Skills Plugins MCP Prompt Model 博客 我的中心

materials-science

Analyzes material properties including crystal structures, phase diagrams, mechanical/thermal/electronic properties, and supports materials discovery through computational approaches; trigger when users discuss alloys, ceramics, polymers, nanomaterials, or materials characterization.

DeepseekModel Curated skill Quality Excellent · 90 v1.0.0

Get

https://deepseekmodel.com/api/download.php?id=beita6969-scienceclaw-skills-materials-science-skill-md&format=skill
Download .skill Standard format with system_prompt and model_config, ready for any agent framework
The actual content of the system_prompt field in the .skill file.
name materials-science description Analyzes material properties including crystal structures, phase diagrams, mechanical/thermal/electronic properties, and supports materials discovery through computational approaches; trigger when users discuss alloys, ceramics, polymers, nanomaterials, or materials characterization. When to Trigger Activate this skill when the user mentions: Crystal structures, lattice parameters, space groups, unit cells Phase diagrams, phase transitions, thermodynamic stability Mechanical properties (tensile strength, hardness, elastic modulus) Electronic properties (band gap, conductivity, dielectric constant) Materials characterization (XRD, SEM, TEM, AFM) Nanomaterials, thin films, composites, polymers Materials databases, high-throughput screening, materials informatics Step-by-Step Methodology Define the materials question - Specify the material system (elements, compounds), property of interest, and application context (structural, electronic, optical, catalytic). Database search - Query Materials Project, AFLOW, ICSD, or OQMD for known structures and computed properties. Check experimental databases (Springer Materials, NIST) for measured values. Structure analysis - Identify crystal system, space group, and Wyckoff positions. Compute lattice parameters and density. For disordered systems, characterize using pair distribution functions or radial distribution functions. Property evaluation - Retrieve or compute relevant properties: formation energy (thermodynamic stability), band structure (electronic), phonon dispersion (thermal), elastic tensor (mechanical). Compare with target specifications. Phase diagram analysis - Construct or retrieve phase diagrams (binary, ternary). Identify stable phases, invariant reactions (eutectic, peritectic), and solid solutions. Use CALPHAD method for complex systems. Characterization guidance - Recommend appropriate techniques: XRD for crystal structure, SEM/TEM for microstructure, XPS for surface chemistry, DSC for thermal transitions. Specify expected peaks/features. Design recommendations - Suggest composition or processing modifications to achieve target properties. Consider trade-offs between competing properties (strength vs. ductility, conductivity vs. transparency). Key Databases and Tools Materials Project - Computed materials properties (DFT) AFLOW - Automatic FLOW for materials discovery ICSD - Inorganic Crystal Structure Database NIST Materials Data - Experimental property data Springer Materials - Curated materials data Thermo-Calc / FactSage - CALPHAD thermodynamic modeling Output Format Crystal structures with space group, lattice parameters (in Angstroms), and atomic positions. Properties in SI units with comparison to reference values. Phase diagrams with labeled phases, invariant points, and temperature/composition axes. Characterization predictions (expected XRD peaks with 2-theta and hkl, expected spectral features). Quality Checklist Crystal structure validated against experimental data when available Property values compared between computational and experimental sources Temperature and pressure conditions specified for all properties Appropriate computational method noted (DFT functional, basis set) Phase diagram includes metastable phases if relevant Synthesis feasibility and processing conditions considered Units consistent and clearly stated throughout Uncertainty or accuracy of computational predictions discussed
Keywords that activate this skill. Click one to copy it.

This skill does not provide trigger words.

The downloaded .skill package contains the following fields.
Field Description
formatFormat tag (skill/v1)
skill_idUnique skill ID
nameSkill name
versionVersion
descriptionDescription
categoryCategories (array)
trigger_wordsTrigger words
tagsTags
sourceSource
source_urlSource URL (this page)
exported_atExported at (set per download)
system_promptSystem prompt body
model_configModel config: provider / model / temperature / max_tokens / top_p
examplesExamples
install_guideImport guide for Coze / Dify / Claude / custom frameworks
The same skill can be exported in different platform formats.
.skill Standard format with system_prompt and model_config, ready for any agent framework Download
.skillpro Enhanced format with scripts, tools, dependencies and hooks Download
.json Plain JSON export with system_prompt and model parameters only Download
Coze Markdown with frontmatter, for Coze platform import Download
Dify Dify DSL, import directly after creating an app Download

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。