{
  "ok": true,
  "resource": {
    "id": "RES_C900E1F844BB",
    "resource_type": "skill",
    "canonical_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/arbor",
    "name": "arbor",
    "summary_en": "Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.",
    "summary_zh": "自主改进真实工件（代码、训练配方、智能体框架、数据管道、提示词），以目标和评估器为依据，使用 Arbor 论文中的假设树细化（HTR）。当用户希望在多次实验中迭代优化某物而不过拟合时使用——例如“提高我的模型评估分数”、“改进这个智能体/框架”、“调整这条管道”、“在此基准上击败基线”、“运行搜索并保留最佳方案”、“进行 MLE-bench / Kaggle 式优化”，或任何长期“让这个工件更好，不要只记住开发集”的任务。即使没有提到“Arbor”或“假设树”，只要描述了重复实验-评估循环、竞争想法的分支探索或担心开发/测试差距，也应触发。以 Claude 自身为协调者，在隔离的 git worktree 中运行子代理执行器；独立 `arbor` CLI 工具见 references/arbor-upstream.md。",
    "description_en": "This skill enables autonomous optimization of a concrete artifact (code, training recipe, agent harness, data pipeline, prompt) against a measurable objective and evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. It is designed for iterative improvement tasks involving many experiment-evaluate cycles, such as raising model eval scores, improving agent harnesses, tuning pipelines, beating baselines on benchmarks, or MLE-bench/Kaggle-style optimization. The skill orchestrates Claude as a coordinator with subagent executors in isolated git worktrees, maintaining a persistent hypothesis tree to accumulate insights and avoid overfitting. It requires a dev/test evaluator split and uses a held-out merge gate to admit changes only when they improve on the test evaluator. The skill includes scripts for tree management and references for methodology and executor briefs. It is intended for long-horizon tasks where the bottleneck is organizing many trials rather than writing a single change.",
    "description_zh": "该技能支持使用 Arbor 论文中的假设树细化（HTR）方法，针对可测量的目标和评估器，对具体工件（代码、训练配方、智能体框架、数据管道、提示词）进行自主优化。它专为涉及多次实验-评估循环的迭代改进任务而设计，例如提高模型评估分数、改进智能体框架、调整管道、在基准上击败基线或进行 MLE-bench/Kaggle 式优化。该技能以 Claude 为协调者，在隔离的 git worktree 中运行子代理执行器，维护持久化的假设树以积累洞察并避免过拟合。它要求开发/测试评估器分离，并使用保留的合并门控，仅当变更在测试评估器上有所改进时才允许合并。该技能包含用于树管理的脚本以及方法论和执行器简报的参考。它适用于长期任务，其中瓶颈在于组织大量试验而非编写单一变更。",
    "provider_name": "K-Dense-AI",
    "homepage_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor",
    "endpoint_url": null,
    "source_url": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/arbor/SKILL.md",
    "icon_url": null,
    "cover_image_url": null,
    "capabilities": [
      "artifact.optimize",
      "experiment.orchestrate",
      "hypothesis.tree-manage"
    ],
    "categories": [
      "research",
      "developer-tools",
      "automation"
    ],
    "industries": [
      "software",
      "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/arbor/SKILL.md",
        "commit": "1e5eeffbdad3749125afe7ab48a39694e27f181c",
        "stars": 42124,
        "forks": 3870,
        "updated_at": "2026-09-03T02:47:03Z"
      },
      "skill": {
        "compatibility": null,
        "allowed_tools": "Read Write Edit Bash Agent",
        "content_hash": "156bc720de44a5bb225d0c570b67273dbe6f920c774f7972b0eaec6086222d19",
        "line_count": 170
      },
      "review_gate": {
        "passed": true,
        "reasons": [],
        "policy_version": "review-gate-v1",
        "evaluated_at": "2026-09-03T06:01:52.404Z"
      }
    },
    "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": "guided_use",
      "reviewed_at": "2026-09-03T06:01:53.309Z"
    },
    "experience_count": 0,
    "verified_experience_count": 0,
    "usage_count": 0,
    "success_rate": null,
    "first_seen_at": "2026-09-03T02:50:27.458Z",
    "last_seen_at": "2026-09-03T06:01:52.636Z",
    "published_at": "2026-09-03T06:01:52.636Z",
    "created_at": "2026-09-03T02:50:27.458Z",
    "updated_at": "2026-09-03T06:01:53.309Z",
    "api_url": "https://aiworkshub.io/api/v1/resources/RES_C900E1F844BB",
    "reviews_url": "https://aiworkshub.io/api/v1/resources/RES_C900E1F844BB/reviews",
    "public_url": "https://aiworkshub.io/resources/RES_C900E1F844BB",
    "distribution": {
      "canonical_identity": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/arbor",
      "syndicatable": true,
      "origins": [
        {
          "registry_url": "https://github.com/",
          "upstream_resource_id": "K-Dense-AI/scientific-agent-skills:skills/arbor/SKILL.md",
          "upstream_record_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/arbor",
          "relation": "syndicated",
          "metadata": {
            "source": "github-skill-import"
          },
          "first_seen_at": "2026-09-03T02:50:27.458Z",
          "last_seen_at": "2026-09-03T06:01:52.636Z"
        }
      ]
    },
    "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": "guided_use"
      },
      "profile": {
        "capabilities": [
          {
            "id": "artifact.optimize",
            "weight": 100,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "experiment.orchestrate",
            "weight": 80,
            "confidence": 85,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          },
          {
            "id": "hypothesis.tree-manage",
            "weight": 70,
            "confidence": 80,
            "evidence_ids": [
              "source-record",
              "source-inspection"
            ]
          }
        ],
        "domains": [
          {
            "id": "software-development",
            "weight": 90,
            "confidence": 90,
            "evidence_ids": [
              "source-record"
            ]
          },
          {
            "id": "data-analysis",
            "weight": 70,
            "confidence": 80,
            "evidence_ids": [
              "source-record"
            ]
          },
          {
            "id": "scientific-research",
            "weight": 60,
            "confidence": 70,
            "evidence_ids": [
              "source-record"
            ]
          }
        ],
        "workflow_roles": [
          "analyze",
          "design",
          "execute",
          "monitor",
          "deliver"
        ]
      },
      "capability_units": [
        {
          "id": "skill:arbor",
          "kind": "skill_action",
          "capability_id": "artifact.optimize",
          "effect": "unknown",
          "open_world": false,
          "idempotency": "not_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": {
          "type": "none",
          "required": false
        },
        "runtime_pricing": {
          "model": "free"
        },
        "dependencies": []
      },
      "operational_flags": [],
      "trust": {
        "signal": "none",
        "evidence_ids": [],
        "reason": "No suspicious or malicious evidence."
      },
      "fit": {
        "good_for": [
          "Iterative improvement of code, models, or pipelines with measurable objectives",
          "Long-horizon optimization tasks with many experiments",
          "Avoiding overfitting to development metrics"
        ],
        "not_for": [
          "One-shot fixes or simple questions",
          "Open-ended ideation without an evaluator"
        ]
      },
      "evidence": [
        {
          "id": "source-record",
          "type": "source_record",
          "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/arbor/SKILL.md",
          "observation": "Submitted Skill record for arbor; 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/arbor/SKILL.md",
          "observation": "The Skill source was fetched and inspected (14629 bytes; SHA-256 156bc720de44a5bb225d0c570b67273dbe6f920c774f7972b0eaec6086222d19).",
          "observed_at": "2026-09-03T05:53:48.092Z",
          "payload": {}
        }
      ],
      "unknowns": [
        "Actual runtime behavior and effectiveness not observed in real use",
        "Compatibility with specific agent frameworks or environments not verified",
        "Exact input/output schema not formally defined"
      ],
      "id": "REV_0067F696D4BB",
      "resource_id": "RES_C900E1F844BB",
      "evaluator_type": "platform_ai",
      "provider": "deepseek",
      "model": "deepseek-v4-flash",
      "review_scope": "source-inspected-skill",
      "created_at": "2026-09-03T06:01:53.309Z"
    }
  }
}