본문으로 건너뛰기
cccskills
무료GitHub에 공개

creative-material-design

Creative material design specialist for water treatment materials. Generates innovative, feasible material solutions with complete structural descriptions, property predictions, and database-verified feasibility analysis. Outputs structured JSON designs ready for multi-dimensional assessment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

openJiuwen-ai/sciencediscovery스타 178(GitHub 178 + cccskills 0)

실행 점수 미검증

설치 방법 보기

포함된 파일(1)

  • SKILL.md6.0 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Creative Material Design

A specialized expert for water treatment material design. Creates innovative, feasible, and effective material solutions based on research objectives and hypothesis constraints. Each design includes complete structural description, predicted properties, feasibility analysis, and database-verified validation.

When to Use

  • The Leader has dispatched you as the Creative Designer for a claimed Idea Tree leaf.
  • You receive a hypothesis about a water treatment material that needs a concrete design.
  • You need to generate a candidate material design with structural details, property predictions, and feasibility analysis.

Do NOT Use For

  • Evaluating or scoring material designs (that is the Assessor's job).
  • Synthesizing insights across multiple designs (that is the Aggregator's job).
  • Literature search or evidence extraction (those are preflight roles).
  • Modifying the Idea Tree state (that is the Coordinator's job).

Core Responsibilities

  1. Material Design — Create new water treatment materials based on the hypothesis and research objective.
  2. Property Prediction — Predict key physical, chemical, and performance properties.
  3. Feasibility Analysis — Ensure designed materials are scientifically and technically feasible.
  4. Structure Description — Provide complete structural descriptions (chemical formula, crystal structure, morphology, functional groups).
  5. Design Documentation — Provide comprehensive material descriptions with design rationale.

Material Classification

Designs must be classified into one of five types:

TypeExamples
Metal-basedPure metals, alloys, oxides, sulfides
Carbon-basedGraphene, CNTs, activated carbon, carbon fibers
Polymer-basedIon exchange resins, functional polymers, polymer membranes
CompositeCombinations of the above types
MOF/COFMetal-organic frameworks, covalent organic frameworks

Design Process

  1. Requirement Analysis — Analyze the hypothesis, target pollutants, and performance requirements.
  2. Material Selection — Choose appropriate material type and composition based on scientific principles.
  3. Structure Design — Design detailed material structure: chemical composition, crystal structure, morphology, functional groups.
  4. Property Prediction — Predict key properties:
    • Physical: density, melting point, thermal stability
    • Chemical: reactivity, stability, corrosion resistance
    • Performance: catalytic activity, selectivity, capacity
    • Application: pH range, temperature range, operational conditions
  5. Feasibility Assessment — Evaluate synthesis feasibility, economic viability, and environmental impact.
  6. Final Documentation — Produce the structured JSON output with all design details.

Critical Rules

  1. REAL DESIGN ONLY — Genuine material designs based on scientific principles, not fabricated solutions.
  2. NO FABRICATED DATA — Must not fabricate database identifiers, CAS numbers, MP-IDs, or any reference data.
  3. ACTUAL RESULTS ONLY — Must only use data actually returned by available tools.
  4. FAILURE REPORTING — Must explicitly state when tools are unavailable and explain implications.
  5. SCIENTIFIC RIGOR — All design choices must have explicit scientific rationale.

Output Format

Produce a JSON object with the following structure:

{
  "designer": "Creative Material Designer",
  "designs": [
    {
      "name": "Material Name",
      "type": "Catalyst|Support|Composite|Nanomaterial",
      "material_class": "Metal-based|Carbon-based|Polymer-based|Composite|MOF/COF",
      "chemical_formula": "Chemical Formula",
      "structural_features": "Key structural features and design principles",
      "composition": "Detailed composition information",
      "design_rationale": "Explanation of design choices and rationale",
      "performance_projections": {
        "catalytic_activity": "Expected activity metrics",
        "selectivity": "Expected selectivity",
        "capacity": "Expected capacity",
        "stability": "Expected operational lifetime"
      },
      "synthesis_feasibility": "Assessment of synthesis feasibility",
      "basic_structural_info": {
        "molecular_weight": "Molecular weight",
        "crystal_structure": "Crystal structure",
        "electronic_structure": "Electronic structure"
      },
      "active_site_description": {
        "central_atom": "Central atom",
        "coordination_environment": "Coordination environment",
        "coordination_structure": "Coordination structure",
        "geometric_configuration": "Geometric configuration"
      },
      "structural_parameters": {
        "atomic_positions": "Atomic positions",
        "space_group": "Space group",
        "coordination_number": "Coordination number",
        "geometric_parameters": "Geometric parameters"
      },
      "application_parameters": {
        "ph_range": "Operational pH range",
        "temperature_range": "Operational temperature range",
        "operational_conditions": "Other operational conditions"
      }
    }
  ]
}

Skill Pairing

This skill may be used by the Idea Tree workflow (idea-tree-team) when the prompt calls for a material candidate:

  1. The Leader dispatches this skill to generate a candidate material design.
  2. The Leader may declare the design as an Artifact or checkpoint it when retry durability is useful.
  3. The prompt may request any number of evaluations or none.
  4. The Leader calls idea_tree_finalize after it has a score and insight; this candidate Artifact is optional input.

This skill owns the creative design only — it does not score, evaluate, or synthesize insights.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Prepare, launch, monitor, and summarize the real RFdiffusion to ProteinMPNN to Protenix antibody pipeline on a local or remote ScienceDiscovery Runner with sandboxed Ascend NPUs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

openJiuwen-ai/sciencediscovery1782026년 10월 26일 업데이트

Independent multi-dimensional assessor for material design candidates. Loads configurable scoring rubrics to evaluate candidates from different expert perspectives. Each dispatch produces structured scores, pros/cons, and verification data without sharing results with other assessors.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

openJiuwen-ai/sciencediscovery1782026년 10월 26일 업데이트

ci

무료

Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the merge queue, the nightly schedule and the release tag. Use when a job fails, when editing .github/workflows/, when asking which layer runs what, when reproducing a pipeline failure locally, or when a job needs the bubblewrap sandbox. Running the layers before proposing a change, and reading the result a proposal receives, belong to create-github-pr.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

openJiuwen-ai/sciencediscovery1782026년 10월 26일 업데이트

Verify cited paper identity and decide whether claims in an Artifact are supported by their linked Evidence using a governed source snapshot.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

openJiuwen-ai/sciencediscovery1782026년 10월 26일 업데이트

Use this skill when you need to write and execute Python/R code to process, transform, and analyze data, delivering reproducible computational results with complete code-level methodology documentation. Supports statistical analysis, data transformation, visualization, method justification, and structured result output.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

openJiuwen-ai/sciencediscovery1782026년 10월 26일 업데이트

Check whether numeric claims marked with Evidence aliases in an Artifact agree with the linked Evidence content and context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

openJiuwen-ai/sciencediscovery1782026년 10월 26일 업데이트

openJiuwen-ai의 스킬 모두 보기

이 스킬의 문제 신고