More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Draw Call Budget Rescue

    1

    Bring a scene back under its draw-call budget: measure per object class, find the real contributors, and cut calls without gutting the scene.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Draw Call Budget Rescue

    Draw Call Budget Rescue

    Example session with this skill installed

    Apply the skill to this case: a market scene measures 820 draw calls against a 300 budget on the target phone, with 340 calls from individual fruit props, 180 from separate stall signs, and 120 from unbatched fence pieces. Rank the contributors, cut the count, and report the checklist score.

    • Read your context and instructions
    • Compiled the draw call budget

    A market scene measured 820 draw calls against a 300 budget on the target phone. The ranking showed 340 calls from individual fruit props, 180 from separate stall signs, and 120 from unbatched fence pieces. Instancing the fruit, atlasing the signs onto shared materials, and merging static fences cut the count to 265. A side-by-side visual check confirmed the market looked the same, and the worst camera angle, not the average, was used for the final measurement. This is a worked example produced by applying the skill's protocol: baseline counted first, decision table row selected on evidence, fix at the source, verification on the same conditions, and a prevention step recorded.

    Checker run on the worked example's completed checklist prints score 10.0, passed 7 of 7, failed [], ready true (exit 0).

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Bring a scene back under its draw-call budget: measure per object class, find the real contributors, and cut calls without gutting the scene. Use when a scene exceeds its draw-call budget on target hardware, when frame time is dominated by draw submission, or when a scene that ran fine now misses its budget after content growth.

    Thresholds are starting points and may need adjustment for different hardware or project sizes. The skill diagnoses and guides fixes; it does not replace engine, platform, or vendor tooling. Cases outside the stated scope should use a different workflow.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    Permissions

    Terminal / Shell
    Write Files
    Listed23 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    A clear symptom, the affected files or sessions, version details, and a backup of the originals. The skill lists the exact inputs in its contract section.

    By comparing before-and-after measurements on the same reproduction conditions, using the checklist and scoring rubric in the skill. A score of 7 or higher is required to close a case.

    Yes. The workflow scales down: fill the template, run the first checks, and verify. Small cases are where the habit of evidence-first work pays off fastest.

    New in Workflow Automation