1

    agensi-skill-authoring-with-gemini

    by Markus Isaksson

    Build high-performance, context-efficient Gemini CLI skills following the professional Agensi standard.

    Updated May 2026
    0 installs

    Free

    One-time purchase

    Included in download

    • Downloadable skill package
    • Works with memory structure
    • 2 permissions declared
    • Instant install

    Sample Output

    A real example of what this skill produces.

    SKILL.md for react-component-refactor

    Trigger: "Refactor this component to use hooks" Tool Strategy:

    • Use grep_search to find class methods
    • Use read_file (lines 10-50) to minimize context
    • Invoke codebase_investigator for dependency mapping Output: A focused diff and a prop-type report.

    About This Skill

    What it does

    This skill provides a professional framework for architecting high-performance AI agent skills specifically for the Gemini CLI. It transforms fuzzy prompts into structured, context-efficient SKILL.md files that follow the Agensi standard. Instead of generic instructions, it generates "agent native" logic that leverages Gemini's unique tools like grep_search and sub-agent delegation.

    What problem it solves

    Most AI prompts fail when converted to persistent skills because they are too verbose, consume too much context, or use inefficient tools (like cat instead of targeted read_file). This developer-focused tool enforces strict boundaries, optimizes for token efficiency, and ensures your skills execute with high fidelity and lower costs.

    Supported tools & frameworks

    Optimized for the Gemini CLI and Agensi marketplace standards. It specifically guides the agent in the precise use of:

    • Native search tools: grep_search and glob
    • Context-aware file handling: read_file with start/end line targeting
    • Advanced control flow: enter_plan_mode and sub-agent invocation

    Why use this skill

    Building a marketplace-ready skill requires more than just "telling the AI what to do." This skill acts as a senior architect, ensuring your finished product includes explicit trigger conditions, non-activation boundaries, and imperative operating procedures that prevent model drift and context window saturation.

    Use Cases

    • Convert existing Claude or GPT prompts into Gemini-native skills
    • Optimize agent workflows to reduce token usage and context window bloat
    • Architect complex multi-step skills utilizing sub-agents and plan mode
    • Standardize internal developer workflows into reusable Agensi skill artifacts

    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

    **Permission Profile**: Authoring & Documentation (Read + Write)

    Tags

    gemini-cli
    prompt-engineering
    skill-authoring
    developer-tools
    agensi

    This skill is specifically designed for the **Gemini CLI** and leverages its unique toolset, memory structure, and sub-agent architecture. The resulting `SKILL.md` files are fully compliant with the Agensi standard.

    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

    Free