[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CXBEV6H5G654RN5HCJT8K5":3,"skill-same:01M6CXBEV6H5G654RN5HCJT8K5":57},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":37,"commitSha":38,"skillDirectory":18,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M6CXBEV6H5G654RN5HCJT8K5","Neuroscience",null,"Neural science including neuronal modeling, synaptic transmission, neural networks, brain imaging analysis, and cognitive neuroscience for biomedical 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\u002Fneuroscience\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28],"neuroscience","python","neural networks","networks","applications","analysis","science","Neural","brain","biomedical","modeling","2026-11-10 10:12:30",false,"---\nname: Neuroscience\ndescription: Neural science including neuronal modeling, synaptic transmission, neural networks, brain imaging analysis, and cognitive neuroscience for biomedical applications.\nlicense: MIT\ncompatibility: python>=3.8\naudience: neuroscientists, cognitive-scientists, researchers, medical-professionals\ncategory: biology\n---\n\n# Neuroscience\n\n## What I Do\n\nI provide comprehensive neuroscience tools including neuronal modeling, synaptic dynamics, neural network analysis, brain imaging quantification, EEG\u002FMEG signal processing, and cognitive assessment for biomedical research applications.\n\n## When to Use Me\n\n- Neuronal spiking models\n- Synaptic plasticity analysis\n- Brain imaging data analysis\n- Neural signal processing\n- Cognitive testing analysis\n- Neuropharmacology studies\n\n## Core Concepts\n\n- **Neuronal Models**: Hodgkin-Huxley, integrate-and-fire\n- **Synaptic Transmission**: Neurotransmitter release, receptors\n- **Synaptic Plasticity**: LTP, LTD, STDP\n- **Neural Networks**: Connectivity, activity patterns\n- **Brain Imaging**: fMRI, PET, structural analysis\n- **Neural Signals**: EEG, MEG, LFP analysis\n- **Cognitive Neuroscience**: Behavioral paradigms\n- **Neuropharmacology**: Drug-receptor interactions\n\n## Code Examples\n\n### Hodgkin-Huxley Model\n\n```python\nimport numpy as np\n\ndef alpha_n(V):\n    return 0.01 * (V + 55) \u002F (1 - np.exp(-(V + 55) \u002F 10))\n\ndef beta_n(V):\n    return 0.125 * np.exp(-(V + 65) \u002F 80)\n\ndef alpha_m(V):\n    return 0.1 * (V + 40) \u002F (1 - np.exp(-(V + 40) \u002F 10))\n\ndef beta_m(V):\n    return 4 * np.exp(-(V + 65) \u002F 18)\n\ndef alpha_h(V):\n    return 0.07 * np.exp(-(V + 65) \u002F 20)\n\ndef beta_h(V):\n    return 1 \u002F (1 + np.exp(-(V + 35) \u002F 10))\n\ndef hodgkin_huxley_step(V, n, m, h, dt, I_ext):\n    dn = (alpha_n(V) * (1 - n) - beta_n(V) * n) * dt\n    dm = (alpha_m(V) * (1 - m) - beta_m(V) * m) * dt\n    dh = (alpha_h(V) * (1 - h) - beta_h(V) * h) * dt\n    \n    dV = (I_ext - 36 * n**4 * (V - 12) - 120 * m**3 * h * (V + 115) - 0.3 * (V + 10.613)) * dt\n    \n    return V + dV, n + dn, m + dm, h + dh\n\ndef simulate_hh(dt=0.01, T=100, I_inj=10):\n    V = -65\n    n = alpha_n(V) \u002F (alpha_n(V) + beta_n(V))\n    m = alpha_m(V) \u002F (alpha_m(V) + beta_m(V))\n    h = alpha_h(V) \u002F (alpha_h(V) + beta_h(V))\n    \n    t = np.arange(0, T, dt)\n    V_trace = np.zeros_like(t)\n    \n    for i, ti in enumerate(t):\n        V, n, m, h = hodgkin_huxley_step(V, n, m, h, dt, I_inj)\n        V_trace[i] = V\n    \n    return t, V_trace\n```\n\n### Integrate-and-Fire Model\n\n```python\nclass LeakyIntegrateAndFire:\n    def __init__(self, C=1, gL=0.1, EL=-70, Vth=-50, Vreset=-75, tau_ref=2):\n        self.C = C\n        self.gL = gL\n        self.EL = EL\n        self.Vth = Vth\n        self.Vreset = Vreset\n        self.tau_ref = tau_ref\n        self.V = EL\n    \n    def update(self, I, dt):\n        if self.tau_ref > 0:\n            self.tau_ref -= dt\n            return False\n        \n        dV = (-self.gL * (self.V - self.EL) + I) \u002F self.C * dt\n        self.V += dV\n        \n        if self.V >= self.Vth:\n            self.V = self.Vreset\n            self.tau_ref = 2\n            return True\n        return False\n    \n    def simulate(self, I_func, T, dt):\n        t = np.arange(0, T, dt)\n        spikes = []\n        V_trace = []\n        \n        for ti in t:\n            I = I_func(ti) if callable(I_func) else I\n            spiked = self.update(I, dt)\n            if spiked:\n                spikes.append(ti)\n            V_trace.append(self.V)\n        \n        return np.array(t), np.array(V_trace), np.array(spikes)\n\nneuron = LeakyIntegrateAndFire()\nt, V, spikes = neuron.simulate(lambda t: 2.5, 100, 0.1)\nprint(f\"Spike count: {len(spikes)}\")\nprint(f\"Average firing rate: {len(spikes) \u002F 100 * 1000:.1f} Hz\")\n```\n\n### Spike Timing Dependent Plasticity\n\n```python\ndef stdp_rule(dt, A_plus=1, tau_plus=20, A_minus=1, tau_minus=20):\n    if dt > 0:\n        return A_plus * np.exp(-dt \u002F tau_plus)\n    else:\n        return -A_minus * np.exp(dt \u002F tau_minus)\n\ndef update_weights_stdp(weights, pre_spikes, post_spikes, dt, time_window=100):\n    dw = np.zeros_like(weights)\n    \n    for i, t_pre in enumerate(pre_spikes):\n        for j, t_post in enumerate(post_spikes):\n            delta_t = t_post - t_pre\n            if abs(delta_t) \u003C= time_window:\n                dw[i, j] = stdp_rule(delta_t)\n    \n    weights = np.clip(weights + dw, 0, 1)\n    return weights\n\ndef hebbian_learning(pre_activity, post_activity, learning_rate=0.01):\n    delta_w = learning_rate * np.outer(pre_activity, post_activity)\n    return delta_w\n\ndef oja's_rule(pre_activity, post_activity, w, alpha=0.001):\n    delta_w = post_activity * (pre_activity - alpha * post_activity * w)\n    return delta_w\n```\n\n### Neural Signal Processing\n\n```python\nfrom scipy import signal\n\ndef bandpower(data, fs, band):\n    f, Pxx = signal.welch(data, fs=fs, nperseg=1024)\n    idx_band = np.logical_and(f >= band[0], f \u003C= band[1])\n    return np.trapz(Pxx[idx_band], f[idx_band])\n\ndef extract_lfp_features(lfp_signal, sampling_rate=1000):\n    theta = bandpower(lfp_signal, sampling_rate, [4, 8])\n    gamma = bandpower(lfp_signal, sampling_rate, [30, 100])\n    delta = bandpower(lfp_signal, sampling_rate, [0.5, 4])\n    \n    return {'theta': theta, 'gamma': gamma, 'delta': delta}\n\ndef detect_spikes_amplitude(data, threshold=-3):\n    std = np.std(data)\n    mean = np.mean(data)\n    threshold_val = mean + threshold * std\n    \n    spikes = np.where(data > threshold_val)[0]\n    return spikes\n\ndef coherence_analysis(signal1, signal2, fs=1000):\n    f, Cxy = signal.coherence(signal1, signal2, fs=fs, nperseg=256)\n    return f, Cxy\n```\n\n### fMRI Analysis Basics\n\n```python\ndef spm_hrf(TR, num_volumes):\n    import scipy.stats as stats\n    d = np.arange(0, num_volumes * TR, TR)\n    hrf = stats.gamma.pdf(d, 6) - stats.gamma.pdf(d, 16) \u002F 6\n    return hrf \u002F np.sum(hrf)\n\ndef motion_correction(motion_params):\n    corrections = {\n        'translation_x': motion_params[0],\n        'translation_y': motion_params[1],\n        'translation_z': motion_params[2],\n        'rotation_x': motion_params[3],\n        'rotation_y': motion_params[4],\n        'rotation_z': motion_params[5]\n    }\n    return corrections\n\ndef compute_beta_maps(design_matrix, bold_timeseries):\n    betas = np.linalg.lstsq(design_matrix, bold_timeseries, rcond=None)[0]\n    return betas\n\ndef roi_timeseries提取(roi_mask, bold_data):\n    n_timepoints = bold_data.shape[3]\n    roi_ts = np.zeros(n_timepoints)\n    for t in range(n_timepoints):\n        roi_ts[t] = np.mean(bold_data[:, :, :, t][roi_mask])\n    return roi_ts\n```\n\n## Best Practices\n\n1. **Model Validation**: Compare with experimental data\n2. **Parameter Sensitivity**: Test parameter ranges\n3. **Noise**: Include realistic noise models\n4. **Spatial Resolution**: Consider imaging limitations\n5. **Multiple Comparisons**: Correct for fMRI analysis\n\n## Common Patterns\n\n```python\n# Firing rate calculation\ndef firing_rate(spike_times, bin_size, time_range):\n    bins = np.arange(time_range[0], time_range[1] + bin_size, bin_size)\n    counts, _ = np.histogram(spike_times, bins)\n    return counts \u002F bin_size\n\n# Information theory measures\ndef mutual_information(rate1, rate2):\n    from sklearn.metrics import mutual_info_score\n    return mutual_info_score(rate1, rate2)\n\n# Neural decoding\ndef neural_decoding(patterns, labels):\n    from sklearn.linear_model import LogisticRegression\n    clf = LogisticRegression()\n    clf.fit(patterns, labels)\n    return clf.score(patterns, labels)\n```\n\n## Core Competencies\n\n1. Biophysical neuron modeling\n2. Synaptic plasticity mechanisms\n3. Neural signal processing\n4. Brain imaging analysis\n5. Cognitive paradigm analysis\n","# Neuroscience\n\n## What I Do\n\nI provide comprehensive neuroscience tools including neuronal modeling, synaptic dynamics, neural network analysis, brain imaging quantification, EEG\u002FMEG signal processing, and cognitive assessment for biomedical research applications.\n\n## When to Use Me\n\n- Neuronal spiking models\n- Synaptic plasticity analysis\n- Brain imaging data analysis\n- Neural signal processing\n- Cognitive testing analysis\n- Neuropharmacology studies\n\n## Core Concepts\n\n- **Neuronal Models**: Hodgkin-Huxley, integrate-and-fire\n- **Synaptic Transmission**: Neurotransmitter release, receptors\n- **Synaptic Plasticity**: LTP, LTD, STDP\n- **Neural Networks**: Connectivity, activity patterns\n- **Brain Imaging**: fMRI, PET, structural analysis\n- **Neural Signals**: EEG, MEG, LFP analysis\n- **Cognitive Neuroscience**: Behavioral paradigms\n- **Neuropharmacology**: Drug-receptor interactions\n\n## Code Examples\n\n### Hodgkin-Huxley Model\n\n```python\nimport numpy as np\n\ndef alpha_n(V):\n    return 0.01 * (V + 55) \u002F (1 - np.exp(-(V + 55) \u002F 10))\n\ndef beta_n(V):\n    return 0.125 * np.exp(-(V + 65) \u002F 80)\n\ndef alpha_m(V):\n    return 0.1 * (V + 40) \u002F (1 - np.exp(-(V + 40) \u002F 10))\n\ndef beta_m(V):\n    return 4 * np.exp(-(V + 65) \u002F 18)\n\ndef alpha_h(V):\n    return 0.07 * np.exp(-(V + 65) \u002F 20)\n\ndef beta_h(V):\n    return 1 \u002F (1 + np.exp(-(V + 35) \u002F 10))\n\ndef hodgkin_huxley_step(V, n, m, h, dt, I_ext):\n    dn = (alpha_n(V) * (1 - n) - beta_n(V) * n) * dt\n    dm = (alpha_m(V) * (1 - m) - beta_m(V) * m) * dt\n    dh = (alpha_h(V) * (1 - h) - beta_h(V) * h) * dt\n    \n    dV = (I_ext - 36 * n**4 * (V - 12) - 120 * m**3 * h * (V + 115) - 0.3 * (V + 10.613)) * dt\n    \n    return V + dV, n + dn, m + dm, h + dh\n\ndef simulate_hh(dt=0.01, T=100, I_inj=10):\n    V = -65\n    n = alpha_n(V) \u002F (alpha_n(V) + beta_n(V))\n    m = alpha_m(V) \u002F (alpha_m(V) + beta_m(V))\n    h = alpha_h(V) \u002F (alpha_h(V) + beta_h(V))\n    \n    t = np.arange(0, T, dt)\n    V_trace = np.zeros_like(t)\n    \n    for i, ti in enumerate(t):\n        V, n, m, h = hodgkin_huxley_step(V, n, m, h, dt, I_inj)\n        V_trace[i] = V\n    \n    return t, V_trace\n```\n\n### Integrate-and-Fire Model\n\n```python\nclass LeakyIntegrateAndFire:\n    def __init__(self, C=1, gL=0.1, EL=-70, Vth=-50, Vreset=-75, tau_ref=2):\n        self.C = C\n        self.gL = gL\n        self.EL = EL\n        self.Vth = Vth\n        self.Vreset = Vreset\n        self.tau_ref = tau_ref\n        self.V = EL\n    \n    def update(self, I, dt):\n        if self.tau_ref > 0:\n            self.tau_ref -= dt\n            return False\n        \n        dV = (-self.gL * (self.V - self.EL) + I) \u002F self.C * dt\n        self.V += dV\n        \n        if self.V >= self.Vth:\n            self.V = self.Vreset\n            self.tau_ref = 2\n            return True\n        return False\n    \n    def simulate(self, I_func, T, dt):\n        t = np.arange(0, T, dt)\n        spikes = []\n        V_trace = []\n        \n        for ti in t:\n            I = I_func(ti) if callable(I_func) else I\n            spiked = self.update(I, dt)\n            if spiked:\n                spikes.append(ti)\n            V_trace.append(self.V)\n        \n        return np.array(t), np.array(V_trace), np.array(spikes)\n\nneuron = LeakyIntegrateAndFire()\nt, V, spikes = neuron.simulate(lambda t: 2.5, 100, 0.1)\nprint(f\"Spike count: {len(spikes)}\")\nprint(f\"Average firing rate: {len(spikes) \u002F 100 * 1000:.1f} Hz\")\n```\n\n### Spike Timing Dependent Plasticity\n\n```python\ndef stdp_rule(dt, A_plus=1, tau_plus=20, A_minus=1, tau_minus=20):\n    if dt > 0:\n        return A_plus * np.exp(-dt \u002F tau_plus)\n    else:\n        return -A_minus * np.exp(dt \u002F tau_minus)\n\ndef update_weights_stdp(weights, pre_spikes, post_spikes, dt, time_window=100):\n    dw = np.zeros_like(weights)\n    \n    for i, t_pre in enumerate(pre_spikes):\n        for j, t_post in enumerate(post_spikes):\n            delta_t = t_post - t_pre\n            if abs(delta_t) \u003C= time_window:\n                dw[i, j] = stdp_rule(delta_t)\n    \n    weights = np.clip(weights + dw, 0, 1)\n    return weights\n\ndef hebbian_learning(pre_activity, post_activity, learning_rate=0.01):\n    delta_w = learning_rate * np.outer(pre_activity, post_activity)\n    return delta_w\n\ndef oja's_rule(pre_activity, post_activity, w, alpha=0.001):\n    delta_w = post_activity * (pre_activity - alpha * post_activity * w)\n    return delta_w\n```\n\n### Neural Signal Processing\n\n```python\nfrom scipy import signal\n\ndef bandpower(data, fs, band):\n    f, Pxx = signal.welch(data, fs=fs, nperseg=1024)\n    idx_band = np.logical_and(f >= band[0], f \u003C= band[1])\n    return np.trapz(Pxx[idx_band], f[idx_band])\n\ndef extract_lfp_features(lfp_signal, sampling_rate=1000):\n    theta = bandpower(lfp_signal, sampling_rate, [4, 8])\n    gamma = bandpower(lfp_signal, sampling_rate, [30, 100])\n    delta = bandpower(lfp_signal, sampling_rate, [0.5, 4])\n    \n    return {'theta': theta, 'gamma': gamma, 'delta': delta}\n\ndef detect_spikes_amplitude(data, threshold=-3):\n    std = np.std(data)\n    mean = np.mean(data)\n    threshold_val = mean + threshold * std\n    \n    spikes = np.where(data > threshold_val)[0]\n    return spikes\n\ndef coherence_analysis(signal1, signal2, fs=1000):\n    f, Cxy = signal.coherence(signal1, signal2, fs=fs, nperseg=256)\n    return f, Cxy\n```\n\n### fMRI Analysis Basics\n\n```python\ndef spm_hrf(TR, num_volumes):\n    import scipy.stats as stats\n    d = np.arange(0, num_volumes * TR, TR)\n    hrf = stats.gamma.pdf(d, 6) - stats.gamma.pdf(d, 16) \u002F 6\n    return hrf \u002F np.sum(hrf)\n\ndef motion_correction(motion_params):\n    corrections = {\n        'translation_x': motion_params[0],\n        'translation_y': motion_params[1],\n        'translation_z': motion_params[2],\n        'rotation_x': motion_params[3],\n        'rotation_y': motion_params[4],\n        'rotation_z': motion_params[5]\n    }\n    return corrections\n\ndef compute_beta_maps(design_matrix, bold_timeseries):\n    betas = np.linalg.lstsq(design_matrix, bold_timeseries, rcond=None)[0]\n    return betas\n\ndef roi_timeseries提取(roi_mask, bold_data):\n    n_timepoints = bold_data.shape[3]\n    roi_ts = np.zeros(n_timepoints)\n    for t in range(n_timepoints):\n        roi_ts[t] = np.mean(bold_data[:, :, :, t][roi_mask])\n    return roi_ts\n```\n\n## Best Practices\n\n1. **Model Validation**: Compare with experimental data\n2. **Parameter Sensitivity**: Test parameter ranges\n3. **Noise**: Include realistic noise models\n4. **Spatial Resolution**: Consider imaging limitations\n5. **Multiple Comparisons**: Correct for fMRI analysis\n\n## Common Patterns\n\n```python\n# Firing rate calculation\ndef firing_rate(spike_times, bin_size, time_range):\n    bins = np.arange(time_range[0], time_range[1] + bin_size, bin_size)\n    counts, _ = np.histogram(spike_times, bins)\n    return counts \u002F bin_size\n\n# Information theory measures\ndef mutual_information(rate1, rate2):\n    from sklearn.metrics import mutual_info_score\n    return mutual_info_score(rate1, rate2)\n\n# Neural decoding\ndef neural_decoding(patterns, labels):\n    from sklearn.linear_model import LogisticRegression\n    clf = LogisticRegression()\n    clf.fit(patterns, labels)\n    return clf.score(patterns, labels)\n```\n\n## Core Competencies\n\n1. Biophysical neuron modeling\n2. Synaptic plasticity mechanisms\n3. Neural signal processing\n4. Brain imaging analysis\n5. Cognitive paradigm analysis\n",{"name":5,"license":14,"audience":34,"category":35,"description":7,"compatibility":36},"neuroscientists, cognitive-scientists, researchers, medical-professionals","biology","python>=3.8","main","5f7a3e453c98261f93d19a6a7de44ad8f7b72d41",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":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill Neuroscience",{"tool":49,"command":50},"bunx","bunx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill Neuroscience",{"tool":52,"command":53},"pnpm","pnpm dlx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill Neuroscience","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fneuroscience\u002FSKILL.md",true,[],[58,70,79,88,98,107],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":29},"01M6CXT9TXDF79BWJTMQAPB49G","xamarin","Xamarin cross-platform development","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fxamarin\u002FSKILL.md",[],[60,65,66,67,68,69],"platform","cross-platform","mobile","opencode","development",{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":29},"01M6CXT8AD04MFYDA32VW3FKAG","wrangling","Data wrangling fundamentals","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwrangling\u002FSKILL.md",[],[72,77,68,24,78],"data wrangling","data",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":29},"01M6CXT717GCN7SRRNPBDP4508","windows","Windows operating system administration and scripting","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwindows\u002FSKILL.md",[],[81,86,68,87],"system","scripting",{"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":29},"01M6CXT54K794NMEM3XAPZZDKT","wide-column","Wide-column data model","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwide-column\u002FSKILL.md",[],[95,96,68,97,78],"wide column","databases","model",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":29},"01M6CXT28FMT2P4V9GZE67WA8E","wide-column-stores","Wide-column database stores","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwide-column-stores\u002FSKILL.md",[],[105,96,68,106],"wide column stores","database",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":29},"01M6CXT0D0M0Q4T2N7C2RX7DSN","websockets","WebSocket implementation and best practices","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwebsockets\u002FSKILL.md",[],[109,114,115,116,68,117,118],"websocket","real-time","time","best practices","implementation"]