1

    skill-evaluation-and-iteration-with-gemini

    by Markus Isaksson

    Diagnose, score, and systematically refactor Gemini CLI skills for high-efficiency performance and reliability.

    Updated May 2026
    Security scanned
    One-time purchase

    $5

    One-time purchase

    30-day refund guarantee

    Secure checkout via Stripe

    Included in download

    • Audit skills for context-window inefficiency and token bloat.
    • Upgrade basic prompts into robust, marketplace-ready agent protocols.
    • file_write, file_read automation included
    • Includes example output and usage patterns
    • Instant install

    Sample Output

    A real example of what this skill produces.

    Tool Precision: 4/10. Notes: Skill uses 'run_shell_command' to read files instead of 'read_file' with line offsets, causing context bloat. Diagnosis: Protocol Weakness. Plan: Update instructions to mandate 'grep_search' for initial discovery. Recommended: Execute surgical rewrite? (Y/N)

    About This Skill

    Optimize Your AI Agent Performance

    Low-quality skills lead to context exhaustion, hallucinations, and agent drift. This skill provides a rigorous diagnostic framework designed specifically for developer-centric agent architectures like the Gemini CLI. It systematically audits your instruction sets to ensure they meet professional distribution standards.

    What it does

    The evaluator performs a multi-phase audit of any instruction file (SKILL.md). It uses a 9-dimension rubric—including Tool Precision, Orchestration, and Output Contracts—to assign objective scores. After diagnosis, it identifies "context leaks" and protocol weaknesses, providing a prioritized plan to refactor vague advice into hard agent protocols. Finally, it can surgically rewrite your skill to implement these improvements automatically.

    Why use this skill

    Prompting an AI yourself is often a trial-and-error process. This skill automates the "red-teaming" of your agent logic. It replaces general prompts with high-efficiency tool patterns (like replacing generic shell commands with targeted search tools), drastically reducing token usage and improving the reliability of your local workflows. It ensures your skills are marketplace-ready by enforcing strict guardrails and clear triggering conditions.

    Supported Frameworks

    Optimized for Gemini CLI and agents utilizing Plan Mode, sub-agent orchestration, and advanced file manipulation tools.

    📖 Learn more: Best DevOps & Deployment Skills for Claude Code →

    Use Cases

    • Audit skills for context-window inefficiency and token bloat.
    • Upgrade basic prompts into robust, marketplace-ready agent protocols.
    • Fix hallucination issues by enforcing strict tool boundaries and guardrails.
    • Refactor vague instructions into imperative, phased execution steps.

    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

    Write Files
    Read Files

    Allowed Hosts

    mcp.agensi.io

    File Scopes

    .gemini/skills/**
    **/*.md

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

    This skill is optimized for evaluating skills meant to be run by the **Gemini CLI**. It is highly attuned to the specific context window and tool capabilities of this environment.

    Frequently Asked Questions

    More Premium Skills

    $5

    One-time