[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFH04J58VNZKAXG4ZQK7VV":3,"skill-same:01M6AFH04J58VNZKAXG4ZQK7VV":151},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":16,"sourceHtmlUrl":17,"categories":18,"keywords":24,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6AFH04J58VNZKAXG4ZQK7VV","neuropixels-analysis",null,"Neuropixels neural recording analysis. Load SpikeGLX\u002FOpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen\u002FIBL curation, AI-assisted visual analysis, for Neuropixels 1.0\u002F2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FSKILL.md",[19],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"analysis","neuropixels analysis","visual","when","for","load","recording","curation","with","sorting","unit","quality metrics","spike","motion","Neural","recordings","use","open","data","metrics","2026-11-10 10:12:30",false,"---\nname: neuropixels-analysis\ndescription: \"Neuropixels neural recording analysis. Load SpikeGLX\u002FOpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen\u002FIBL curation, AI-assisted visual analysis, for Neuropixels 1.0\u002F2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.\"\n---\n\n# Neuropixels Data Analysis\n\n## Overview\n\nComprehensive toolkit for analyzing Neuropixels high-density neural recordings using current best practices from SpikeInterface, Allen Institute, and International Brain Laboratory (IBL). Supports the full workflow from raw data to publication-ready curated units.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Working with Neuropixels recordings (.ap.bin, .lf.bin, .meta files)\n- Loading data from SpikeGLX, Open Ephys, or NWB formats\n- Preprocessing neural recordings (filtering, CAR, bad channel detection)\n- Detecting and correcting motion\u002Fdrift in recordings\n- Running spike sorting (Kilosort4, SpykingCircus2, Mountainsort5)\n- Computing quality metrics (SNR, ISI violations, presence ratio)\n- Curating units using Allen\u002FIBL criteria\n- Creating visualizations of neural data\n- Exporting results to Phy or NWB\n\n## Supported Hardware & Formats\n\n| Probe | Electrodes | Channels | Notes |\n|-------|-----------|----------|-------|\n| Neuropixels 1.0 | 960 | 384 | Requires phase_shift correction |\n| Neuropixels 2.0 (single) | 1280 | 384 | Denser geometry |\n| Neuropixels 2.0 (4-shank) | 5120 | 384 | Multi-region recording |\n\n| Format | Extension | Reader |\n|--------|-----------|--------|\n| SpikeGLX | `.ap.bin`, `.lf.bin`, `.meta` | `si.read_spikeglx()` |\n| Open Ephys | `.continuous`, `.oebin` | `si.read_openephys()` |\n| NWB | `.nwb` | `si.read_nwb()` |\n\n## Quick Start\n\n### Basic Import and Setup\n\n```python\nimport spikeinterface.full as si\nimport neuropixels_analysis as npa\n\n# Configure parallel processing\njob_kwargs = dict(n_jobs=-1, chunk_duration='1s', progress_bar=True)\n```\n\n### Loading Data\n\n```python\n# SpikeGLX (most common)\nrecording = si.read_spikeglx('\u002Fpath\u002Fto\u002Fdata', stream_id='imec0.ap')\n\n# Open Ephys (common for many labs)\nrecording = si.read_openephys('\u002Fpath\u002Fto\u002FRecord_Node_101\u002F')\n\n# Check available streams\nstreams, ids = si.get_neo_streams('spikeglx', '\u002Fpath\u002Fto\u002Fdata')\nprint(streams)  # ['imec0.ap', 'imec0.lf', 'nidq']\n\n# For testing with subset of data\nrecording = recording.frame_slice(0, int(60 * recording.get_sampling_frequency()))\n```\n\n### Complete Pipeline (One Command)\n\n```python\n# Run full analysis pipeline\nresults = npa.run_pipeline(\n    recording,\n    output_dir='output\u002F',\n    sorter='kilosort4',\n    curation_method='allen',\n)\n\n# Access results\nsorting = results['sorting']\nmetrics = results['metrics']\nlabels = results['labels']\n```\n\n## Standard Analysis Workflow\n\n### 1. Preprocessing\n\n```python\n# Recommended preprocessing chain\nrec = si.highpass_filter(recording, freq_min=400)\nrec = si.phase_shift(rec)  # Required for Neuropixels 1.0\nbad_ids, _ = si.detect_bad_channels(rec)\nrec = rec.remove_channels(bad_ids)\nrec = si.common_reference(rec, operator='median')\n\n# Or use our wrapper\nrec = npa.preprocess(recording)\n```\n\n### 2. Check and Correct Drift\n\n```python\n# Check for drift (always do this!)\nmotion_info = npa.estimate_motion(rec, preset='kilosort_like')\nnpa.plot_drift(rec, motion_info, output='drift_map.png')\n\n# Apply correction if needed\nif motion_info['motion'].max() > 10:  # microns\n    rec = npa.correct_motion(rec, preset='nonrigid_accurate')\n```\n\n### 3. Spike Sorting\n\n```python\n# Kilosort4 (recommended, requires GPU)\nsorting = si.run_sorter('kilosort4', rec, folder='ks4_output')\n\n# CPU alternatives\nsorting = si.run_sorter('tridesclous2', rec, folder='tdc2_output')\nsorting = si.run_sorter('spykingcircus2', rec, folder='sc2_output')\nsorting = si.run_sorter('mountainsort5', rec, folder='ms5_output')\n\n# Check available sorters\nprint(si.installed_sorters())\n```\n\n### 4. Postprocessing\n\n```python\n# Create analyzer and compute all extensions\nanalyzer = si.create_sorting_analyzer(sorting, rec, sparse=True)\n\nanalyzer.compute('random_spikes', max_spikes_per_unit=500)\nanalyzer.compute('waveforms', ms_before=1.0, ms_after=2.0)\nanalyzer.compute('templates', operators=['average', 'std'])\nanalyzer.compute('spike_amplitudes')\nanalyzer.compute('correlograms', window_ms=50.0, bin_ms=1.0)\nanalyzer.compute('unit_locations', method='monopolar_triangulation')\nanalyzer.compute('quality_metrics')\n\nmetrics = analyzer.get_extension('quality_metrics').get_data()\n```\n\n### 5. Curation\n\n```python\n# Allen Institute criteria (conservative)\ngood_units = metrics.query(\"\"\"\n    presence_ratio > 0.9 and\n    isi_violations_ratio \u003C 0.5 and\n    amplitude_cutoff \u003C 0.1\n\"\"\").index.tolist()\n\n# Or use automated curation\nlabels = npa.curate(metrics, method='allen')  # 'allen', 'ibl', 'strict'\n```\n\n### 6. AI-Assisted Curation (For Uncertain Units)\n\nWhen using this skill with Claude Code, Claude can directly analyze waveform plots and provide expert curation decisions. For programmatic API access:\n\n```python\nfrom anthropic import Anthropic\n\n# Setup API client\nclient = Anthropic()\n\n# Analyze uncertain units visually\nuncertain = metrics.query('snr > 3 and snr \u003C 8').index.tolist()\n\nfor unit_id in uncertain:\n    result = npa.analyze_unit_visually(analyzer, unit_id, api_client=client)\n    print(f\"Unit {unit_id}: {result['classification']}\")\n    print(f\"  Reasoning: {result['reasoning'][:100]}...\")\n```\n\n**Claude Code Integration**: When running within Claude Code, ask Claude to examine waveform\u002Fcorrelogram plots directly - no API setup required.\n\n### 7. Generate Analysis Report\n\n```python\n# Generate comprehensive HTML report with visualizations\nreport_dir = npa.generate_analysis_report(results, 'output\u002F')\n# Opens report.html with summary stats, figures, and unit table\n\n# Print formatted summary to console\nnpa.print_analysis_summary(results)\n```\n\n### 8. Export Results\n\n```python\n# Export to Phy for manual review\nsi.export_to_phy(analyzer, output_folder='phy_export\u002F',\n                 compute_pc_features=True, compute_amplitudes=True)\n\n# Export to NWB\nfrom spikeinterface.exporters import export_to_nwb\nexport_to_nwb(rec, sorting, 'output.nwb')\n\n# Save quality metrics\nmetrics.to_csv('quality_metrics.csv')\n```\n\n## Common Pitfalls and Best Practices\n\n1. **Always check drift** before spike sorting - drift > 10μm significantly impacts quality\n2. **Use phase_shift** for Neuropixels 1.0 probes (not needed for 2.0)\n3. **Save preprocessed data** to avoid recomputing - use `rec.save(folder='preprocessed\u002F')`\n4. **Use GPU** for Kilosort4 - it's 10-50x faster than CPU alternatives\n5. **Review uncertain units manually** - automated curation is a starting point\n6. **Combine metrics with AI** - use metrics for clear cases, AI for borderline units\n7. **Document your thresholds** - different analyses may need different criteria\n8. **Export to Phy** for critical experiments - human oversight is valuable\n\n## Key Parameters to Adjust\n\n### Preprocessing\n- `freq_min`: Highpass cutoff (300-400 Hz typical)\n- `detect_threshold`: Bad channel detection sensitivity\n\n### Motion Correction\n- `preset`: 'kilosort_like' (fast) or 'nonrigid_accurate' (better for severe drift)\n\n### Spike Sorting (Kilosort4)\n- `batch_size`: Samples per batch (30000 default)\n- `nblocks`: Number of drift blocks (increase for long recordings)\n- `Th_learned`: Detection threshold (lower = more spikes)\n\n### Quality Metrics\n- `snr_threshold`: Signal-to-noise cutoff (3-5 typical)\n- `isi_violations_ratio`: Refractory violations (0.01-0.5)\n- `presence_ratio`: Recording coverage (0.5-0.95)\n\n## Bundled Resources\n\n### scripts\u002Fpreprocess_recording.py\nAutomated preprocessing script:\n```bash\npython scripts\u002Fpreprocess_recording.py \u002Fpath\u002Fto\u002Fdata --output preprocessed\u002F\n```\n\n### scripts\u002Frun_sorting.py\nRun spike sorting:\n```bash\npython scripts\u002Frun_sorting.py preprocessed\u002F --sorter kilosort4 --output sorting\u002F\n```\n\n### scripts\u002Fcompute_metrics.py\nCompute quality metrics and apply curation:\n```bash\npython scripts\u002Fcompute_metrics.py sorting\u002F preprocessed\u002F --output metrics\u002F --curation allen\n```\n\n### scripts\u002Fexport_to_phy.py\nExport to Phy for manual curation:\n```bash\npython scripts\u002Fexport_to_phy.py metrics\u002Fanalyzer --output phy_export\u002F\n```\n\n### assets\u002Fanalysis_template.py\nComplete analysis template. Copy and customize:\n```bash\ncp assets\u002Fanalysis_template.py my_analysis.py\n# Edit parameters and run\npython my_analysis.py\n```\n\n### reference\u002Fstandard_workflow.md\nDetailed step-by-step workflow with explanations for each stage.\n\n### reference\u002Fapi_reference.md\nQuick function reference organized by module.\n\n### reference\u002Fplotting_guide.md\nComprehensive visualization guide for publication-quality figures.\n\n## Detailed Reference Guides\n\n| Topic | Reference |\n|-------|-----------|\n| Full workflow | [reference\u002Fstandard_workflow.md](reference\u002Fstandard_workflow.md) |\n| API reference | [reference\u002Fapi_reference.md](reference\u002Fapi_reference.md) |\n| Plotting guide | [reference\u002Fplotting_guide.md](reference\u002Fplotting_guide.md) |\n| Preprocessing | [PREPROCESSING.md](PREPROCESSING.md) |\n| Spike sorting | [SPIKE_SORTING.md](SPIKE_SORTING.md) |\n| Motion correction | [MOTION_CORRECTION.md](MOTION_CORRECTION.md) |\n| Quality metrics | [QUALITY_METRICS.md](QUALITY_METRICS.md) |\n| Automated curation | [AUTOMATED_CURATION.md](AUTOMATED_CURATION.md) |\n| AI-assisted curation | [AI_CURATION.md](AI_CURATION.md) |\n| Waveform analysis | [ANALYSIS.md](ANALYSIS.md) |\n\n## Installation\n\n```bash\n# Core packages\npip install spikeinterface[full] probeinterface neo\n\n# Spike sorters\npip install kilosort          # Kilosort4 (GPU required)\npip install spykingcircus     # SpykingCircus2 (CPU)\npip install mountainsort5     # Mountainsort5 (CPU)\n\n# Our toolkit\npip install neuropixels-analysis\n\n# Optional: AI curation\npip install anthropic\n\n# Optional: IBL tools\npip install ibl-neuropixel ibllib\n```\n\n## Project Structure\n\n```\nproject\u002F\n├── raw_data\u002F\n│   └── recording_g0\u002F\n│       └── recording_g0_imec0\u002F\n│           ├── recording_g0_t0.imec0.ap.bin\n│           └── recording_g0_t0.imec0.ap.meta\n├── preprocessed\u002F           # Saved preprocessed recording\n├── motion\u002F                 # Motion estimation results\n├── sorting_output\u002F         # Spike sorter output\n├── analyzer\u002F               # SortingAnalyzer (waveforms, metrics)\n├── phy_export\u002F             # For manual curation\n├── ai_curation\u002F            # AI analysis reports\n└── results\u002F\n    ├── quality_metrics.csv\n    ├── curation_labels.json\n    └── output.nwb\n```\n\n## Additional Resources\n\n- **SpikeInterface Docs**: https:\u002F\u002Fspikeinterface.readthedocs.io\u002F\n- **Neuropixels Tutorial**: https:\u002F\u002Fspikeinterface.readthedocs.io\u002Fen\u002Fstable\u002Fhow_to\u002Fanalyze_neuropixels.html\n- **Kilosort4 GitHub**: https:\u002F\u002Fgithub.com\u002FMouseLand\u002FKilosort\n- **IBL Neuropixel Tools**: https:\u002F\u002Fgithub.com\u002Fint-brain-lab\u002Fibl-neuropixel\n- **Allen Institute ecephys**: https:\u002F\u002Fgithub.com\u002FAllenInstitute\u002Fecephys_spike_sorting\n- **Bombcell (Automated QC)**: https:\u002F\u002Fgithub.com\u002FJulie-Fabre\u002Fbombcell\n- **SpikeAgent (AI Curation)**: https:\u002F\u002Fgithub.com\u002FSpikeAgent\u002FSpikeAgent\n","# Neuropixels Data Analysis\n\n## Overview\n\nComprehensive toolkit for analyzing Neuropixels high-density neural recordings using current best practices from SpikeInterface, Allen Institute, and International Brain Laboratory (IBL). Supports the full workflow from raw data to publication-ready curated units.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Working with Neuropixels recordings (.ap.bin, .lf.bin, .meta files)\n- Loading data from SpikeGLX, Open Ephys, or NWB formats\n- Preprocessing neural recordings (filtering, CAR, bad channel detection)\n- Detecting and correcting motion\u002Fdrift in recordings\n- Running spike sorting (Kilosort4, SpykingCircus2, Mountainsort5)\n- Computing quality metrics (SNR, ISI violations, presence ratio)\n- Curating units using Allen\u002FIBL criteria\n- Creating visualizations of neural data\n- Exporting results to Phy or NWB\n\n## Supported Hardware & Formats\n\n| Probe | Electrodes | Channels | Notes |\n|-------|-----------|----------|-------|\n| Neuropixels 1.0 | 960 | 384 | Requires phase_shift correction |\n| Neuropixels 2.0 (single) | 1280 | 384 | Denser geometry |\n| Neuropixels 2.0 (4-shank) | 5120 | 384 | Multi-region recording |\n\n| Format | Extension | Reader |\n|--------|-----------|--------|\n| SpikeGLX | `.ap.bin`, `.lf.bin`, `.meta` | `si.read_spikeglx()` |\n| Open Ephys | `.continuous`, `.oebin` | `si.read_openephys()` |\n| NWB | `.nwb` | `si.read_nwb()` |\n\n## Quick Start\n\n### Basic Import and Setup\n\n```python\nimport spikeinterface.full as si\nimport neuropixels_analysis as npa\n\n# Configure parallel processing\njob_kwargs = dict(n_jobs=-1, chunk_duration='1s', progress_bar=True)\n```\n\n### Loading Data\n\n```python\n# SpikeGLX (most common)\nrecording = si.read_spikeglx('\u002Fpath\u002Fto\u002Fdata', stream_id='imec0.ap')\n\n# Open Ephys (common for many labs)\nrecording = si.read_openephys('\u002Fpath\u002Fto\u002FRecord_Node_101\u002F')\n\n# Check available streams\nstreams, ids = si.get_neo_streams('spikeglx', '\u002Fpath\u002Fto\u002Fdata')\nprint(streams)  # ['imec0.ap', 'imec0.lf', 'nidq']\n\n# For testing with subset of data\nrecording = recording.frame_slice(0, int(60 * recording.get_sampling_frequency()))\n```\n\n### Complete Pipeline (One Command)\n\n```python\n# Run full analysis pipeline\nresults = npa.run_pipeline(\n    recording,\n    output_dir='output\u002F',\n    sorter='kilosort4',\n    curation_method='allen',\n)\n\n# Access results\nsorting = results['sorting']\nmetrics = results['metrics']\nlabels = results['labels']\n```\n\n## Standard Analysis Workflow\n\n### 1. Preprocessing\n\n```python\n# Recommended preprocessing chain\nrec = si.highpass_filter(recording, freq_min=400)\nrec = si.phase_shift(rec)  # Required for Neuropixels 1.0\nbad_ids, _ = si.detect_bad_channels(rec)\nrec = rec.remove_channels(bad_ids)\nrec = si.common_reference(rec, operator='median')\n\n# Or use our wrapper\nrec = npa.preprocess(recording)\n```\n\n### 2. Check and Correct Drift\n\n```python\n# Check for drift (always do this!)\nmotion_info = npa.estimate_motion(rec, preset='kilosort_like')\nnpa.plot_drift(rec, motion_info, output='drift_map.png')\n\n# Apply correction if needed\nif motion_info['motion'].max() > 10:  # microns\n    rec = npa.correct_motion(rec, preset='nonrigid_accurate')\n```\n\n### 3. Spike Sorting\n\n```python\n# Kilosort4 (recommended, requires GPU)\nsorting = si.run_sorter('kilosort4', rec, folder='ks4_output')\n\n# CPU alternatives\nsorting = si.run_sorter('tridesclous2', rec, folder='tdc2_output')\nsorting = si.run_sorter('spykingcircus2', rec, folder='sc2_output')\nsorting = si.run_sorter('mountainsort5', rec, folder='ms5_output')\n\n# Check available sorters\nprint(si.installed_sorters())\n```\n\n### 4. Postprocessing\n\n```python\n# Create analyzer and compute all extensions\nanalyzer = si.create_sorting_analyzer(sorting, rec, sparse=True)\n\nanalyzer.compute('random_spikes', max_spikes_per_unit=500)\nanalyzer.compute('waveforms', ms_before=1.0, ms_after=2.0)\nanalyzer.compute('templates', operators=['average', 'std'])\nanalyzer.compute('spike_amplitudes')\nanalyzer.compute('correlograms', window_ms=50.0, bin_ms=1.0)\nanalyzer.compute('unit_locations', method='monopolar_triangulation')\nanalyzer.compute('quality_metrics')\n\nmetrics = analyzer.get_extension('quality_metrics').get_data()\n```\n\n### 5. Curation\n\n```python\n# Allen Institute criteria (conservative)\ngood_units = metrics.query(\"\"\"\n    presence_ratio > 0.9 and\n    isi_violations_ratio \u003C 0.5 and\n    amplitude_cutoff \u003C 0.1\n\"\"\").index.tolist()\n\n# Or use automated curation\nlabels = npa.curate(metrics, method='allen')  # 'allen', 'ibl', 'strict'\n```\n\n### 6. AI-Assisted Curation (For Uncertain Units)\n\nWhen using this skill with Claude Code, Claude can directly analyze waveform plots and provide expert curation decisions. For programmatic API access:\n\n```python\nfrom anthropic import Anthropic\n\n# Setup API client\nclient = Anthropic()\n\n# Analyze uncertain units visually\nuncertain = metrics.query('snr > 3 and snr \u003C 8').index.tolist()\n\nfor unit_id in uncertain:\n    result = npa.analyze_unit_visually(analyzer, unit_id, api_client=client)\n    print(f\"Unit {unit_id}: {result['classification']}\")\n    print(f\"  Reasoning: {result['reasoning'][:100]}...\")\n```\n\n**Claude Code Integration**: When running within Claude Code, ask Claude to examine waveform\u002Fcorrelogram plots directly - no API setup required.\n\n### 7. Generate Analysis Report\n\n```python\n# Generate comprehensive HTML report with visualizations\nreport_dir = npa.generate_analysis_report(results, 'output\u002F')\n# Opens report.html with summary stats, figures, and unit table\n\n# Print formatted summary to console\nnpa.print_analysis_summary(results)\n```\n\n### 8. Export Results\n\n```python\n# Export to Phy for manual review\nsi.export_to_phy(analyzer, output_folder='phy_export\u002F',\n                 compute_pc_features=True, compute_amplitudes=True)\n\n# Export to NWB\nfrom spikeinterface.exporters import export_to_nwb\nexport_to_nwb(rec, sorting, 'output.nwb')\n\n# Save quality metrics\nmetrics.to_csv('quality_metrics.csv')\n```\n\n## Common Pitfalls and Best Practices\n\n1. **Always check drift** before spike sorting - drift > 10μm significantly impacts quality\n2. **Use phase_shift** for Neuropixels 1.0 probes (not needed for 2.0)\n3. **Save preprocessed data** to avoid recomputing - use `rec.save(folder='preprocessed\u002F')`\n4. **Use GPU** for Kilosort4 - it's 10-50x faster than CPU alternatives\n5. **Review uncertain units manually** - automated curation is a starting point\n6. **Combine metrics with AI** - use metrics for clear cases, AI for borderline units\n7. **Document your thresholds** - different analyses may need different criteria\n8. **Export to Phy** for critical experiments - human oversight is valuable\n\n## Key Parameters to Adjust\n\n### Preprocessing\n- `freq_min`: Highpass cutoff (300-400 Hz typical)\n- `detect_threshold`: Bad channel detection sensitivity\n\n### Motion Correction\n- `preset`: 'kilosort_like' (fast) or 'nonrigid_accurate' (better for severe drift)\n\n### Spike Sorting (Kilosort4)\n- `batch_size`: Samples per batch (30000 default)\n- `nblocks`: Number of drift blocks (increase for long recordings)\n- `Th_learned`: Detection threshold (lower = more spikes)\n\n### Quality Metrics\n- `snr_threshold`: Signal-to-noise cutoff (3-5 typical)\n- `isi_violations_ratio`: Refractory violations (0.01-0.5)\n- `presence_ratio`: Recording coverage (0.5-0.95)\n\n## Bundled Resources\n\n### scripts\u002Fpreprocess_recording.py\nAutomated preprocessing script:\n```bash\npython scripts\u002Fpreprocess_recording.py \u002Fpath\u002Fto\u002Fdata --output preprocessed\u002F\n```\n\n### scripts\u002Frun_sorting.py\nRun spike sorting:\n```bash\npython scripts\u002Frun_sorting.py preprocessed\u002F --sorter kilosort4 --output sorting\u002F\n```\n\n### scripts\u002Fcompute_metrics.py\nCompute quality metrics and apply curation:\n```bash\npython scripts\u002Fcompute_metrics.py sorting\u002F preprocessed\u002F --output metrics\u002F --curation allen\n```\n\n### scripts\u002Fexport_to_phy.py\nExport to Phy for manual curation:\n```bash\npython scripts\u002Fexport_to_phy.py metrics\u002Fanalyzer --output phy_export\u002F\n```\n\n### assets\u002Fanalysis_template.py\nComplete analysis template. Copy and customize:\n```bash\ncp assets\u002Fanalysis_template.py my_analysis.py\n# Edit parameters and run\npython my_analysis.py\n```\n\n### reference\u002Fstandard_workflow.md\nDetailed step-by-step workflow with explanations for each stage.\n\n### reference\u002Fapi_reference.md\nQuick function reference organized by module.\n\n### reference\u002Fplotting_guide.md\nComprehensive visualization guide for publication-quality figures.\n\n## Detailed Reference Guides\n\n| Topic | Reference |\n|-------|-----------|\n| Full workflow | [reference\u002Fstandard_workflow.md](reference\u002Fstandard_workflow.md) |\n| API reference | [reference\u002Fapi_reference.md](reference\u002Fapi_reference.md) |\n| Plotting guide | [reference\u002Fplotting_guide.md](reference\u002Fplotting_guide.md) |\n| Preprocessing | [PREPROCESSING.md](PREPROCESSING.md) |\n| Spike sorting | [SPIKE_SORTING.md](SPIKE_SORTING.md) |\n| Motion correction | [MOTION_CORRECTION.md](MOTION_CORRECTION.md) |\n| Quality metrics | [QUALITY_METRICS.md](QUALITY_METRICS.md) |\n| Automated curation | [AUTOMATED_CURATION.md](AUTOMATED_CURATION.md) |\n| AI-assisted curation | [AI_CURATION.md](AI_CURATION.md) |\n| Waveform analysis | [ANALYSIS.md](ANALYSIS.md) |\n\n## Installation\n\n```bash\n# Core packages\npip install spikeinterface[full] probeinterface neo\n\n# Spike sorters\npip install kilosort          # Kilosort4 (GPU required)\npip install spykingcircus     # SpykingCircus2 (CPU)\npip install mountainsort5     # Mountainsort5 (CPU)\n\n# Our toolkit\npip install neuropixels-analysis\n\n# Optional: AI curation\npip install anthropic\n\n# Optional: IBL tools\npip install ibl-neuropixel ibllib\n```\n\n## Project Structure\n\n```\nproject\u002F\n├── raw_data\u002F\n│   └── recording_g0\u002F\n│       └── recording_g0_imec0\u002F\n│           ├── recording_g0_t0.imec0.ap.bin\n│           └── recording_g0_t0.imec0.ap.meta\n├── preprocessed\u002F           # Saved preprocessed recording\n├── motion\u002F                 # Motion estimation results\n├── sorting_output\u002F         # Spike sorter output\n├── analyzer\u002F               # SortingAnalyzer (waveforms, metrics)\n├── phy_export\u002F             # For manual curation\n├── ai_curation\u002F            # AI analysis reports\n└── results\u002F\n    ├── quality_metrics.csv\n    ├── curation_labels.json\n    └── output.nwb\n```\n\n## Additional Resources\n\n- **SpikeInterface Docs**: https:\u002F\u002Fspikeinterface.readthedocs.io\u002F\n- **Neuropixels Tutorial**: https:\u002F\u002Fspikeinterface.readthedocs.io\u002Fen\u002Fstable\u002Fhow_to\u002Fanalyze_neuropixels.html\n- **Kilosort4 GitHub**: https:\u002F\u002Fgithub.com\u002FMouseLand\u002FKilosort\n- **IBL Neuropixel Tools**: https:\u002F\u002Fgithub.com\u002Fint-brain-lab\u002Fibl-neuropixel\n- **Allen Institute ecephys**: https:\u002F\u002Fgithub.com\u002FAllenInstitute\u002Fecephys_spike_sorting\n- **Bombcell (Automated QC)**: https:\u002F\u002Fgithub.com\u002FJulie-Fabre\u002Fbombcell\n- **SpikeAgent (AI Curation)**: https:\u002F\u002Fgithub.com\u002FSpikeAgent\u002FSpikeAgent\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add davila7\u002Fclaude-code-templates --skill neuropixels-analysis",{"tool":66,"command":67},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill neuropixels-analysis",{"tool":69,"command":70},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill neuropixels-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FSKILL.md",true,[74,80,84,90,94,99,103,107,111,115,119,123,127,131,135,139,143,147],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"AI_CURATION.md","REFERENCE","参考文档",8657,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FAI_CURATION.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"ANALYSIS.md",9869,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FANALYSIS.md",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"assets\u002Fanalysis_template.py","SCRIPT","脚本",9014,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Fassets\u002Fanalysis_template.py",{"path":91,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":92,"sourceHtmlUrl":93},"AUTOMATED_CURATION.md",10033,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FAUTOMATED_CURATION.md",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",1065,{"path":100,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":101,"sourceHtmlUrl":102},"MOTION_CORRECTION.md",8670,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FMOTION_CORRECTION.md",{"path":104,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":105,"sourceHtmlUrl":106},"PREPROCESSING.md",6696,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FPREPROCESSING.md",{"path":108,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":109,"sourceHtmlUrl":110},"QUALITY_METRICS.md",9454,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FQUALITY_METRICS.md",{"path":112,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":113,"sourceHtmlUrl":114},"references\u002Fapi_reference.md",8175,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Freferences\u002Fapi_reference.md",{"path":116,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":117,"sourceHtmlUrl":118},"references\u002Fplotting_guide.md",10837,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Freferences\u002Fplotting_guide.md",{"path":120,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":121,"sourceHtmlUrl":122},"references\u002Fstandard_workflow.md",8646,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Freferences\u002Fstandard_workflow.md",{"path":124,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":125,"sourceHtmlUrl":126},"scripts\u002Fcompute_metrics.py",5226,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Fscripts\u002Fcompute_metrics.py",{"path":128,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":129,"sourceHtmlUrl":130},"scripts\u002Fexplore_recording.py",5529,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Fscripts\u002Fexplore_recording.py",{"path":132,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":133,"sourceHtmlUrl":134},"scripts\u002Fexport_to_phy.py",2477,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Fscripts\u002Fexport_to_phy.py",{"path":136,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":137,"sourceHtmlUrl":138},"scripts\u002Fneuropixels_pipeline.py",13286,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Fscripts\u002Fneuropixels_pipeline.py",{"path":140,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":141,"sourceHtmlUrl":142},"scripts\u002Fpreprocess_recording.py",4235,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Fscripts\u002Fpreprocess_recording.py",{"path":144,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":145,"sourceHtmlUrl":146},"scripts\u002Frun_sorting.py",2573,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002Fscripts\u002Frun_sorting.py",{"path":148,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":149,"sourceHtmlUrl":150},"SPIKE_SORTING.md",7918,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FSPIKE_SORTING.md",[152,176,203,236,271,295],{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":159,"publishedAt":45},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[158],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},[160,161,162,163,164,29,165,166,41,28,167,33,168,169,170,171,172,173,174,175],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","reduce","record","track","verdict","evm","solana","how","public","look",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":45},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[182],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},[184,185,186,187,188,189,190,191,192,193,194,28,195,196,197,198,199,200,201,202],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":218,"publishedAt":45},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[209,212,213],{"categoryNo":210,"categoryName":211,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},{"categoryNo":214,"categoryName":215,"taxonomyType":216,"taxonomyTypeDesc":217},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[219,220,221,222,223,224,225,29,226,227,228,229,230,231,232,41,233,234,28,235],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":237,"name":238,"nameZh":6,"description":239,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":240,"licenseFileUrl":241,"sourceHtmlUrl":242,"categories":243,"keywords":247,"publishedAt":45},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[244],{"categoryNo":245,"categoryName":246,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000009","前端开发",[248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,29,270],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":272,"name":273,"nameZh":6,"description":274,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":240,"licenseFileUrl":275,"sourceHtmlUrl":276,"categories":277,"keywords":282,"publishedAt":45},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[278,281],{"categoryNo":279,"categoryName":280,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":245,"categoryName":246,"taxonomyType":22,"taxonomyTypeDesc":23},[283,284,285,286,287,249,288,258,259,289,290,291,292,29,293,33,294],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":296,"name":297,"nameZh":6,"description":298,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":240,"licenseFileUrl":299,"sourceHtmlUrl":300,"categories":301,"keywords":309,"publishedAt":45},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[302,305,306],{"categoryNo":303,"categoryName":304,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},{"categoryNo":307,"categoryName":308,"taxonomyType":216,"taxonomyTypeDesc":217},"01JBSEEDCAT000000000000036","内容创作者",[310,311,312,313,314,315,43,316,251,317,261,195,318,319,320,321,322,231,323,28,324,25,325,326,327,173,328],"discernment nudge","nudge","interpretation","help","run","reasoning","writing","lookup","content","review","conversation","short","up","invoke","you","claims","argument","assemble","recommendations"]