Update to CompText Benchmark

{
  "canonical_app_id": null,
  "connector_id": null,
  "created_at": "2026-08-23T16:31:16.543677Z",
  "discoverability": "LISTED",
  "id": "plugins_6a8b1e75fc008191a65fa89587954dc6",
  "is_template": false,
  "name": "comptext-benchmark",
  "release": {
    "app_ids": [],
    "app_manifest": null,
    "app_templates": [],
    "description": "Run, inspect, and compare reproducible Raw vs CompText benchmarks with quality-first evidence.",
    "display_name": "CompText Benchmark",
    "id": "pluginrel_05132bfbd06c8191b2e28e62e032b387",
    "interface": {
      "brand_color": "#6A4BD8",
      "capabilities": [],
      "category": "Developer Tools",
      "composer_icon_dark_url": null,
      "composer_icon_url": "https://files.openai.com/content?id=file_0000000071e081f4b3e5607af6aa02a3",
      "default_prompt": "Run a reproducible Raw vs CompText benchmark and report quality separately from token efficiency.",
      "default_prompts": [
        "Run a reproducible Raw vs CompText benchmark and report quality separately from token efficiency."
      ],
      "developer_name": "CompText Labs",
      "logo_url": "https://files.openai.com/content?id=file_000000006cf081f4b373dc1866e42dd8",
      "logo_url_dark": "https://files.openai.com/content?id=file_00000000bcfc81f6bf38b9885eaca883",
      "long_description": "Run, inspect, and compare Raw versus CompText experiments while keeping quality and efficiency separate and preserving evidence.",
      "plugin_category_id": "developer tools",
      "privacy_policy_url": "https://github.com/ProfRandom92/comptext-marketplace/blob/main/plugins/comptext-benchmark/PRIVACY.md",
      "screenshot_urls": [],
      "short_description": "Benchmark Raw vs CompText.",
      "terms_of_service_url": "https://github.com/ProfRandom92/comptext-marketplace/blob/main/plugins/comptext-benchmark/TERMS.md",
      "website_url": "https://github.com/ProfRandom92/comptext-marketplace/tree/main/plugins/comptext-benchmark"
    },
    "keywords": [
      "benchmark",
      "context-compression",
      "evaluation",
      "comptext"
    ],
    "onboarding_skill_name": null,
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Use when the user asks for a Raw vs CompText verdict, quality regression check, efficiency delta, or evidence-based benchmark comparison.",
        "interface": {
          "brand_color": null,
          "default_prompt": "Compare completed CompText benchmark artifacts, separate quality from efficiency, and flag any token win that causes a regression.",
          "display_name": "Compare CompText Benchmark",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "chart",
          "short_description": "Judge benchmark deltas with evidence"
        },
        "name": "compare-benchmark",
        "plugin_release_skill_id": "pluginrsk_6a8b1e780b7c8191911692caf1330060"
      },
      {
        "description": "Use when the user asks for benchmark status, failures, evidence, active/completed arms, or whether a rerun is required.",
        "interface": {
          "brand_color": null,
          "default_prompt": "Inspect the exact CompText benchmark run, report structured status and evidence, and preserve the frozen manifest on failures.",
          "display_name": "Inspect CompText Benchmark",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "radar",
          "short_description": "Inspect run state and failure evidence"
        },
        "name": "inspect-benchmark",
        "plugin_release_skill_id": "pluginrsk_6a8b1e77db3081919b2a71c7143739ef"
      },
      {
        "description": "Use when the user asks to run or rerun a Raw vs CompText benchmark, validate token reduction, or check quality regressions.",
        "interface": {
          "brand_color": null,
          "default_prompt": "Run a reproducible Raw vs CompText benchmark, preserve quality evidence, and report efficiency separately from fidelity.",
          "display_name": "Run CompText Benchmark",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "chart",
          "short_description": "Run Raw vs CompText benchmarks reproducibly"
        },
        "name": "run-benchmark",
        "plugin_release_skill_id": "pluginrsk_6a8b1e78101c8191a194fdd61f69a0c1"
      }
    ],
    "version": "0.1.5"
  },
  "scope": "GLOBAL",
  "status": "ENABLED"
}