[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CX7VQ95P7RK0SMSPB2QVRG":3,"skill-same:01M6CX7VQ95P7RK0SMSPB2QVRG":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6CX7VQ95P7RK0SMSPB2QVRG","Materials Science",null,"Materials science fundamentals including crystal structures, mechanical properties, phase diagrams, polymers, ceramics, and composites for materials engineering applications.","ffsshhttiikk\u002Fopencode-agents-skills","ffsshhttiikk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F226346827?v=4","01M6CWD9RR3Y7VRQX3MXYC8FYH","01M6CWD9WVPYAZW0J82G1VKGHY",3,"MIT","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fmaterials-science\u002FSKILL.md",[],[18,5,19,20,21,22,23,24],"science","python","engineering","applications","diagrams","properties","polymers","2026-11-10 10:12:30",false,"---\nname: Materials Science\ndescription: Materials science fundamentals including crystal structures, mechanical properties, phase diagrams, polymers, ceramics, and composites for materials engineering applications.\nlicense: MIT\ncompatibility: python>=3.8\naudience: materials-scientists, engineers, researchers, students\ncategory: engineering\n---\n\n# Materials Science\n\n## What I Do\n\nI provide comprehensive materials science tools including crystal structure analysis, mechanical properties, phase diagrams, polymers, ceramics, and composite materials for materials engineering applications.\n\n## When to Use Me\n\n- Material selection and characterization\n- Mechanical property prediction\n- Phase diagram analysis\n- Failure analysis\n- Microstructure engineering\n- Corrosion analysis\n\n## Core Concepts\n\n- **Crystal Structures**: BCC, FCC, HCP, defects\n- **Mechanical Properties**: Strength, hardness, toughness\n- **Phase Diagrams**: Binary, ternary, invariant reactions\n- **Polymers**: Molecular weight, Tg, crystallinity\n- **Ceramics**: Brittle fracture, thermal properties\n- **Composites**: Rule of mixtures, laminate theory\n- **Corrosion**: Electrochemical, pitting, galvanic\n- **Materials Selection**: Ashby charts, indices\n\n## Code Examples\n\n### Crystal Structures\n\n```python\nimport numpy as np\n\ndef lattice_parameter_a(atomic_radius, structure):\n    if structure == 'BCC':\n        return 4 * atomic_radius \u002F np.sqrt(3)\n    elif structure == 'FCC':\n        return 2 * np.sqrt(2) * atomic_radius\n    elif structure == 'HCP':\n        return 2 * atomic_radius\n    return None\n\ndef atomic_packing_factor(structure):\n    if structure == 'BCC':\n        return np.pi * np.sqrt(3) \u002F 8\n    elif structure == 'FCC':\n        return np.pi \u002F np.sqrt(18)\n    elif structure == 'HCP':\n        return np.pi \u002F (3 * np.sqrt(2))\n    return None\n\ndef miller_indices_distance(d_hkl, a, h, k, l):\n    return a \u002F np.sqrt(h**2 + k**2 + l**2)\n\ndef schmid_factor(phi, lambda_):\n    return np.cos(np.radians(phi)) * np.cos(np.radians(lambda_))\n\ndef critical_resolved_shear_stress(tau_y, schmid_factor):\n    return tau_y \u002F schmid_factor\n\nr_Fe = 1.24e-10  # Angstroms\na_BCC = lattice_parameter_a(r_Fe, 'BCC')\nprint(f\"BCC lattice parameter: {a_BCC:.4f} Angstroms\")\nAPF = atomic_packing_factor('FCC')\nprint(f\"FCC atomic packing factor: {APF:.4f}\")\n```\n\n### Mechanical Properties\n\n```python\ndef youngs_modulus_voigt(E1, E2, V1):\n    return V1 * E1 + (1 - V1) * E2\n\ndef poisson_ratio_nu(E, G):\n    return E \u002F (2 * G) - 1\n\ndef yield_strength_hall_petch(d, d0, sigma0, ky):\n    return sigma0 + ky \u002F np.sqrt(d)\n\ndef work_hardening_exponent(true_strain, true_stress, n):\n    return np.log(true_stress) - n * np.log(true_stress \u002F K)\n\ndef fracture_toughness_KIC(Y, sigma, a):\n    return Y * sigma * np.sqrt(np.pi * a)\n\ndef creep_rate_A(sigma, Q, R, T, n):\n    return A * sigma**n * np.exp(-Q \u002F (R * T))\n\nE = 200e9  # GPa\nG = 80e9   # GPa\nnu = poisson_ratio_nu(E, G)\nprint(f\"Poisson ratio: {nu:.3f}\")\n```\n\n### Phase Diagrams\n\n```python\ndef lever_rule(C0, C_alpha, C_beta, f_alpha):\n    return f_alpha = (C_beta - C0) \u002F (C_beta - C_alpha)\n\ndef gibbs_phase_rule(F, C, P):\n    return F = C - P + 2\n\ndef ttt_diagram_start_time(A, Q, R, T):\n    return 1 \u002F A * np.exp(Q \u002F (R * T))\n\ndef continuous_cooling_transformation(T, t):\n    return np.exp(-((T - Ms) \u002F M)**2 \u002F (2 * t**2))\n\ndef invariant_reaction_type(composition_range):\n    if composition_range > 0:\n        return 'eutectic'\n    elif composition_range \u003C 0:\n        return 'eutectoid'\n    return 'peritectic'\n\ndef t0_temperature(T_melt, H_fus, delta_S):\n    return T_melt - H_fus \u002F delta_S\n\nC0, C_alpha, C_beta = 40, 10, 80\nf_alpha = lever_rule(C0, C_alpha, C_beta, 0)\nprint(f\"Alpha fraction: {f_alpha:.2%}\")\n```\n\n### Polymer Properties\n\n```python\ndef glass_transition_tpTg, delta_Cp):\n    return Tg + delta_Cp\n\ndef degree_of_crystallinity(X_c, Delta_H_m, Delta_H_100):\n    return Delta_H_m \u002F Delta_H_100 * 100\n\ndef number_average_molecular_weight(M0, DP):\n    return M0 * DP\n\ndef weight_average_molecular_weight(Mn, PDI):\n    return Mn * PDI\n\ndef mark_houwink_sakurada(M, K, a):\n    return K * M**a\n\ndef rheology_viscosity(eta0, shear_rate, n):\n    return eta0 * shear_rate**(n - 1)\n\ndef time_temperature_superposition(T, T_ref, aT, freq_ref):\n    return freq_ref * aT\n\nM0 = 100  # g\u002Fmol (monomer)\nDP = 1000\nMn = number_average_molecular_weight(M0, DP)\nprint(f\"Number average MW: {Mn:.0f} g\u002Fmol\")\n```\n\n### Composite Materials\n\n```python\ndef rule_of_mixtures_isostrain(E_c, E_f, V_f, E_m):\n    return E_c = E_m * (1 - V_f) + E_f * V_f\n\ndef rule_of_mixtures_isostress(E_c, E_f, V_f, E_m):\n    return E_c = 1 \u002F ((1 - V_f)\u002FE_m + V_f\u002FE_f)\n\ndef halpin_tsai_modulus(E_f, E_m, V_f, aspect_ratio):\n    return E_c = E_m * (1 + xi * eta * V_f) \u002F (1 - eta * V_f)\n\ndef laminate_stiffness(A_matrix, D_matrix):\n    return A, B, D\n\ndef shear_lag_model(sigma_m, sigma_f, s):\n    return sigma_f = sigma_m * (1 - np.exp(-s \u002F l)) \u002F (1 - V_f)\n\ndef fiber_volume_fraction(w_f, rho_f, rho_m):\n    return V_f = 1 \u002F (1 + (rho_m \u002F rho_f) * ((1 - w_f) \u002F w_f))\n\nV_f = 0.6  # 60% fiber volume\nE_f = 230e9  # GPa (carbon)\nE_m = 3.5e9  # GPa (epoxy)\nE_c = rule_of_mixtures_isostrain(E_f, E_m, V_f, E_m)\nprint(f\"Composite modulus: {E_c:.1f} GPa\")\n```\n\n## Best Practices\n\n1. **Microstructure-Property Relations**: Link structure to properties\n2. **Processing-Microstructure**: Control processing for desired structure\n3. **Testing**: Appropriate characterization techniques\n4. **Statistical Analysis**: Account for variability\n5. **Modeling**: Calibrate models with experimental data\n\n## Common Patterns\n\n```python\n# Materials selection (Ashby method)\ndef materials_index(E, rho, sigma_y):\n    return sigma_y \u002F rho**0.5\n```\n\n## Core Competencies\n\n1. Crystal structure and defects\n2. Mechanical properties\n3. Phase diagram analysis\n4. Composite materials\n5. Materials selection\n","# Materials Science\n\n## What I Do\n\nI provide comprehensive materials science tools including crystal structure analysis, mechanical properties, phase diagrams, polymers, ceramics, and composite materials for materials engineering applications.\n\n## When to Use Me\n\n- Material selection and characterization\n- Mechanical property prediction\n- Phase diagram analysis\n- Failure analysis\n- Microstructure engineering\n- Corrosion analysis\n\n## Core Concepts\n\n- **Crystal Structures**: BCC, FCC, HCP, defects\n- **Mechanical Properties**: Strength, hardness, toughness\n- **Phase Diagrams**: Binary, ternary, invariant reactions\n- **Polymers**: Molecular weight, Tg, crystallinity\n- **Ceramics**: Brittle fracture, thermal properties\n- **Composites**: Rule of mixtures, laminate theory\n- **Corrosion**: Electrochemical, pitting, galvanic\n- **Materials Selection**: Ashby charts, indices\n\n## Code Examples\n\n### Crystal Structures\n\n```python\nimport numpy as np\n\ndef lattice_parameter_a(atomic_radius, structure):\n    if structure == 'BCC':\n        return 4 * atomic_radius \u002F np.sqrt(3)\n    elif structure == 'FCC':\n        return 2 * np.sqrt(2) * atomic_radius\n    elif structure == 'HCP':\n        return 2 * atomic_radius\n    return None\n\ndef atomic_packing_factor(structure):\n    if structure == 'BCC':\n        return np.pi * np.sqrt(3) \u002F 8\n    elif structure == 'FCC':\n        return np.pi \u002F np.sqrt(18)\n    elif structure == 'HCP':\n        return np.pi \u002F (3 * np.sqrt(2))\n    return None\n\ndef miller_indices_distance(d_hkl, a, h, k, l):\n    return a \u002F np.sqrt(h**2 + k**2 + l**2)\n\ndef schmid_factor(phi, lambda_):\n    return np.cos(np.radians(phi)) * np.cos(np.radians(lambda_))\n\ndef critical_resolved_shear_stress(tau_y, schmid_factor):\n    return tau_y \u002F schmid_factor\n\nr_Fe = 1.24e-10  # Angstroms\na_BCC = lattice_parameter_a(r_Fe, 'BCC')\nprint(f\"BCC lattice parameter: {a_BCC:.4f} Angstroms\")\nAPF = atomic_packing_factor('FCC')\nprint(f\"FCC atomic packing factor: {APF:.4f}\")\n```\n\n### Mechanical Properties\n\n```python\ndef youngs_modulus_voigt(E1, E2, V1):\n    return V1 * E1 + (1 - V1) * E2\n\ndef poisson_ratio_nu(E, G):\n    return E \u002F (2 * G) - 1\n\ndef yield_strength_hall_petch(d, d0, sigma0, ky):\n    return sigma0 + ky \u002F np.sqrt(d)\n\ndef work_hardening_exponent(true_strain, true_stress, n):\n    return np.log(true_stress) - n * np.log(true_stress \u002F K)\n\ndef fracture_toughness_KIC(Y, sigma, a):\n    return Y * sigma * np.sqrt(np.pi * a)\n\ndef creep_rate_A(sigma, Q, R, T, n):\n    return A * sigma**n * np.exp(-Q \u002F (R * T))\n\nE = 200e9  # GPa\nG = 80e9   # GPa\nnu = poisson_ratio_nu(E, G)\nprint(f\"Poisson ratio: {nu:.3f}\")\n```\n\n### Phase Diagrams\n\n```python\ndef lever_rule(C0, C_alpha, C_beta, f_alpha):\n    return f_alpha = (C_beta - C0) \u002F (C_beta - C_alpha)\n\ndef gibbs_phase_rule(F, C, P):\n    return F = C - P + 2\n\ndef ttt_diagram_start_time(A, Q, R, T):\n    return 1 \u002F A * np.exp(Q \u002F (R * T))\n\ndef continuous_cooling_transformation(T, t):\n    return np.exp(-((T - Ms) \u002F M)**2 \u002F (2 * t**2))\n\ndef invariant_reaction_type(composition_range):\n    if composition_range > 0:\n        return 'eutectic'\n    elif composition_range \u003C 0:\n        return 'eutectoid'\n    return 'peritectic'\n\ndef t0_temperature(T_melt, H_fus, delta_S):\n    return T_melt - H_fus \u002F delta_S\n\nC0, C_alpha, C_beta = 40, 10, 80\nf_alpha = lever_rule(C0, C_alpha, C_beta, 0)\nprint(f\"Alpha fraction: {f_alpha:.2%}\")\n```\n\n### Polymer Properties\n\n```python\ndef glass_transition_tpTg, delta_Cp):\n    return Tg + delta_Cp\n\ndef degree_of_crystallinity(X_c, Delta_H_m, Delta_H_100):\n    return Delta_H_m \u002F Delta_H_100 * 100\n\ndef number_average_molecular_weight(M0, DP):\n    return M0 * DP\n\ndef weight_average_molecular_weight(Mn, PDI):\n    return Mn * PDI\n\ndef mark_houwink_sakurada(M, K, a):\n    return K * M**a\n\ndef rheology_viscosity(eta0, shear_rate, n):\n    return eta0 * shear_rate**(n - 1)\n\ndef time_temperature_superposition(T, T_ref, aT, freq_ref):\n    return freq_ref * aT\n\nM0 = 100  # g\u002Fmol (monomer)\nDP = 1000\nMn = number_average_molecular_weight(M0, DP)\nprint(f\"Number average MW: {Mn:.0f} g\u002Fmol\")\n```\n\n### Composite Materials\n\n```python\ndef rule_of_mixtures_isostrain(E_c, E_f, V_f, E_m):\n    return E_c = E_m * (1 - V_f) + E_f * V_f\n\ndef rule_of_mixtures_isostress(E_c, E_f, V_f, E_m):\n    return E_c = 1 \u002F ((1 - V_f)\u002FE_m + V_f\u002FE_f)\n\ndef halpin_tsai_modulus(E_f, E_m, V_f, aspect_ratio):\n    return E_c = E_m * (1 + xi * eta * V_f) \u002F (1 - eta * V_f)\n\ndef laminate_stiffness(A_matrix, D_matrix):\n    return A, B, D\n\ndef shear_lag_model(sigma_m, sigma_f, s):\n    return sigma_f = sigma_m * (1 - np.exp(-s \u002F l)) \u002F (1 - V_f)\n\ndef fiber_volume_fraction(w_f, rho_f, rho_m):\n    return V_f = 1 \u002F (1 + (rho_m \u002F rho_f) * ((1 - w_f) \u002F w_f))\n\nV_f = 0.6  # 60% fiber volume\nE_f = 230e9  # GPa (carbon)\nE_m = 3.5e9  # GPa (epoxy)\nE_c = rule_of_mixtures_isostrain(E_f, E_m, V_f, E_m)\nprint(f\"Composite modulus: {E_c:.1f} GPa\")\n```\n\n## Best Practices\n\n1. **Microstructure-Property Relations**: Link structure to properties\n2. **Processing-Microstructure**: Control processing for desired structure\n3. **Testing**: Appropriate characterization techniques\n4. **Statistical Analysis**: Account for variability\n5. **Modeling**: Calibrate models with experimental data\n\n## Common Patterns\n\n```python\n# Materials selection (Ashby method)\ndef materials_index(E, rho, sigma_y):\n    return sigma_y \u002F rho**0.5\n```\n\n## Core Competencies\n\n1. Crystal structure and defects\n2. Mechanical properties\n3. Phase diagram analysis\n4. Composite materials\n5. Materials selection\n",{"name":5,"license":14,"audience":30,"category":20,"description":7,"compatibility":31},"materials-scientists, engineers, researchers, students","python>=3.8","main","5f7a3e453c98261f93d19a6a7de44ad8f7b72d41","materials-science",2,"https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk","2026-03-01 06:55:40",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill \"Materials Science\"",{"tool":45,"command":46},"bunx","bunx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill \"Materials Science\"",{"tool":48,"command":49},"pnpm","pnpm dlx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill \"Materials Science\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fmaterials-science\u002FSKILL.md",true,[53,59,63,67,71],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"prompts\u002Falternative-investments.md","REFERENCE","参考文档",18232,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fwealth-advisory\u002Fprompts\u002Falternative-investments.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"prompts\u002Festate-tax-planning.md",18043,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fwealth-advisory\u002Fprompts\u002Festate-tax-planning.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"prompts\u002Ffinancial-planning.md",16589,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fwealth-advisory\u002Fprompts\u002Ffinancial-planning.md",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"prompts\u002Fportfolio-construction.md",21977,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fwealth-advisory\u002Fprompts\u002Fportfolio-construction.md",{"path":72,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":73,"sourceHtmlUrl":74},"prompts\u002Fprivate-banking.md",14904,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fwealth-advisory\u002Fprompts\u002Fprivate-banking.md",[76,88,97,106,116,125],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":25},"01M6CXT9TXDF79BWJTMQAPB49G","xamarin","Xamarin cross-platform development","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fxamarin\u002FSKILL.md",[],[78,83,84,85,86,87],"platform","cross-platform","mobile","opencode","development",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":25},"01M6CXT8AD04MFYDA32VW3FKAG","wrangling","Data wrangling fundamentals","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwrangling\u002FSKILL.md",[],[90,95,86,18,96],"data wrangling","data",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":25},"01M6CXT717GCN7SRRNPBDP4508","windows","Windows operating system administration and scripting","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwindows\u002FSKILL.md",[],[99,104,86,105],"system","scripting",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":25},"01M6CXT54K794NMEM3XAPZZDKT","wide-column","Wide-column data model","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwide-column\u002FSKILL.md",[],[113,114,86,115,96],"wide column","databases","model",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":25},"01M6CXT28FMT2P4V9GZE67WA8E","wide-column-stores","Wide-column database stores","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwide-column-stores\u002FSKILL.md",[],[123,114,86,124],"wide column stores","database",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":25},"01M6CXT0D0M0Q4T2N7C2RX7DSN","websockets","WebSocket implementation and best practices","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwebsockets\u002FSKILL.md",[],[127,132,133,134,86,135,136],"websocket","real-time","time","best practices","implementation"]