Update to Gauntlet

{
  "canonical_app_id": null,
  "connector_id": null,
  "created_at": "2026-08-19T10:56:38.839475Z",
  "discoverability": "LISTED",
  "id": "plugins_6a858a648f2081919256f55cced396c5",
  "is_template": false,
  "name": "gauntlet",
  "release": {
    "app_ids": [],
    "app_manifest": null,
    "app_templates": [],
    "description": "Turn important tasks into rigorous build-test-critique-benchmark-improve workflows.",
    "display_name": "Gauntlet",
    "id": "pluginrel_c4fca0d8a1208191992a7d1caf00c94f",
    "interface": {
      "brand_color": "#B45309",
      "capabilities": [
        "Quality review",
        "Iterative improvement",
        "Benchmarking",
        "Prompt building",
        "Auditing",
        "Planning"
      ],
      "category": "Productivity",
      "composer_icon_dark_url": null,
      "composer_icon_url": "https://files.openai.com/content?id=file_000000003edc81f49eebe97c5354daa4",
      "default_prompt": "Improve this by finding and fixing the weakest parts.",
      "default_prompts": [
        "Improve this by finding and fixing the weakest parts.",
        "Turn this task into a rigorous copy-paste prompt.",
        "Audit this work, preserve what's already strong, and improve the material weaknesses."
      ],
      "developer_name": "MARCEL EBERT",
      "logo_url": "https://files.openai.com/content?id=file_00000000667881f6872160c28d79996f",
      "logo_url_dark": null,
      "long_description": "Gauntlet turns important requests into rigorous, proportionate quality-control workflows. It can execute a task, audit and improve existing work, or build a reusable Gauntlet prompt. It adapts reviewers, benchmarks, validation, stress tests, implementation checks, and stop gates to the task while keeping simple requests simple.",
      "plugin_category_id": "productivity",
      "privacy_policy_url": null,
      "screenshot_urls": [],
      "short_description": "Rigorous quality-control loops",
      "terms_of_service_url": null,
      "website_url": null
    },
    "keywords": [
      "quality",
      "review",
      "benchmark",
      "iteration",
      "audit",
      "workflow"
    ],
    "onboarding_skill_name": null,
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Turn requests that invoke Gauntlet as a quality-control workflow into rigorous, proportionate build-test-critique-benchmark-improve processes for arbitrary non-trivial tasks. Use when the user commands \"Gauntlet this,\" \"Run the Gauntlet,\" \"Build a Gauntlet,\" requests a \"Gauntlet prompt,\" asks to \"Audit this with Gauntlet,\" or unmistakably requests an adversarial iterative quality-control loop. Support three modes: BUILD a self-contained copy-paste prompt, RUN the underlying task, or AUDIT/IMPROVE existing work. Adapt tests, critics, real benchmarks, stress tests, iteration evidence, conditional implementation translation, and stop gates across software, design, research, writing, strategy, data, visual, and mixed work. For qualifying product and software feature work, translate selected decisions into implementation-ready behavior without forcing a full specification. Do not trigger for ordinary quality requests or for literal, historical, or titled gauntlets unrelated to this methodology.",
        "interface": {
          "brand_color": "#B45309",
          "default_prompt": null,
          "display_name": "Gauntlet",
          "icon_large_url": "https://files.openai.com/content?id=file_00000000e3c482438f324d55d9110962",
          "icon_small_url": "https://files.openai.com/content?id=file_000000005f6c81f480b612461afdf72c",
          "iconography": "radar",
          "short_description": "Build, critique, benchmark, improve, and verify."
        },
        "name": "gauntlet",
        "plugin_release_skill_id": "pluginrsk_6a858a6c5b488191806a7a4348679f22"
      }
    ],
    "version": "1.0.0"
  },
  "scope": "GLOBAL",
  "status": "ENABLED"
}