{"id":"3b11477f-f84a-46ed-8d8c-67d59c2ef03f","entityType":"agent","slug":"clawhub-sheng7564-jupyter-notebook-manager","name":"jupyter-notebook-manager","canonicalUrl":"https://www.xpersona.co/agent/clawhub-sheng7564-jupyter-notebook-manager","canonicalPath":"/agent/clawhub-sheng7564-jupyter-notebook-manager","generatedAt":"2026-10-11T17:44:03.443Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T15:06:19.284Z","emptyReason":null},"description":"Complete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities Skill: jupyter-notebook-manager Owner: sheng7564 Summary: Complete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-16T04:00:55.218Z | user first commit Archive index: Archive v1.0.0: 10 files, 28798 bytes Files: README.md (10618b), requirements.txt (391b), scripts/notebook_creator.py (24401b), scripts/notebook_execu","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s179v11yrph12syd1q1a2qzttn84yqka:jupyter-notebook-manager","sourceUrl":"https://clawhub.ai/sheng7564/jupyter-notebook-manager","homepage":"https://clawhub.ai/sheng7564/skills/jupyter-notebook-manager","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/sheng7564/jupyter-notebook-manager","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/sheng7564/skills/jupyter-notebook-manager","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Complete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities Skill: jupyter-notebook-manager Owner: sheng7564 Summ"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:06:19.284Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:06:19.284Z","emptyReason":null},"stars":null,"forks":null,"downloads":1044,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:06:19.271Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T15:06:19.284Z","lastCrawledAt":"2026-10-11T15:06:19.271Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T15:06:19.271Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-04-16T04:00:55.218Z","changelog":"first commit","fileCount":10,"zipByteSize":28798}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s179v11yrph12syd1q1a2qzttn84yqka:jupyter-notebook-manager","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T17:44:03.441Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sheng7564-jupyter-notebook-manager/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T15:06:19.284Z","emptyReason":null},"readme":"Skill: jupyter-notebook-manager\n\nOwner: sheng7564\n\nSummary: Complete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-04-16T04:00:55.218Z | user\n\nfirst commit\n\nArchive index:\n\nArchive v1.0.0: 10 files, 28798 bytes\n\nFiles: README.md (10618b), requirements.txt (391b), scripts/notebook_creator.py (24401b), scripts/notebook_executor.py (11499b), skill-card.md (2487b), SKILL.md (13734b), tests/README.md (5593b), tests/test_creator.py (11171b), tests/test_executor.py (14864b), _meta.json (143b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: jupyter-notebook-manager\nversion: 1.0.0\nauthor: AI Skills Community\ndescription: Complete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities\ntags:\n  - jupyter\n  - data-science\n  - python\n  - notebook\n  - analysis\ncategory: data-science\nrequires:\n  - jupyter\n  - nbformat\n  - nbconvert\n  - pandas\ntrigger_keywords:\n  - jupyter\n  - notebook\n  - ipynb\n  - data analysis\n  - create notebook\n  - run notebook\n  - debug notebook\n  - execute notebook\n  - analyze data\n---\n\n# Jupyter Notebook Manager\n\nComplete Jupyter notebook management system that enables Claude to create, execute, debug, analyze, and optimize Jupyter notebooks with deep integration of data science workflows.\n\n## 🎯 When to Use This Skill\n\n### Trigger Conditions\n\nUse this skill when you encounter:\n\n1. **User mentions Jupyter-related keywords**:\n   - \"create a Jupyter notebook\"\n   - \"run this notebook\"\n   - \"debug my .ipynb file\"\n   - \"analyze notebook results\"\n   - \"optimize my notebook\"\n\n2. **User requests data analysis workflows**:\n   - \"set up data analysis pipeline\"\n   - \"perform data cleaning\"\n   - \"visualize analysis results\"\n   - \"generate analysis report\"\n\n3. **User provides .ipynb files**:\n   - Detecting .ipynb file references\n   - User uploads notebook files\n   - Working directory contains notebooks\n\n4. **User needs notebook operations**:\n   - \"convert notebook to Python script\"\n   - \"extract code from notebook\"\n   - \"merge multiple notebooks\"\n   - \"generate notebook template\"\n\n## 🚀 Core Capabilities\n\n### 1. Notebook Creation & Templates\n\n**When**: User needs to create new notebooks for specific analysis tasks\n\n**Capabilities**:\n- Generate notebooks from scratch with proper structure\n- Provide domain-specific templates (EDA, ML, visualization)\n- Add markdown documentation and code cells\n- Configure kernel and metadata\n- Support custom templates\n\n**Example**:\n```python\n# User: \"Create a data analysis notebook for sales data\"\n# → Generates structured notebook with:\n#   - Import cells (pandas, numpy, matplotlib)\n#   - Data loading section\n#   - EDA section with common analyses\n#   - Visualization section\n#   - Summary section\n```\n\n### 2. Notebook Execution & Monitoring\n\n**When**: User needs to run notebooks and track execution\n\n**Capabilities**:\n- Execute notebooks programmatically\n- Monitor execution progress\n- Capture outputs and errors\n- Handle long-running cells\n- Support parameterized execution\n\n**Example**:\n```python\n# User: \"Run analysis.ipynb with dataset=sales_2024.csv\"\n# → Executes notebook with parameters\n# → Shows real-time progress\n# → Captures all outputs\n# → Reports execution time and status\n```\n\n### 3. Debugging & Error Analysis\n\n**When**: Notebook execution fails or produces unexpected results\n\n**Capabilities**:\n- Identify error cells and stack traces\n- Analyze variable states at error points\n- Suggest fixes for common issues\n- Detect dependency problems\n- Check data quality issues\n\n**Example**:\n```python\n# User: \"My notebook fails at cell 5\"\n# → Analyzes error traceback\n# → Checks variable values before error\n# → Identifies root cause (e.g., missing column)\n# → Suggests fix with corrected code\n```\n\n### 4. Variable Inspection & State Analysis\n\n**When**: User needs to understand notebook state and variables\n\n**Capabilities**:\n- Extract all variables and their types\n- Show dataframe summaries\n- Visualize data distributions\n- Track variable flow across cells\n- Detect unused variables\n\n**Example**:\n```python\n# User: \"What variables are defined in this notebook?\"\n# → Lists all variables with types\n# → Shows dataframe shapes and dtypes\n# → Displays memory usage\n# → Highlights key variables\n```\n\n### 5. Code Quality & Optimization\n\n**When**: User wants to improve notebook code\n\n**Capabilities**:\n- Detect code smells and anti-patterns\n- Suggest performance improvements\n- Identify redundant computations\n- Recommend vectorization\n- Check PEP 8 compliance\n\n**Example**:\n```python\n# User: \"Optimize my data processing notebook\"\n# → Identifies slow loops that can be vectorized\n# → Suggests caching for expensive operations\n# → Recommends better pandas operations\n# → Provides optimized code snippets\n```\n\n### 6. Notebook Conversion & Export\n\n**When**: User needs different formats or want to modularize code\n\n**Capabilities**:\n- Convert notebook to Python script\n- Export to HTML/PDF/Markdown\n- Extract functions for reuse\n- Generate documentation\n- Create clean code modules\n\n**Example**:\n```python\n# User: \"Convert my notebook to a Python module\"\n# → Extracts all function definitions\n# → Creates proper module structure\n# → Adds docstrings\n# → Generates import-ready .py file\n```\n\n### 7. Results Visualization & Reporting\n\n**When**: User needs to present or summarize notebook results\n\n**Capabilities**:\n- Generate executive summaries\n- Create result dashboards\n- Extract key findings\n- Compile visualizations\n- Format output reports\n\n**Example**:\n```python\n# User: \"Summarize the results from my analysis notebook\"\n# → Extracts all plots and tables\n# → Identifies key metrics and insights\n# → Generates markdown report\n# → Includes data quality notes\n```\n\n### 8. Collaborative Features\n\n**When**: Multiple users work on notebooks\n\n**Capabilities**:\n- Compare notebook versions\n- Merge notebook changes\n- Generate diff reports\n- Track cell modifications\n- Resolve conflicts\n\n**Example**:\n```python\n# User: \"Compare my notebook with the previous version\"\n# → Shows cell-by-cell differences\n# → Highlights output changes\n# → Identifies new/deleted cells\n# → Suggests conflict resolution\n```\n\n## 🛠️ Tool Integration\n\n### Core Tools\n\n1. **nbformat** - Notebook file I/O and manipulation\n2. **nbconvert** - Format conversion and execution\n3. **papermill** - Parameterized execution\n4. **nbdime** - Notebook diffing and merging\n5. **pandas** - Data manipulation and analysis\n6. **matplotlib/seaborn** - Visualization\n7. **jupyter_client** - Kernel management\n\n### Script Integration\n\nThe skill includes these utility scripts:\n\n- `scripts/notebook_creator.py` - Template-based notebook generation\n- `scripts/notebook_executor.py` - Robust notebook execution\n- `scripts/notebook_debugger.py` - Error analysis and debugging\n- `scripts/notebook_analyzer.py` - Code quality and optimization\n- `scripts/notebook_converter.py` - Format conversion utilities\n- `scripts/notebook_reporter.py` - Results extraction and reporting\n\n## 📋 Workflow Examples\n\n### Workflow 1: Create and Run Analysis\n\n```markdown\nUser: \"Create a sales analysis notebook and run it with Q4_sales.csv\"\n\nStep 1: Generate Template\n→ Call notebook_creator.py with \"sales-analysis\" template\n→ Customize for Q4 data\n\nStep 2: Configure Parameters\n→ Set data_file = \"Q4_sales.csv\"\n→ Set analysis_type = \"quarterly\"\n\nStep 3: Execute Notebook\n→ Call notebook_executor.py\n→ Monitor progress (show cell N/M)\n\nStep 4: Report Results\n→ Extract key metrics\n→ Show visualizations\n→ Summarize findings\n```\n\n### Workflow 2: Debug Failed Notebook\n\n```markdown\nUser: \"My notebook analysis.ipynb crashes at cell 10\"\n\nStep 1: Identify Error\n→ Parse notebook with nbformat\n→ Find cell 10 and error traceback\n\nStep 2: Analyze Context\n→ Check variables in cells 1-9\n→ Identify dataframe state before error\n\nStep 3: Diagnose Issue\n→ Analyze error message\n→ Check for common issues (missing columns, type errors, etc.)\n\nStep 4: Suggest Fix\n→ Provide corrected code\n→ Explain root cause\n→ Offer prevention tips\n```\n\n### Workflow 3: Optimize Slow Notebook\n\n```markdown\nUser: \"This notebook takes 10 minutes to run, can you optimize it?\"\n\nStep 1: Profile Execution\n→ Run with timing enabled\n→ Identify slow cells\n\nStep 2: Analyze Code\n→ Detect inefficient patterns\n→ Find opportunities for vectorization\n\nStep 3: Suggest Improvements\n→ Show optimized code versions\n→ Estimate speed improvements\n\nStep 4: Validate\n→ Test optimized notebook\n→ Verify outputs match original\n```\n\n## 🎓 Best Practices\n\n### Notebook Structure\n\n1. **Start with imports and configuration**\n   - Group all imports at top\n   - Set display options early\n   - Configure logging\n\n2. **Use markdown for documentation**\n   - Section headers with ##\n   - Explain analysis steps\n   - Document assumptions\n\n3. **Modular code cells**\n   - One logical operation per cell\n   - Avoid overly long cells\n   - Keep cell outputs manageable\n\n4. **Clear variable naming**\n   - Use descriptive names\n   - Follow naming conventions\n   - Avoid single-letter variables (except i, j, k)\n\n### Code Quality\n\n1. **Avoid loops when vectorization possible**\n   ```python\n   # Bad\n   for i in range(len(df)):\n       df.loc[i, 'new_col'] = df.loc[i, 'a'] + df.loc[i, 'b']\n   \n   # Good\n   df['new_col'] = df['a'] + df['b']\n   ```\n\n2. **Cache expensive computations**\n   ```python\n   # Check if already computed\n   if not os.path.exists('cached_result.pkl'):\n       result = expensive_computation()\n       result.to_pickle('cached_result.pkl')\n   else:\n       result = pd.read_pickle('cached_result.pkl')\n   ```\n\n3. **Handle errors gracefully**\n   ```python\n   try:\n       df = pd.read_csv('data.csv')\n   except FileNotFoundError:\n       print(\"⚠️ Data file not found, using sample data\")\n       df = generate_sample_data()\n   ```\n\n### Performance Tips\n\n1. **Use appropriate data types**\n   - Convert to categorical for low-cardinality strings\n   - Use int32 instead of int64 when possible\n   - Leverage datetime types\n\n2. **Process data in chunks for large files**\n   ```python\n   chunks = pd.read_csv('large_file.csv', chunksize=10000)\n   result = pd.concat([process(chunk) for chunk in chunks])\n   ```\n\n3. **Leverage pandas built-in functions**\n   - Use `query()` for filtering\n   - Use `eval()` for expressions\n   - Use `pipe()` for chaining\n\n## 🔍 Error Patterns and Solutions\n\n### Common Issues\n\n| Error Pattern | Cause | Solution |\n|--------------|-------|----------|\n| `KeyError: 'column_name'` | Column doesn't exist | Check `df.columns`, verify spelling |\n| `SettingWithCopyWarning` | Chained assignment | Use `.loc[]` or `.copy()` |\n| `MemoryError` | Dataset too large | Process in chunks or use dask |\n| `ModuleNotFoundError` | Missing package | Add to requirements, install in kernel |\n| `KernelDead` | Out of memory or crash | Restart kernel, reduce data size |\n\n### Debugging Checklist\n\n```python\n# 1. Check data loading\nprint(f\"Shape: {df.shape}\")\nprint(f\"Columns: {df.columns.tolist()}\")\nprint(f\"Dtypes:\\n{df.dtypes}\")\n\n# 2. Check for missing values\nprint(f\"Missing values:\\n{df.isnull().sum()}\")\n\n# 3. Check data types\nprint(f\"Object columns: {df.select_dtypes('object').columns.tolist()}\")\n\n# 4. Check memory usage\nprint(f\"Memory: {df.memory_usage(deep=True).sum() / 1024**2:.2f} MB\")\n\n# 5. Check for duplicates\nprint(f\"Duplicates: {df.duplicated().sum()}\")\n```\n\n## 📊 Template Library\n\n### Available Templates\n\n1. **exploratory-data-analysis** - Comprehensive EDA workflow\n2. **machine-learning-training** - ML model development pipeline\n3. **time-series-analysis** - Time series forecasting\n4. **data-cleaning** - Data quality and cleaning\n5. **statistical-testing** - Hypothesis testing and statistics\n6. **visualization-dashboard** - Interactive visualizations\n7. **data-pipeline** - ETL and data transformation\n8. **report-generation** - Automated reporting\n\n### Template Usage\n\n```bash\n# Create notebook from template\npython scripts/notebook_creator.py \\\n  --template exploratory-data-analysis \\\n  --output eda_analysis.ipynb \\\n  --data-file sales_data.csv \\\n  --target-column revenue\n```\n\n## 🔗 Integration Points\n\n### With Other Skills\n\n- **pandas-data-wrangler**: Data manipulation operations\n- **matplotlib-plotter**: Advanced visualizations\n- **ml-model-trainer**: Model training and evaluation\n- **data-pipeline-builder**: ETL workflows\n\n### With External Tools\n\n- **Jupyter Lab/Notebook**: Interactive development\n- **VS Code**: Notebook editing and debugging\n- **Papermill**: Batch execution and parameterization\n- **nbconvert**: Publishing and sharing\n- **git**: Version control (with nbstripout)\n\n## 🎯 Success Criteria\n\nA successful skill invocation should:\n\n✅ Understand user's notebook-related intent  \n✅ Select appropriate operation (create/run/debug/optimize)  \n✅ Execute operation with proper error handling  \n✅ Provide clear progress updates  \n✅ Return actionable results or insights  \n✅ Offer next steps or improvements  \n✅ Handle edge cases gracefully  \n\n## 📚 Resources\n\n### Documentation Links\n\n- [Jupyter Documentation](https://jupyter.org/documentation)\n- [nbformat Specification](https://nbformat.readthedocs.io/)\n- [nbconvert Guide](https://nbconvert.readthedocs.io/)\n- [Papermill Documentation](https://papermill.readthedocs.io/)\n\n### Example Notebooks\n\nSee `examples/` directory for:\n- Sample analysis notebooks\n- Template demonstrations\n- Use case tutorials\n- Best practice examples\n\n## 🚨 Limitations\n\n1. **Kernel Management**: Cannot directly interact with running kernels (use scripts)\n2. **Interactive Widgets**: Limited support for ipywidgets\n3. **Long-Running**: Very long computations (>10 min) may timeout\n4. **GPU Operations**: No direct GPU kernel access\n5. **Large Files**: Memory constraints for very large notebooks (>100MB)\n\n## 📝 Notes\n\n- Always validate notebook structure before execution\n- Use timeouts to prevent hanging on infinite loops\n- Sanitize user inputs in parameterized execution\n- Consider notebook size when extracting outputs\n- Test scripts with various notebook formats\n- Maintain compatibility with Jupyter 4.x and 5.x formats\n\n---\n\n**Version**: 1.0.0  \n**Last Updated**: 2026-04-16  \n**Maintainer**: AI Skills Community\n\nFile v1.0.0:README.md\n\n# 🪐 Jupyter Notebook Manager\n\n**Complete Jupyter notebook management system for Claude AI**\n\nA comprehensive skill that enables Claude to create, execute, debug, analyze, and optimize Jupyter notebooks with deep integration of data science workflows.\n\n[![Version](https://img.shields.io/badge/version-1.0.0-blue.svg)](https://github.com/ai-skills/jupyter-notebook-manager)\n[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)\n[![Python](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org)\n\n---\n\n## ✨ Features\n\n###  **8 Core Capabilities**\n\n1. 📝 **Notebook Creation** - Generate notebooks from templates (EDA, ML, Cleaning, etc.)\n2. ▶️ **Notebook Execution** - Run notebooks with monitoring and parameter injection\n3. 🐛 **Debugging & Analysis** - Identify errors, analyze state, suggest fixes\n4. 🔍 **Variable Inspection** - Explore variables, dataframes, and memory usage\n5. ⚡ **Code Optimization** - Detect bottlenecks, suggest improvements\n6. 🔄 **Format Conversion** - Convert between .ipynb, .py, HTML, PDF\n7. 📊 **Results Reporting** - Extract insights and generate summaries\n8. 👥 **Collaboration** - Compare versions, merge changes, resolve conflicts\n\n---\n\n## 🚀 Quick Start\n\n### Installation\n\n```bash\n# Install dependencies\npip install -r requirements.txt\n\n# Verify installation\npython scripts/notebook_creator.py --list-templates\n```\n\n### Basic Usage\n\n#### 1. Create a Notebook\n\n```bash\n# Create from template\npython scripts/notebook_creator.py \\\n  --template exploratory-data-analysis \\\n  --output my_analysis.ipynb \\\n  --data-file sales_data.csv \\\n  --title \"Q4 Sales Analysis\"\n```\n\n#### 2. Execute a Notebook\n\n```bash\n# Run notebook\npython scripts/notebook_executor.py \\\n  my_analysis.ipynb \\\n  --output results.ipynb\n\n# With parameters\npython scripts/notebook_executor.py \\\n  my_analysis.ipynb \\\n  --param dataset=Q4_data.csv \\\n  --param year=2024\n```\n\n#### 3. Use with Claude\n\nJust tell Claude what you need:\n\n```\nUser: \"Create a data analysis notebook for my sales data\"\n\nClaude: I'll create an EDA notebook for you...\n[Creates structured notebook with all analysis sections]\n\nUser: \"Run it with my Q4_sales.csv file\"\n\nClaude: Executing notebook with your data...\n[Shows real-time progress and results]\n```\n\n---\n\n## 📖 Documentation\n\n### Available Templates\n\n| Template | Purpose | Use Case |\n|----------|---------|----------|\n| `exploratory-data-analysis` | Comprehensive EDA | Understand new datasets |\n| `machine-learning-training` | ML model pipeline | Train and evaluate models |\n| `data-cleaning` | Data quality | Clean messy data |\n| `time-series-analysis` | Time series forecasting | Temporal data |\n| `statistical-testing` | Hypothesis testing | Statistical analysis |\n| `visualization-dashboard` | Interactive viz | Present results |\n| `blank` | Minimal structure | Start from scratch |\n\n### Script Reference\n\n#### notebook_creator.py\n\n```bash\npython scripts/notebook_creator.py [OPTIONS]\n\nOptions:\n  --template TEXT          Template name (default: blank)\n  --output PATH           Output notebook path\n  --title TEXT            Notebook title\n  --author TEXT           Author name\n  --data-file PATH        Data file path\n  --target-column TEXT    Target variable (for ML)\n  --list-templates        Show available templates\n```\n\n#### notebook_executor.py\n\n```bash\npython scripts/notebook_executor.py NOTEBOOK [OPTIONS]\n\nArguments:\n  NOTEBOOK                Path to notebook file\n\nOptions:\n  --output PATH           Output path (default: overwrite input)\n  --timeout INT           Timeout in seconds (default: 600)\n  --kernel TEXT           Kernel name (default: python3)\n  --param KEY=VALUE       Parameters to inject\n  --quiet                 Suppress output\n```\n\n---\n\n## 🧪 Testing\n\n### Run Tests\n\n```bash\n# All tests\npytest tests/ -v\n\n# Specific test file\npytest tests/test_creator.py -v\n\n# With coverage\npytest tests/ --cov=scripts --cov-report=html\n\n# Skip slow tests\npytest tests/ -m \"not slow\"\n```\n\n### Test Coverage\n\n- **Unit Tests**: 30 test cases across creator and executor\n- **Integration Tests**: End-to-end workflows\n- **Scenario Tests**: Real-world use cases\n- **Coverage Goal**: >80%\n\nSee [tests/README.md](tests/README.md) for detailed test documentation.\n\n---\n\n## 📚 Examples\n\n### Example 1: Quick EDA\n\n```python\nfrom notebook_creator import NotebookCreator\n\ncreator = NotebookCreator()\nnotebook_path = creator.create_notebook(\n    template=\"exploratory-data-analysis\",\n    output_path=\"eda.ipynb\",\n    title=\"Customer Analysis\",\n    data_file=\"customers.csv\"\n)\n\nprint(f\"Created: {notebook_path}\")\n```\n\n### Example 2: Parameterized Execution\n\n```python\nfrom notebook_executor import NotebookExecutor\n\nexecutor = NotebookExecutor(timeout=300)\nresult = executor.execute(\n    notebook_path=\"analysis.ipynb\",\n    parameters={\n        \"dataset\": \"data_2024.csv\",\n        \"threshold\": 0.8\n    },\n    verbose=True\n)\n\nif result[\"status\"] == \"success\":\n    print(f\"Completed in {result['execution_time']:.2f}s\")\n    print(f\"Cells: {result['cell_count']}\")\nelse:\n    print(f\"Error in cell {result['error_cell']}: {result['error']}\")\n```\n\n### Example 3: Error Debugging\n\nWhen a notebook fails, the executor provides detailed error information:\n\n```python\nresult = executor.execute(\"broken_notebook.ipynb\")\n\nif result[\"status\"] == \"error\":\n    print(f\"❌ Error in cell {result['error_cell']}\")\n    print(f\"Type: {result['error']}\")\n    print(f\"Message:\\n{result['error_message']}\")\n    \n    # Analyze and suggest fix\n    # (This would be done by Claude in actual usage)\n```\n\n---\n\n## 🎯 Use Cases\n\n### Data Science Workflow\n\n```\n1. Create EDA notebook → 2. Analyze data → 3. Clean data → \n4. Create ML notebook → 5. Train models → 6. Generate report\n```\n\n### Debugging Workflow\n\n```\nUser reports error → Load notebook → Identify error cell → \nAnalyze context → Suggest fix → Test fix\n```\n\n### Optimization Workflow\n\n```\nProfile notebook → Identify slow cells → Analyze code patterns → \nSuggest optimizations → Validate improvements\n```\n\n---\n\n## 🏗️ Project Structure\n\n```\njupyter-notebook-manager/\n├── SKILL.md                 # Skill documentation (main)\n├── README.md                # This file\n├── requirements.txt         # Python dependencies\n├── check_quality.py         # Quality checker script\n│\n├── scripts/                 # Core functionality\n│   ├── notebook_creator.py  # Template-based notebook creation\n│   └── notebook_executor.py # Robust notebook execution\n│\n├── tests/                   # Test suite\n│   ├── README.md            # Test documentation\n│   ├── test_creator.py      # Creator unit tests\n│   ├── test_executor.py     # Executor unit tests\n│   └── fixtures/            # Test data\n│\n├── examples/                # Usage examples\n│   └── (example notebooks)\n│\n└── assets/                  # Additional resources\n    └── templates/           # Notebook templates\n```\n\n---\n\n## 🔧 Configuration\n\n### Environment Variables\n\n```bash\n# Jupyter kernel to use\nexport JUPYTER_KERNEL=\"python3\"\n\n# Default timeout for execution\nexport NOTEBOOK_TIMEOUT=600\n\n# Matplotlib backend (for headless)\nexport MPLBACKEND=Agg\n```\n\n### Customization\n\n#### Add Custom Template\n\n```python\nclass NotebookCreator:\n    def _template_custom(self, **kwargs):\n        \"\"\"Your custom template.\"\"\"\n        return [\n            self._create_cell(\"markdown\", [\"# My Custom Template\\n\"]),\n            self._create_cell(\"code\", [\"import pandas as pd\\n\"]),\n            # Add more cells...\n        ]\n```\n\nRegister it in `_load_templates()`.\n\n---\n\n## 🤝 Integration with Other Skills\n\nThis skill works well with:\n\n- **pandas-data-wrangler**: Data manipulation operations\n- **matplotlib-plotter**: Advanced visualizations\n- **ml-model-trainer**: Model training and evaluation\n- **data-pipeline-builder**: ETL workflows\n\n---\n\n## ⚠️ Limitations\n\n1. **Kernel Management**: Cannot directly interact with running Jupyter kernels\n2. **Interactive Widgets**: Limited support for ipywidgets\n3. **Long-Running Operations**: Very long computations (>10 min) may timeout\n4. **GPU Operations**: No direct GPU kernel access\n5. **Large Files**: Memory constraints for very large notebooks (>100MB)\n\n---\n\n## 🐛 Troubleshooting\n\n### Common Issues\n\n**Issue**: `ModuleNotFoundError: No module named 'nbformat'`\n```bash\n# Solution\npip install nbformat nbconvert jupyter\n```\n\n**Issue**: Notebook execution hangs\n```bash\n# Solution: Increase timeout\npython scripts/notebook_executor.py notebook.ipynb --timeout 1200\n```\n\n**Issue**: Display issues in generated plots\n```bash\n# Solution: Use headless backend\nexport MPLBACKEND=Agg\npython scripts/notebook_executor.py notebook.ipynb\n```\n\n---\n\n## 📊 Performance\n\n| Operation | Average Time | Notes |\n|-----------|--------------|-------|\n| Create blank notebook | <0.1s | Instant |\n| Create EDA notebook | <0.5s | Template-based |\n| Execute simple notebook (10 cells) | 2-5s | Depends on operations |\n| Execute complex notebook (50 cells) | 10-60s | Varies by computation |\n| Large dataset (1M rows) | 30-300s | Memory-dependent |\n\n---\n\n## 🗺️ Roadmap\n\n### Version 1.1 (Next)\n- [ ] Add notebook_analyzer.py for code quality analysis\n- [ ] Add notebook_optimizer.py for performance optimization\n- [ ] Support for R kernels\n- [ ] Interactive debugging mode\n\n### Version 1.2 (Future)\n- [ ] Notebook merge and diff tools\n- [ ] CI/CD integration helpers\n- [ ] Notebook security scanner\n- [ ] Cloud execution support (AWS SageMaker, Google Colab)\n\n### Version 2.0 (Long-term)\n- [ ] Real-time collaboration features\n- [ ] AI-powered code suggestions\n- [ ] Automated test generation\n- [ ] Visual notebook editor integration\n\n---\n\n## 📄 License\n\nMIT License - see [LICENSE](LICENSE) file for details.\n\n---\n\n## 🙏 Acknowledgments\n\n- Inspired by [Papermill](https://github.com/nteract/papermill) for parameterized notebooks\n- Built on top of [nbformat](https://github.com/jupyter/nbformat) and [nbconvert](https://github.com/jupyter/nbconvert)\n- Tested with [pytest](https://pytest.org)\n\n---\n\n## 📮 Contact & Support\n\n- **Issues**: [GitHub Issues](https://github.com/ai-skills/jupyter-notebook-manager/issues)\n- **Discussions**: [GitHub Discussions](https://github.com/ai-skills/jupyter-notebook-manager/discussions)\n- **Email**: skills@ai-community.org\n\n---\n\n## ⭐ Star History\n\nIf you find this skill useful, please consider giving it a star! ⭐\n\n---\n\n**Made with ❤️ by the AI Skills Community**\n\n*Last Updated: 2026-04-16*\n\nFile v1.0.0:tests/README.md\n\n# Jupyter Notebook Manager - Test Suite\n\nThis directory contains comprehensive test cases for the jupyter-notebook-manager skill.\n\n## Test Structure\n\n```\ntests/\n├── README.md (this file)\n├── test_creator.py          # Unit tests for notebook_creator.py\n├── test_executor.py          # Unit tests for notebook_executor.py\n├── test_integration.py       # Integration tests\n├── test_scenarios/           # Real-world scenario tests\n│   ├── scenario_01_eda.md\n│   ├── scenario_02_ml.md\n│   ├── scenario_03_debug.md\n│   └── scenario_04_optimize.md\n└── fixtures/                 # Test data and notebooks\n    ├── sample_data.csv\n    ├── simple_notebook.ipynb\n    ├── error_notebook.ipynb\n    └── large_notebook.ipynb\n```\n\n## Test Categories\n\n### 1. Unit Tests\n\n**Purpose**: Test individual functions and methods\n\n- `test_creator.py`: Notebook creation logic\n  - Template loading\n  - Cell generation\n  - Metadata handling\n  - Custom cell injection\n\n- `test_executor.py`: Notebook execution logic\n  - Execution flow\n  - Parameter injection\n  - Error capture\n  - Output extraction\n\n### 2. Integration Tests\n\n**Purpose**: Test end-to-end workflows\n\n- `test_integration.py`:\n  - Create → Execute workflow\n  - Execute → Analyze workflow\n  - Multi-step operations\n\n### 3. Scenario Tests\n\n**Purpose**: Test real-world use cases\n\n- **Scenario 1: Exploratory Data Analysis**\n  - User provides CSV file\n  - Create EDA notebook\n  - Execute and analyze results\n  - Validate output quality\n\n- **Scenario 2: Machine Learning Pipeline**\n  - User requests ML model training\n  - Create ML notebook\n  - Execute with different parameters\n  - Compare model performances\n\n- **Scenario 3: Debugging Failed Notebook**\n  - User reports notebook error\n  - Identify error cell\n  - Analyze error cause\n  - Suggest fix\n\n- **Scenario 4: Notebook Optimization**\n  - User complains about slow execution\n  - Profile notebook performance\n  - Identify bottlenecks\n  - Provide optimized version\n\n## Test Data\n\n### Sample Datasets\n\n1. **sample_data.csv** - Clean dataset for testing\n   - 1000 rows, 10 columns\n   - Mix of numeric and categorical\n   - No missing values\n   - Known patterns for validation\n\n2. **messy_data.csv** - Dirty dataset for cleaning tests\n   - Missing values (20%)\n   - Duplicates (5%)\n   - Outliers\n   - Type inconsistencies\n\n3. **large_data.csv** - Performance testing\n   - 100,000 rows\n   - Memory stress test\n   - Optimization opportunities\n\n### Test Notebooks\n\n1. **simple_notebook.ipynb** - Basic operations\n   - Simple calculations\n   - Quick execution (<5s)\n   - All cells succeed\n\n2. **error_notebook.ipynb** - Error scenarios\n   - Cell 5 has KeyError\n   - Cell 8 has TypeError\n   - Tests error handling\n\n3. **long_running_notebook.ipynb** - Timeout testing\n   - Has sleep(60) call\n   - Tests timeout handling\n\n4. **large_notebook.ipynb** - Scale testing\n   - 100+ cells\n   - Large outputs\n   - Tests memory handling\n\n## Running Tests\n\n### Quick Test\n\n```bash\n# Run all tests\npython -m pytest tests/ -v\n\n# Run specific test file\npython -m pytest tests/test_creator.py -v\n\n# Run with coverage\npython -m pytest tests/ --cov=scripts --cov-report=html\n```\n\n### Scenario Tests\n\n```bash\n# Run scenario 1: EDA\npython tests/run_scenario.py --scenario eda\n\n# Run scenario 2: ML\npython tests/run_scenario.py --scenario ml\n\n# Run all scenarios\npython tests/run_scenario.py --all\n```\n\n## Test Coverage Goals\n\n- **Code Coverage**: >80%\n- **Branch Coverage**: >70%\n- **Scenario Coverage**: 100% of documented use cases\n\n## Expected Test Results\n\n### Success Criteria\n\n✅ All unit tests pass  \n✅ All integration tests pass  \n✅ At least 4 scenario tests pass  \n✅ No critical bugs found  \n✅ Performance within acceptable range (<10s for simple notebooks)  \n\n### Known Issues\n\n- ⚠️ Timeout tests may be flaky on slow machines\n- ⚠️ Large notebook tests require >2GB RAM\n- ⚠️ Some matplotlib tests may fail in headless environments\n\n## Test Maintenance\n\n### Adding New Tests\n\n1. Identify the feature/bug to test\n2. Create test case in appropriate file\n3. Add test data if needed\n4. Document expected behavior\n5. Update this README\n\n### Updating Tests\n\nWhen modifying scripts, update corresponding tests:\n\n```python\n# Before: Old behavior\nassert result == expected_old\n\n# After: New behavior  \nassert result == expected_new\n```\n\n## CI/CD Integration\n\nThese tests can be integrated into CI/CD pipelines:\n\n```yaml\n# .github/workflows/test.yml\nname: Test Jupyter Notebook Manager\non: [push, pull_request]\njobs:\n  test:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions/checkout@v2\n      - name: Set up Python\n        uses: actions/setup-python@v2\n        with:\n          python-version: '3.9'\n      - name: Install dependencies\n        run: |\n          pip install -r requirements.txt\n          pip install pytest pytest-cov\n      - name: Run tests\n        run: pytest tests/ -v --cov=scripts\n```\n\n## Troubleshooting\n\n### Common Test Failures\n\n**Issue**: ImportError for nbformat\n```bash\n# Solution\npip install nbformat nbconvert jupyter\n```\n\n**Issue**: Timeout in executor tests\n```bash\n# Solution: Increase timeout\npytest tests/test_executor.py --timeout=300\n```\n\n**Issue**: Display issues in viz tests\n```bash\n# Solution: Use headless backend\nexport MPLBACKEND=Agg\npytest tests/\n```\n\n## Test Metrics\n\nTrack these metrics over time:\n\n- Test execution time\n- Coverage percentage\n- Number of flaky tests\n- Bug detection rate\n\n---\n\n**Last Updated**: 2026-04-16  \n**Maintained By**: AI Skills Community\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn740584p7nqabpxt7wtpn9c2184y18n\",\n  \"slug\": \"jupyter-notebook-manager\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776312055218\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:\n\nComplete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[sheng7564](https://clawhub.ai/user/sheng7564)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and data practitioners use this skill to create, execute, debug, analyze, and optimize Jupyter notebooks for data science workflows. It can generate notebook templates, run notebooks with parameters, capture execution results, and provide guidance on notebook errors or performance issues.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Notebook execution can run code from notebooks and injected parameters.\n\nMitigation: Use the skill only with trusted notebooks and trusted parameter values, and run it in an isolated environment with restricted filesystem and network access.\n\nRisk: Generated notebooks may contain incorrect, unsafe, or unsuitable code before review.\n\nMitigation: Review generated notebooks before running them, especially cells that load data, write files, install packages, or execute shell commands.\n\nRisk: Notebook execution may overwrite the input notebook when no output path is provided.\n\nMitigation: Provide an explicit output path for executed notebooks to preserve the original file.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/sheng7564/skills/jupyter-notebook-manager)\n- [Jupyter Documentation](https://jupyter.org/documentation)\n- [nbformat Specification](https://nbformat.readthedocs.io/)\n- [nbconvert Guide](https://nbconvert.readthedocs.io/)\n- [Papermill Documentation](https://papermill.readthedocs.io/)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with Python and shell command examples; generated or executed Jupyter notebook files and execution status summaries.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May create or overwrite .ipynb files and may include captured notebook outputs or error summaries.]\n\n## Skill Version(s):\n\n1.0.0 (source: SKILL.md frontmatter and server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.0:requirements.txt\n\n##Core Dependencies\njupyter>=1.0.0\nnbformat>=5.0.0\nnbconvert>=6.0.0\nipykernel>=6.0.0\n\n# Data Science Libraries\npandas>=1.3.0\nnumpy>=1.20.0\nmatplotlib>=3.3.0\nseaborn>=0.11.0\nscikit-learn>=1.0.0\n\n# Advanced Notebook Tools\npapermill>=2.3.0\nnbdime>=3.1.0\njupyter-client>=7.0.0\n\n# Testing\npytest>=7.0.0\npytest-cov>=3.0.0\npytest-timeout>=2.1.0\n\n# Utilities\npathlib2>=2.3.0; python_version < '3.4'","readmeExcerpt":"Skill: jupyter-notebook-manager Owner: sheng7564 Summary: Complete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-16T04:00:55.218Z | user first commit Archive index: Archive v1.0.0: 10 files, 28798 bytes Files: README.md (10618b), requirements.txt (391b), scripts/notebook_creator.py (24401b), scripts/notebook_execu","codeSnippets":[],"executableExamples":[{"language":"python","snippet":"# User: \"Create a data analysis notebook for sales data\"\n# → Generates structured notebook with:\n#   - Import cells (pandas, numpy, matplotlib)\n#   - Data loading section\n#   - EDA section with common analyses\n#   - Visualization section\n#   - Summary section"},{"language":"python","snippet":"# User: \"Run analysis.ipynb with dataset=sales_2024.csv\"\n# → Executes notebook with parameters\n# → Shows real-time progress\n# → Captures all outputs\n# → Reports execution time and status"},{"language":"python","snippet":"# User: \"My notebook fails at cell 5\"\n# → Analyzes error traceback\n# → Checks variable values before error\n# → Identifies root cause (e.g., missing column)\n# → Suggests fix with corrected code"},{"language":"python","snippet":"# User: \"What variables are defined in this notebook?\"\n# → Lists all variables with types\n# → Shows dataframe shapes and dtypes\n# → Displays memory usage\n# → Highlights key variables"},{"language":"python","snippet":"# User: \"Optimize my data processing notebook\"\n# → Identifies slow loops that can be vectorized\n# → Suggests caching for expensive operations\n# → Recommends better pandas operations\n# → Provides optimized code snippets"},{"language":"python","snippet":"# User: \"Convert my notebook to a Python module\"\n# → Extracts all function definitions\n# → Creates proper module structure\n# → Adds docstrings\n# → Generates import-ready .py file"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: jupyter-notebook-manager\nversion: 1.0.0\nauthor: AI Skills Community\ndescription: Complete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities\ntags:\n  - jupyter\n  - data-science\n  - python\n  - notebook\n  - analysis\ncategory: data-science\nrequires:\n  - jupyter\n  - nbformat\n  - nbconvert\n  - pandas\ntrigger_keywords:\n  - jupyter\n  - notebook\n  - ipynb\n  - data analysis\n  - create notebook\n  - run notebook\n  - debug notebook\n  - execute notebook\n  - analyze data\n---\n\n# Jupyter Notebook Manager\n\nComplete Jupyter notebook management system that enables Claude to create, execute, debug, analyze, and optimize Jupyter notebooks with deep integration of data science workflows.\n\n## 🎯 When to Use This Skill\n\n### Trigger Conditions\n\nUse this skill when you encounter:\n\n1. **User mentions Jupyter-related keywords**:\n   - \"create a Jupyter notebook\"\n   - \"run this notebook\"\n   - \"debug my .ipynb file\"\n   - \"analyze notebook results\"\n   - \"optimize my notebook\"\n\n2. **User requests data analysis workflows**:\n   - \"set up data analysis pipeline\"\n   - \"perform data cleaning\"\n   - \"visualize analysis results\"\n   - \"generate analysis report\"\n\n3. **User provides .ipynb files**:\n   - Detecting .ipynb file references\n   - User uploads notebook files\n   - Working directory contains notebooks\n\n4. **User needs notebook operations**:\n   - \"convert notebook to Python script\"\n   - \"extract code from notebook\"\n   - \"merge multiple notebooks\"\n   - \"generate notebook template\"\n\n## 🚀 Core Capabilities\n\n### 1. Notebook Creation & Templates\n\n**When**: User needs to create new notebooks for specific analysis tasks\n\n**Capabilities**:\n- Generate notebooks from scratch with proper structure\n- Provide domain-specific templates (EDA, ML, visualization)\n- Add markdown documentation and code cells\n- Configure kernel and metadata\n- Support custom templates\n\n**Example**:\n```python\n# User: \"Create a data analysis notebook for sales data\"\n# → Generates structured notebook with:\n#   - Import cells (pandas, numpy, matplotlib)\n#   - Data loading section\n#   - EDA section with common analyses\n#   - Visualization section\n#   - Summary section\n```\n\n### 2. Notebook Execution & Monitoring\n\n**When**: User needs to run notebooks and track execution\n\n**Capabilities**:\n- Execute notebooks programmatically\n- Monitor execution progress\n- Capture outputs and errors\n- Handle long-running cells\n- Support parameterized execution\n\n**Example**:\n```python\n# User: \"Run analysis.ipynb with dataset=sales_2024.csv\"\n# → Executes notebook with parameters\n# → Shows real-time progress\n# → Captures all outputs\n# → Reports execution time and status\n```\n\n### 3. Debugging & Error Analysis\n\n**When**: Notebook execution fails or produces unexpected results\n\n**Capabilities**:\n- Identify error cells and stack traces\n- Analyze variable states at error points\n- Suggest fixes for common issues\n- Detect dependency problems\n- Check data quality issues\n\n**Example**:\n```python\n# Us"},{"path":"README.md","content":"# 🪐 Jupyter Notebook Manager\n\n**Complete Jupyter notebook management system for Claude AI**\n\nA comprehensive skill that enables Claude to create, execute, debug, analyze, and optimize Jupyter notebooks with deep integration of data science workflows.\n\n[![Version](https://img.shields.io/badge/version-1.0.0-blue.svg)](https://github.com/ai-skills/jupyter-notebook-manager)\n[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)\n[![Python](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org)\n\n---\n\n## ✨ Features\n\n###  **8 Core Capabilities**\n\n1. 📝 **Notebook Creation** - Generate notebooks from templates (EDA, ML, Cleaning, etc.)\n2. ▶️ **Notebook Execution** - Run notebooks with monitoring and parameter injection\n3. 🐛 **Debugging & Analysis** - Identify errors, analyze state, suggest fixes\n4. 🔍 **Variable Inspection** - Explore variables, dataframes, and memory usage\n5. ⚡ **Code Optimization** - Detect bottlenecks, suggest improvements\n6. 🔄 **Format Conversion** - Convert between .ipynb, .py, HTML, PDF\n7. 📊 **Results Reporting** - Extract insights and generate summaries\n8. 👥 **Collaboration** - Compare versions, merge changes, resolve conflicts\n\n---\n\n## 🚀 Quick Start\n\n### Installation\n\n```bash\n# Install dependencies\npip install -r requirements.txt\n\n# Verify installation\npython scripts/notebook_creator.py --list-templates\n```\n\n### Basic Usage\n\n#### 1. Create a Notebook\n\n```bash\n# Create from template\npython scripts/notebook_creator.py \\\n  --template exploratory-data-analysis \\\n  --output my_analysis.ipynb \\\n  --data-file sales_data.csv \\\n  --title \"Q4 Sales Analysis\"\n```\n\n#### 2. Execute a Notebook\n\n```bash\n# Run notebook\npython scripts/notebook_executor.py \\\n  my_analysis.ipynb \\\n  --output results.ipynb\n\n# With parameters\npython scripts/notebook_executor.py \\\n  my_analysis.ipynb \\\n  --param dataset=Q4_data.csv \\\n  --param year=2024\n```\n\n#### 3. Use with Claude\n\nJust tell Claude what you need:\n\n```\nUser: \"Create a data analysis notebook for my sales data\"\n\nClaude: I'll create an EDA notebook for you...\n[Creates structured notebook with all analysis sections]\n\nUser: \"Run it with my Q4_sales.csv file\"\n\nClaude: Executing notebook with your data...\n[Shows real-time progress and results]\n```\n\n---\n\n## 📖 Documentation\n\n### Available Templates\n\n| Template | Purpose | Use Case |\n|----------|---------|----------|\n| `exploratory-data-analysis` | Comprehensive EDA | Understand new datasets |\n| `machine-learning-training` | ML model pipeline | Train and evaluate models |\n| `data-cleaning` | Data quality | Clean messy data |\n| `time-series-analysis` | Time series forecasting | Temporal data |\n| `statistical-testing` | Hypothesis testing | Statistical analysis |\n| `visualization-dashboard` | Interactive viz | Present results |\n| `blank` | Minimal structure | Start from scratch |\n\n### Script Reference\n\n#### notebook_creator.py\n\n```bash\npython scripts/notebook_creator.py [OPTIONS]\n\nOptions:\n  --template TEXT          T"},{"path":"tests/README.md","content":"# Jupyter Notebook Manager - Test Suite\n\nThis directory contains comprehensive test cases for the jupyter-notebook-manager skill.\n\n## Test Structure\n\n```\ntests/\n├── README.md (this file)\n├── test_creator.py          # Unit tests for notebook_creator.py\n├── test_executor.py          # Unit tests for notebook_executor.py\n├── test_integration.py       # Integration tests\n├── test_scenarios/           # Real-world scenario tests\n│   ├── scenario_01_eda.md\n│   ├── scenario_02_ml.md\n│   ├── scenario_03_debug.md\n│   └── scenario_04_optimize.md\n└── fixtures/                 # Test data and notebooks\n    ├── sample_data.csv\n    ├── simple_notebook.ipynb\n    ├── error_notebook.ipynb\n    └── large_notebook.ipynb\n```\n\n## Test Categories\n\n### 1. Unit Tests\n\n**Purpose**: Test individual functions and methods\n\n- `test_creator.py`: Notebook creation logic\n  - Template loading\n  - Cell generation\n  - Metadata handling\n  - Custom cell injection\n\n- `test_executor.py`: Notebook execution logic\n  - Execution flow\n  - Parameter injection\n  - Error capture\n  - Output extraction\n\n### 2. Integration Tests\n\n**Purpose**: Test end-to-end workflows\n\n- `test_integration.py`:\n  - Create → Execute workflow\n  - Execute → Analyze workflow\n  - Multi-step operations\n\n### 3. Scenario Tests\n\n**Purpose**: Test real-world use cases\n\n- **Scenario 1: Exploratory Data Analysis**\n  - User provides CSV file\n  - Create EDA notebook\n  - Execute and analyze results\n  - Validate output quality\n\n- **Scenario 2: Machine Learning Pipeline**\n  - User requests ML model training\n  - Create ML notebook\n  - Execute with different parameters\n  - Compare model performances\n\n- **Scenario 3: Debugging Failed Notebook**\n  - User reports notebook error\n  - Identify error cell\n  - Analyze error cause\n  - Suggest fix\n\n- **Scenario 4: Notebook Optimization**\n  - User complains about slow execution\n  - Profile notebook performance\n  - Identify bottlenecks\n  - Provide optimized version\n\n## Test Data\n\n### Sample Datasets\n\n1. **sample_data.csv** - Clean dataset for testing\n   - 1000 rows, 10 columns\n   - Mix of numeric and categorical\n   - No missing values\n   - Known patterns for validation\n\n2. **messy_data.csv** - Dirty dataset for cleaning tests\n   - Missing values (20%)\n   - Duplicates (5%)\n   - Outliers\n   - Type inconsistencies\n\n3. **large_data.csv** - Performance testing\n   - 100,000 rows\n   - Memory stress test\n   - Optimization opportunities\n\n### Test Notebooks\n\n1. **simple_notebook.ipynb** - Basic operations\n   - Simple calculations\n   - Quick execution (<5s)\n   - All cells succeed\n\n2. **error_notebook.ipynb** - Error scenarios\n   - Cell 5 has KeyError\n   - Cell 8 has TypeError\n   - Tests error handling\n\n3. **long_running_notebook.ipynb** - Timeout testing\n   - Has sleep(60) call\n   - Tests timeout handling\n\n4. **large_notebook.ipynb** - Scale testing\n   - 100+ cells\n   - Large outputs\n   - Tests memory handling\n\n## Running Tests\n\n### Quick Test\n\n```bash\n# Run all tests\npython -m pytest tests/ -v\n\n# Run s"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn740584p7nqabpxt7wtpn9c2184y18n\",\n  \"slug\": \"jupyter-notebook-manager\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776312055218\n}"},{"path":"skill-card.md","content":"## Description:\n\nComplete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[sheng7564](https://clawhub.ai/user/sheng7564)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and data practitioners use this skill to create, execute, debug, analyze, and optimize Jupyter notebooks for data science workflows. It can generate notebook templates, run notebooks with parameters, capture execution results, and provide guidance on notebook errors or performance issues.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Notebook execution can run code from notebooks and injected parameters.\n\nMitigation: Use the skill only with trusted notebooks and trusted parameter values, and run it in an isolated environment with restricted filesystem and network access.\n\nRisk: Generated notebooks may contain incorrect, unsafe, or unsuitable code before review.\n\nMitigation: Review generated notebooks before running them, especially cells that load data, write files, install packages, or execute shell commands.\n\nRisk: Notebook execution may overwrite the input notebook when no output path is provided.\n\nMitigation: Provide an explicit output path for executed notebooks to preserve the original file.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/sheng7564/skills/jupyter-notebook-manager)\n- [Jupyter Documentation](https://jupyter.org/documentation)\n- [nbformat Specification](https://nbformat.readthedocs.io/)\n- [nbconvert Guide](https://nbconvert.readthedocs.io/)\n- [Papermill Documentation](https://papermill.readthedocs.io/)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with Python and shell command examples; generated or executed Jupyter notebook files and execution status summaries.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May create or overwrite .ipynb files and may include captured notebook outputs or error summaries.]\n\n## Skill Version(s):\n\n1.0.0 (source: SKILL.md frontmatter and server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Complete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities Skill: jupyter-notebook-manager Owner: sheng7564 Summary: Complete Jupyter notebook management system with creation, execution, debugging, and analysis capabilities Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-16T04:00:55.218Z | user first commit Archive index: Archive v1.0.0: 10 files, 28798 bytes Files: README.md (10618b), requirements.txt (391b), scripts/notebook_creator.py (24401b), scripts/notebook_execu","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1368,"uniquenessScore":45,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T15:06:19.284Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T15:06:19.284Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T17:44:03.443Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}