill produces.

    Portability Verdict: High Source: Grok 'System-Scan' (uses bash_proxy) Gemini Adapter:

    • Trigger: 'Perform security audit'
    • Tool Mapping: 'bash_proxy' -> 'grep_search' + 'read_file'
    • Strategy: Use 'enter_plan_mode' for multi-step analysis. Action: Saving to .gemini/skills/security-audit.md

    About This Skill

    What it does

    This skill acts as an architectural translator for AI agent behaviors. It analyzes skills written for specific platforms—like Grok, Claude Code, or Cursor—and ports them into highly optimized Gemini-native skills. It strips away platform-specific "dialects" (like XML tags or proprietary tool calls) and maps the core logic to the Gemini CLI's native toolset.

    Why use this skill

    Prompting an AI to "act like this other skill" often results in hallucinated tool calls or inefficient token usage. This developer-centric tool provides a systematic refactoring process that:

    • Separates agent-agnostic logic from platform-specific implementation.
    • Maps foreign tools (like MCP bridges or custom shell commands) to Gemini's native grep_search, glob, and read_file capabilities.
    • Implements a "Core + Adapter" architecture, making your skills maintainable across multiple IDEs and CLI agents.

    Supported tools

    This skill supports porting between Gemini CLI, Cursor (.mdc), GitHub Copilot (.instructions.md), Claude Code, and Grok. It focuses on converting non-native workflows into Gemini's orchestration patterns, such as Plan Mode and Sub-Agent invocation.

    📖 Learn more: Best Code Review Skills for Claude Code →

    Use Cases

    • Translate platform-specific XML or .mdc rules into Gemini-native adapters.
    • Extract a portable 'logic core' from existing skills for multi-agent use.
    • Fix failing skills that attempt to use non-existent tools in Gemini.
    • Optimize foreign skills for Gemini's Plan Mode and Sub-Agent architecture.

    Reviews

    No reviews yet - be the first to share your experience.

    Only users who have downloaded or purchased this skill can leave a review.

    Security Scanned

    Passed automated security review

    Permissions

    Read Files
    Write Files

    File Scopes

    .gemini/skills/**
    **/*.md
    .cursor/rules/**
    .github/instructions/**

    **Permission Profile**: Analysis & Refactoring (Read + Write)

    Tags

    refactoring
    gemini-cli
    cross-platform
    developer-tools
    prompt-engineering

    This skill is executed by the **Gemini CLI** and specializes in translating foreign skill logic into Gemini-native workflows, while also understanding the architectures of Cursor, Copilot, Claude, and Grok for outbound porting.

    Creator

    Markus Isaksson

    Frequently Asked Questions

    Learn More About AI Agent Skills

    More Premium Skills

    context-switch-protector

    Eliminate the "re-entry tax" with structured state dumps that capture your focus before context switching.

    $51 installs

    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.

    $1012 installs

    diagnosing-rag-failure-modes

    RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.

    $105 installs

    keyword-research

    Transform URLs or product lists into SEO keyword research packs with Google Ads data and intent-based clustering.

    $75 installs

    $8

    One-time