{
  "slug": "frontend-slides",
  "title": "Frontend Slides",
  "description": "A controlled three-pair evaluation of the pinned Frontend Slides skill on a complete, pre-approved seven-slide investor-deck brief.",
  "status": "ADOPTED",
  "status_label": "Passed evaluation \u00b7 adopted",
  "package_hash": "832994fe1dfcce2aa7ceca9a1b7b708eca94becef242713999855f4e946cf4d5",
  "repo_url": "https://github.com/zarazhangrui/frontend-slides/tree/9906a34d640d2111f724544cbc50f7f130569ae1",
  "get_label": "Get the pinned skill",
  "model": "OpenAI GPT-5.6 Sol",
  "method": "Three blind baseline-versus-skill pairs in isolated Harbor containers. Same model, prompt, files, and objective checker; only the skill installation changed.",
  "claim": "On this fixed-stage deck task, the skill won two blind pairs and tied one; its outputs passed every objective check, versus one of three baselines.",
  "status_explanation": "The skill passed Edge's preregistered three-pair adoption gate: a strict majority of blind wins, treatment verification passed, and treatment tool errors did not exceed baseline.",
  "stats": [
    {
      "value": "2 / 1 / 0",
      "label": "wins / ties / losses"
    },
    {
      "value": "3 of 3",
      "label": "skill outputs passed"
    },
    {
      "value": "1 of 3",
      "label": "baseline outputs passed"
    },
    {
      "value": "6",
      "label": "recorded agent runs"
    }
  ],
  "limitations": [
    "One task family with three paired samples; no confidence interval can support a catalog-wide efficacy claim.",
    "The brief supplied an already-approved visual direction; the interactive style-selection phase was not evaluated.",
    "Visual quality was judged from recorded artifacts, not audience outcomes."
  ]
}