{
  "ok": true,
  "resource": {
    "id": "RES_FAFAF5B4C937",
    "resource_type": "skill",
    "canonical_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/experimental-design",
    "name": "experimental-design",
    "summary_en": "Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls, factorial or fractional-factorial designs, design of experiments (DOE), screening many factors, response-surface optimization, crossover or repeated-measures or split-plot designs, cluster/group randomization, Latin squares, plate layouts, batch/run-order effects, replication vs. pseudoreplication, or sequential/adaptive/group-sequential designs. Trigger even for informal phrasings like \"how should I set up this experiment\", \"how do I avoid confounding\", \"what's the best way to test these 6 factors\", or \"assign these mice to conditions\". For computing the sample size or power once the design is chosen, use statistical-power; for analyzing data already collected, use statistical-analysis.",
    "summary_zh": "在数据收集之前设计实验和研究——选择设计、随机化、区组化以及安排处理组合，使结果可解释。当有人计划研究、询问如何将受试者/样本分配到组、提到随机化、区组、分层、对照、因子或部分因子设计、实验设计（DOE）、筛选多个因素、响应面优化、交叉或重复测量或裂区设计、整群/分组随机化、拉丁方、板布局、批次/运行顺序效应、重复与伪重复，或序贯/自适应/组序贯设计时使用。即使是非正式表述，如“我该如何设置这个实验”、“如何避免混杂”、“测试这6个因素的最佳方法是什么”或“将这些小鼠分配到条件中”，也会触发。一旦选定设计，如需计算样本量或功效，请使用statistical-power；如需分析已收集的数据，请使用statistical-analysis。",
    "description_en": "This skill provides procedural guidance for designing experiments and studies before data collection. It covers randomization, blocking, stratification, controls, factorial and fractional-factorial designs, design of experiments (DOE), screening designs, response-surface optimization, crossover, repeated-measures, split-plot, cluster-randomized, Latin square, and sequential/adaptive designs. It includes decision trees, reference documents, and Python scripts for generating randomization schedules and DOE matrices. The skill emphasizes avoiding structural mistakes such as pseudoreplication and confounding. It is designed for research agents and requires Python >=3.10 with numpy, pandas, and pyDOE3. The skill is part of the Scientific Agent Skills library by K-Dense Inc. and is licensed under MIT.",
    "description_zh": "该技能提供在数据收集前设计实验和研究的程序性指导。涵盖随机化、区组、分层、对照、因子和部分因子设计、实验设计（DOE）、筛选设计、响应面优化、交叉、重复测量、裂区、整群随机化、拉丁方和序贯/自适应设计。包括决策树、参考文档和用于生成随机化方案和DOE矩阵的Python脚本。该技能强调避免结构错误，如伪重复和混杂。专为研究代理设计，需要Python >=3.10，并依赖numpy、pandas和pyDOE3。该技能是K-Dense Inc.的Scientific Agent Skills库的一部分，采用MIT许可。",
    "provider_name": "K-Dense-AI",
    "homepage_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/experimental-design",
    "endpoint_url": null,
    "source_url": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/experimental-design/SKILL.md",
    "icon_url": null,
    "cover_image_url": null,
    "capabilities": [
      "research.experimental-design",
      "research.randomization",
      "research.blocking",
      "research.doe",
      "research.screening",
      "research.response-surface",
      "research.crossover",
      "research.repeated-measures",
      "research.split-plot",
      "research.cluster-randomization",
      "research.latin-square",
      "research.sequential-design",
      "research.adaptive-design",
      "research.pseudoreplication-avoidance",
      "research.confounding-avoidance"
    ],
    "categories": [
      "research"
    ],
    "industries": [
      "health",
      "general"
    ],
    "protocols": [
      "agent-skills"
    ],
    "auth": {
      "type": "none",
      "required": false
    },
    "pricing": {
      "model": "free"
    },
    "input_schema": {},
    "output_schema": {},
    "metadata": {
      "content_language": "en",
      "translation_status": "original-only",
      "license": {
        "spdx_id": "MIT",
        "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE"
      },
      "github": {
        "repository": "K-Dense-AI/scientific-agent-skills",
        "owner": "K-Dense-AI",
        "path": "skills/experimental-design/SKILL.md",
        "commit": "1e5eeffbdad3749125afe7ab48a39694e27f181c",
        "stars": 42124,
        "forks": 3870,
        "updated_at": "2026-09-03T02:47:03Z"
      },
      "skill": {
        "compatibility": "Requires Python >=3.10. Scripts use numpy, pandas, and pyDOE3 (DOE matrices). Install with uv as shown below.",
        "allowed_tools": "Read Write Edit Bash",
        "content_hash": "8d1e072e96c40dea985deac2d67d2cb800bb8db1cb18b31db0e623ca66e66741",
        "line_count": 252
      },
      "review_gate": {
        "passed": true,
        "reasons": [],
        "policy_version": "review-gate-v1",
        "evaluated_at": "2026-09-03T05:59:26.112Z"
      }
    },
    "latest_version": "1e5eeffbdad3",
    "status": "listed",
    "health_status": "unknown",
    "source_kind": "imported",
    "source_agent": "aiworkshub-skill-reviewer",
    "trust": {
      "signal": "none",
      "reason": "No suspicious or malicious evidence.",
      "signals": {
        "yellow": 0,
        "red": 0
      }
    },
    "review_summary": {
      "method_version": "capability-evidence-v2",
      "capability_definition": "strong",
      "contract_completeness": "strong",
      "access_friction": "low",
      "operational_transparency": "strong",
      "evidence_strength": "source_inspected",
      "use_readiness": "ready_for_guidance",
      "reviewed_at": "2026-09-03T05:59:26.950Z"
    },
    "experience_count": 0,
    "verified_experience_count": 0,
    "usage_count": 0,
    "success_rate": null,
    "first_seen_at": "2026-09-03T02:50:34.587Z",
    "last_seen_at": "2026-09-03T05:59:26.333Z",
    "published_at": "2026-09-03T05:59:26.333Z",
    "created_at": "2026-09-03T02:50:34.587Z",
    "updated_at": "2026-09-03T05:59:26.950Z",
    "api_url": "https://aiworkshub.io/api/v1/resources/RES_FAFAF5B4C937",
    "reviews_url": "https://aiworkshub.io/api/v1/resources/RES_FAFAF5B4C937/reviews",
    "public_url": "https://aiworkshub.io/resources/RES_FAFAF5B4C937",
    "distribution": {
      "canonical_identity": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/experimental-design",
      "syndicatable": true,
      "origins": [
        {
          "registry_url": "https://github.com/",
          "upstream_resource_id": "K-Dense-AI/scientific-agent-skills:skills/experimental-design/SKILL.md",
          "upstream_record_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/experimental-design",
          "relation": "syndicated",
          "metadata": {
            "source": "github-skill-import"
          },
          "first_seen_at": "2026-09-03T02:50:34.587Z",
          "last_seen_at": "2026-09-03T05:59:26.333Z"
        }
      ]
    },
    "tools": [],
    "review_profile": {
      "schema_version": "aiworkshub.resource-review/0.2",
      "method_version": "capability-evidence-v2",
      "review_state": {
        "identity": "verified",
        "source": "verified",
        "connectivity": "unknown",
        "contract": "strong",
        "safe_use": "untested",
        "real_use": "unobserved"
      },
      "assessment": {
        "capability_definition": "strong",
        "contract_completeness": "strong",
        "access_friction": "low",
        "operational_transparency": "strong",
        "evidence_strength": "source_inspected",
        "use_readiness": "ready_for_guidance"
      },
      "profile": {
        "capabilities": [
          {
            "id": "research.experimental-design",
            "weight": 100,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.randomization",
            "weight": 90,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.blocking",
            "weight": 80,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.doe",
            "weight": 90,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.screening",
            "weight": 70,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.response-surface",
            "weight": 70,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.crossover",
            "weight": 60,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.repeated-measures",
            "weight": 60,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.split-plot",
            "weight": 60,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.cluster-randomization",
            "weight": 60,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.latin-square",
            "weight": 50,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.sequential-design",
            "weight": 50,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.adaptive-design",
            "weight": 50,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.pseudoreplication-avoidance",
            "weight": 80,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "research.confounding-avoidance",
            "weight": 80,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          }
        ],
        "domains": [
          {
            "id": "research",
            "weight": 100,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "health",
            "weight": 70,
            "confidence": 80,
            "evidence_ids": [
              "source-record"
            ]
          },
          {
            "id": "biology",
            "weight": 60,
            "confidence": 80,
            "evidence_ids": [
              "source-record"
            ]
          },
          {
            "id": "agriculture",
            "weight": 50,
            "confidence": 70,
            "evidence_ids": [
              "source-record"
            ]
          },
          {
            "id": "engineering",
            "weight": 50,
            "confidence": 70,
            "evidence_ids": [
              "source-record"
            ]
          }
        ],
        "workflow_roles": [
          "design",
          "analyze",
          "instruct"
        ]
      },
      "capability_units": [
        {
          "id": "skill:experimental-design",
          "kind": "skill_action",
          "capability_id": "research.experimental-design",
          "effect": "unknown",
          "open_world": false,
          "idempotency": "idempotent",
          "confirmation": "explicit policy",
          "input_contract": "natural_language",
          "output_contract": "natural_language",
          "accepts": [
            "task context"
          ],
          "produces": [
            "task result"
          ],
          "runtime_auth": {},
          "pricing": {},
          "evidence_ids": [
            "source-inspection"
          ],
          "metadata": {}
        }
      ],
      "access": {
        "distribution_license": {
          "spdx_id": "MIT",
          "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE"
        },
        "runtime_auth": {},
        "runtime_pricing": {},
        "dependencies": [
          "python>=3.10",
          "numpy",
          "pandas",
          "pyDOE3"
        ]
      },
      "operational_flags": [],
      "trust": {
        "signal": "none",
        "evidence_ids": [],
        "reason": "No suspicious or malicious evidence."
      },
      "fit": {
        "good_for": [
          "Planning experiments and studies before data collection",
          "Choosing appropriate experimental designs",
          "Generating randomization schedules and DOE matrices",
          "Avoiding pseudoreplication and confounding",
          "Educational guidance on experimental design principles"
        ],
        "not_for": [
          "Computing sample size or power (use statistical-power skill)",
          "Analyzing already collected data (use statistical-analysis skill)"
        ]
      },
      "evidence": [
        {
          "id": "source-record",
          "type": "source_record",
          "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/experimental-design/SKILL.md",
          "observation": "Submitted Skill record for experimental-design; declared license MIT.",
          "observed_at": "2026-09-03T02:47:03Z",
          "payload": {}
        },
        {
          "id": "source-inspection",
          "type": "source_inspection",
          "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/experimental-design/SKILL.md",
          "observation": "The Skill source was fetched and inspected (14002 bytes; SHA-256 8d1e072e96c40dea985deac2d67d2cb800bb8db1cb18b31db0e623ca66e66741).",
          "observed_at": "2026-09-03T05:48:36.851Z",
          "payload": {}
        }
      ],
      "unknowns": [
        "Actual runtime behavior and output quality not tested",
        "Real-world usage not observed",
        "Connectivity to external resources not verified",
        "Exact content of reference files not inspected",
        "Compatibility with different Python environments not fully verified"
      ],
      "id": "REV_0213292051A5",
      "resource_id": "RES_FAFAF5B4C937",
      "evaluator_type": "platform_ai",
      "provider": "deepseek",
      "model": "deepseek-v4-flash",
      "review_scope": "source-inspected-skill",
      "created_at": "2026-09-03T05:59:26.950Z"
    }
  }
}