{"id":"e029e88c-4605-4f08-bd58-88a1d281b65d","entityType":"agent","slug":"clawhub-skills-anisafifi-dataset-finder","name":"dataset-finder","canonicalUrl":"https://www.xpersona.co/agent/clawhub-skills-anisafifi-dataset-finder","canonicalPath":"/agent/clawhub-skills-anisafifi-dataset-finder","generatedAt":"2026-10-10T00:26:03.631Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to \"find datasets\", \"search for data\", \"download dataset from Kaggle\", \"get data from Hugging Face\", \"find ML datasets\", or mentions of data repositories like Kaggle, UCI ML Repository, Data.gov, or Hugging Face. Also use for previewing dataset statistics, generating data cards, or discovering datasets for machine learning projects. Requires OpenClawCLI installation from clawhub.ai. --- name: dataset-finder description: \"Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to \\\"find datasets\\\", \\\"search for data\\\", \\\"download dataset from Kaggle\\\", \\\"get data from Hugging Face\\\", \\\"find ML datasets\\\", or mentions of data repositories like Kaggle, UCI ML Repository, Data.gov, or Hugging Face. Also use for previewing d","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":"clawhub skill install skills:anisafifi:dataset-finder","sourceUrl":"https://github.com/openclaw/skills/tree/main/skills/anisafifi/dataset-finder","homepage":null,"primaryLinks":[{"label":"View on ClawHub","url":"https://github.com/openclaw/skills/tree/main/skills/anisafifi/dataset-finder","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":50,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to \"find datasets\", \"search"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"damage","status":"self-declared"},{"label":"for","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"damage","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"for","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:damage|supported|profile capability:for|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No source adoption metrics were available."},"stars":null,"forks":null,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-02-25T03:36:59.179Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-25T03:36:59.179Z","lastIndexedAt":null,"nextCrawlAt":"2026-02-26T03:36:59.179Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install skills:anisafifi:dataset-finder","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-skills-anisafifi-dataset-finder/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-anisafifi-dataset-finder/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-anisafifi-dataset-finder/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-anisafifi-dataset-finder/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-anisafifi-dataset-finder/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-anisafifi-dataset-finder/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T00:26:03.630Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-anisafifi-dataset-finder/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-anisafifi-dataset-finder/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-anisafifi-dataset-finder/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-anisafifi-dataset-finder/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":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"---\nname: dataset-finder\ndescription: \"Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to \\\"find datasets\\\", \\\"search for data\\\", \\\"download dataset from Kaggle\\\", \\\"get data from Hugging Face\\\", \\\"find ML datasets\\\", or mentions of data repositories like Kaggle, UCI ML Repository, Data.gov, or Hugging Face. Also use for previewing dataset statistics, generating data cards, or discovering datasets for machine learning projects. Requires OpenClawCLI installation from clawhub.ai.\"\nlicense: Proprietary\n---\n\n# Dataset Finder\n\nSearch, download, and explore datasets from multiple repositories including Kaggle, Hugging Face, UCI ML Repository, and Data.gov. Preview statistics, generate data cards, and manage datasets for machine learning projects.\n\n⚠️ **Prerequisite:** Install [OpenClawCLI](https://clawhub.ai/) (Windows, MacOS)\n\n**Installation:**\n```bash\n# Standard installation\npip install kaggle datasets pandas huggingface-hub requests beautifulsoup4\n\n# If you encounter permission errors, use a virtual environment\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\npip install kaggle datasets pandas huggingface-hub requests beautifulsoup4\n```\n\n**Never use `--break-system-packages`** as it can damage your system's Python installation.\n\n---\n\n## Quick Reference\n\n| Task | Command |\n|------|---------|\n| Search Kaggle | `python scripts/dataset.py kaggle search \"housing prices\"` |\n| Download Kaggle dataset | `python scripts/dataset.py kaggle download \"username/dataset-name\"` |\n| Search Hugging Face | `python scripts/dataset.py huggingface search \"sentiment\"` |\n| Download HF dataset | `python scripts/dataset.py huggingface download \"dataset-name\"` |\n| Search UCI ML | `python scripts/dataset.py uci search \"classification\"` |\n| Preview dataset | `python scripts/dataset.py preview dataset.csv` |\n| Generate data card | `python scripts/dataset.py datacard dataset.csv --output README.md` |\n| List local datasets | `python scripts/dataset.py list` |\n\n---\n\n## Core Features\n\n### 1. Multi-Repository Search\n\nSearch across multiple data repositories from a single interface.\n\n**Supported Sources:**\n- **Kaggle** - ML competitions and community datasets\n- **Hugging Face** - NLP, vision, and audio datasets\n- **UCI ML Repository** - Classic ML datasets\n- **Data.gov** - US government open data\n- **Local** - Manage downloaded datasets\n\n### 2. Dataset Download\n\nDownload datasets with automatic format detection.\n\n**Supported formats:**\n- CSV, TSV\n- JSON, JSONL\n- Parquet\n- Excel (XLSX, XLS)\n- ZIP archives\n- HDF5\n- Feather\n\n### 3. Dataset Preview\n\nGet quick statistics and insights without loading entire datasets.\n\n**Preview features:**\n- Shape (rows × columns)\n- Column names and types\n- Missing value counts\n- Basic statistics (mean, std, min, max)\n- Memory usage\n- Sample rows\n\n### 4. Data Card Generation\n\nAutomatically generate dataset documentation.\n\n**Includes:**\n- Dataset description\n- Schema information\n- Statistics summary\n- Usage examples\n- License information\n- Citation details\n\n---\n\n## Repository-Specific Commands\n\n### Kaggle\n\nSearch and download datasets from Kaggle.\n\n**Setup:**\n1. Get Kaggle API credentials from https://www.kaggle.com/settings\n2. Place `kaggle.json` in `~/.kaggle/` (Linux/Mac) or `%USERPROFILE%\\.kaggle\\` (Windows)\n\n```bash\n# Search datasets\npython scripts/dataset.py kaggle search \"house prices\"\n\n# Search with filters\npython scripts/dataset.py kaggle search \"NLP\" --file-type csv --sort-by hotness\n\n# Download dataset\npython scripts/dataset.py kaggle download \"zillow/zecon\"\n\n# Download specific files\npython scripts/dataset.py kaggle download \"username/dataset\" --file \"train.csv\"\n\n# List dataset files\npython scripts/dataset.py kaggle list \"username/dataset-name\"\n```\n\n**Search options:**\n- `--file-type` - Filter by file type (csv, json, etc.)\n- `--license` - Filter by license type\n- `--sort-by` - Sort by hotness, votes, updated, or relevance\n- `--max-results` - Limit number of results\n\n**Output:**\n```\n1. House Prices - Advanced Regression Techniques\n   Owner: zillow/zecon\n   Size: 1.5 MB\n   Last updated: 2023-06-15\n   Downloads: 150,000+\n   URL: https://www.kaggle.com/datasets/zillow/zecon\n\n2. Housing Prices Dataset\n   Owner: username/housing-data\n   Size: 850 KB\n   Last updated: 2023-08-20\n   Downloads: 50,000+\n   URL: https://www.kaggle.com/datasets/username/housing-data\n```\n\n### Hugging Face Datasets\n\nSearch and download datasets from Hugging Face Hub.\n\n```bash\n# Search datasets\npython scripts/dataset.py huggingface search \"sentiment analysis\"\n\n# Search with filters\npython scripts/dataset.py huggingface search \"NLP\" --task text-classification --language en\n\n# Download dataset\npython scripts/dataset.py huggingface download \"imdb\"\n\n# Download specific split\npython scripts/dataset.py huggingface download \"imdb\" --split train\n\n# Download specific configuration\npython scripts/dataset.py huggingface download \"glue\" --config mrpc\n\n# Stream large datasets\npython scripts/dataset.py huggingface download \"large-dataset\" --streaming\n```\n\n**Search options:**\n- `--task` - Filter by task (text-classification, translation, etc.)\n- `--language` - Filter by language code\n- `--multimodal` - Include multimodal datasets\n- `--benchmark` - Only benchmark datasets\n- `--max-results` - Limit results\n\n**Output:**\n```\n1. IMDB Movie Reviews\n   Dataset ID: imdb\n   Tasks: sentiment-classification\n   Languages: en\n   Size: 84.1 MB\n   Downloads: 1M+\n   URL: https://huggingface.co/datasets/imdb\n\n2. Stanford Sentiment Treebank\n   Dataset ID: sst2\n   Tasks: sentiment-classification\n   Languages: en\n   Size: 7.4 MB\n   Downloads: 500K+\n   URL: https://huggingface.co/datasets/sst2\n```\n\n### UCI ML Repository\n\nSearch and download classic ML datasets.\n\n```bash\n# Search datasets\npython scripts/dataset.py uci search \"classification\"\n\n# Search by characteristics\npython scripts/dataset.py uci search \"regression\" --min-samples 1000\n\n# Download dataset\npython scripts/dataset.py uci download \"iris\"\n\n# Download with metadata\npython scripts/dataset.py uci download \"wine-quality\" --include-metadata\n```\n\n**Search options:**\n- `--task-type` - classification, regression, clustering\n- `--min-samples` - Minimum number of instances\n- `--min-features` - Minimum number of features\n- `--data-type` - tabular, text, image, time-series\n\n**Output:**\n```\n1. Iris Dataset\n   ID: iris\n   Task: classification\n   Samples: 150\n   Features: 4\n   Classes: 3\n   Missing values: No\n   URL: https://archive.ics.uci.edu/ml/datasets/iris\n\n2. Wine Quality\n   ID: wine-quality\n   Task: classification/regression\n   Samples: 6497\n   Features: 11\n   Missing values: No\n   URL: https://archive.ics.uci.edu/ml/datasets/wine+quality\n```\n\n### Data.gov\n\nSearch US government open data.\n\n```bash\n# Search datasets\npython scripts/dataset.py datagov search \"census\"\n\n# Search with organization filter\npython scripts/dataset.py datagov search \"health\" --organization \"cdc.gov\"\n\n# Search by topic\npython scripts/dataset.py datagov search \"education\" --tags \"schools,students\"\n\n# Download dataset\npython scripts/dataset.py datagov download \"dataset-id\"\n```\n\n**Search options:**\n- `--organization` - Filter by publishing organization\n- `--tags` - Filter by tags (comma-separated)\n- `--format` - Filter by format (csv, json, xml, etc.)\n- `--max-results` - Limit results\n\n**Output:**\n```\n1. 2020 Census Demographic Data\n   Organization: census.gov\n   Format: CSV\n   Size: 125 MB\n   Last updated: 2023-01-15\n   Tags: census, demographics, population\n   URL: https://catalog.data.gov/dataset/...\n```\n\n---\n\n## Dataset Management\n\n### Preview Datasets\n\nGet quick insights without loading entire datasets.\n\n```bash\n# Basic preview\npython scripts/dataset.py preview data.csv\n\n# Detailed statistics\npython scripts/dataset.py preview data.csv --detailed\n\n# Custom sample size\npython scripts/dataset.py preview data.csv --sample 20\n\n# Multiple files\npython scripts/dataset.py preview train.csv test.csv\n```\n\n**Output:**\n```\nDataset: train.csv\nShape: 1000 rows × 15 columns\nSize: 2.5 MB\nMemory usage: 120 KB\n\nColumns:\n  - id (int64): no missing values\n  - name (object): 5 missing values\n  - age (int64): no missing values\n  - income (float64): 12 missing values\n  - category (object): no missing values\n\nNumeric columns statistics:\n           age       income\ncount   1000.0       988.0\nmean      35.2     65432.1\nstd       12.5     25000.0\nmin       18.0     20000.0\nmax       75.0    150000.0\n\nCategorical columns:\n  - category: 5 unique values\n  - name: 995 unique values\n\nSample (first 5 rows):\n   id      name  age    income category\n0   1  John Doe   35   65000.0        A\n1   2  Jane Doe   28   55000.0        B\n2   3  Bob Smith  42   85000.0        A\n...\n```\n\n### Generate Data Cards\n\nCreate standardized dataset documentation.\n\n```bash\n# Generate data card\npython scripts/dataset.py datacard dataset.csv --output DATACARD.md\n\n# Include statistics\npython scripts/dataset.py datacard dataset.csv --include-stats --output README.md\n\n# Custom template\npython scripts/dataset.py datacard dataset.csv --template custom_template.md\n\n# Multiple datasets\npython scripts/dataset.py datacard train.csv test.csv --output-dir datacards/\n```\n\n**Generated data card includes:**\n- Dataset description\n- File information (size, format, rows, columns)\n- Schema (column names, types, descriptions)\n- Statistics (distributions, missing values, correlations)\n- Sample data\n- Usage examples\n- License and citation\n- Known issues/limitations\n\n**Example output (DATACARD.md):**\n```markdown\n# Dataset Card: Housing Prices\n\n## Dataset Description\nThis dataset contains housing prices and features for regression analysis.\n\n## Dataset Information\n- **Format:** CSV\n- **Size:** 1.2 MB\n- **Rows:** 1,460\n- **Columns:** 81\n\n## Schema\n| Column | Type | Description | Missing |\n|--------|------|-------------|---------|\n| Id | int64 | Unique identifier | 0 |\n| MSSubClass | int64 | Building class | 0 |\n| LotArea | int64 | Lot size in sq ft | 0 |\n| SalePrice | int64 | Sale price | 0 |\n...\n\n## Statistics\n- Numerical features: 38\n- Categorical features: 43\n- Missing values: 19 columns affected\n- Target variable: SalePrice (range: $34,900 - $755,000)\n\n## Usage\n```python\nimport pandas as pd\ndf = pd.read_csv('housing_prices.csv')\n```\n\n## License\nCreative Commons\n```\n\n### List Local Datasets\n\nManage downloaded datasets.\n\n```bash\n# List all datasets\npython scripts/dataset.py list\n\n# List with details\npython scripts/dataset.py list --detailed\n\n# Filter by source\npython scripts/dataset.py list --source kaggle\n\n# Filter by size\npython scripts/dataset.py list --min-size 100MB --max-size 1GB\n```\n\n**Output:**\n```\nLocal Datasets (5 total, 2.5 GB):\n\n1. zillow/zecon (Kaggle)\n   Downloaded: 2024-01-15\n   Size: 1.5 MB\n   Files: train.csv, test.csv\n   Location: datasets/kaggle/zillow/zecon/\n\n2. imdb (Hugging Face)\n   Downloaded: 2024-01-20\n   Size: 84.1 MB\n   Splits: train, test, unsupervised\n   Location: datasets/huggingface/imdb/\n\n3. iris (UCI ML)\n   Downloaded: 2024-01-18\n   Size: 4.5 KB\n   Files: iris.data, iris.names\n   Location: datasets/uci/iris/\n```\n\n---\n\n## Common Workflows\n\n### Machine Learning Project Setup\n\nFind and download datasets for a new ML project.\n\n```bash\n# Step 1: Search for relevant datasets\npython scripts/dataset.py kaggle search \"house prices\" --max-results 10 --output search_results.json\n\n# Step 2: Download selected dataset\npython scripts/dataset.py kaggle download \"zillow/zecon\"\n\n# Step 3: Preview the data\npython scripts/dataset.py preview datasets/kaggle/zillow/zecon/train.csv --detailed\n\n# Step 4: Generate documentation\npython scripts/dataset.py datacard datasets/kaggle/zillow/zecon/train.csv --output DATACARD.md\n```\n\n### NLP Project Dataset Collection\n\nGather text datasets for NLP tasks.\n\n```bash\n# Search Hugging Face for sentiment datasets\npython scripts/dataset.py huggingface search \"sentiment\" --task text-classification --language en\n\n# Download multiple datasets\npython scripts/dataset.py huggingface download \"imdb\"\npython scripts/dataset.py huggingface download \"sst2\"\npython scripts/dataset.py huggingface download \"yelp_polarity\"\n\n# Preview each dataset\npython scripts/dataset.py list --source huggingface\n```\n\n### Dataset Comparison\n\nCompare multiple datasets for selection.\n\n```bash\n# Search across repositories\npython scripts/dataset.py kaggle search \"titanic\" --output kaggle_results.json\npython scripts/dataset.py uci search \"classification\" --output uci_results.json\n\n# Preview candidates\npython scripts/dataset.py preview candidate1.csv --output stats1.txt\npython scripts/dataset.py preview candidate2.csv --output stats2.txt\n\n# Generate comparison data cards\npython scripts/dataset.py datacard candidate1.csv candidate2.csv --output-dir comparison/\n```\n\n### Building a Dataset Library\n\nOrganize datasets for team use.\n\n```bash\n# Create organized structure\nmkdir -p datasets/{kaggle,huggingface,uci,custom}\n\n# Download datasets with metadata\npython scripts/dataset.py kaggle download \"dataset1\" --output-dir datasets/kaggle/\npython scripts/dataset.py huggingface download \"dataset2\" --output-dir datasets/huggingface/\n\n# Generate data cards for all\npython scripts/dataset.py datacard datasets/**/*.csv --output-dir datacards/\n\n# Create inventory\npython scripts/dataset.py list --detailed --output inventory.json\n```\n\n### Data Quality Assessment\n\nAssess dataset quality before use.\n\n```bash\n# Preview with detailed statistics\npython scripts/dataset.py preview dataset.csv --detailed --output quality_report.txt\n\n# Check for issues\npython scripts/dataset.py validate dataset.csv --check-missing --check-duplicates --check-outliers\n\n# Generate comprehensive data card\npython scripts/dataset.py datacard dataset.csv --include-stats --include-quality --output QA_REPORT.md\n```\n\n---\n\n## Advanced Features\n\n### Batch Download\n\nDownload multiple datasets at once.\n\n```bash\n# Create download list\ncat > datasets.txt << EOF\nkaggle:zillow/zecon\nkaggle:username/housing\nhuggingface:imdb\nuci:iris\nEOF\n\n# Batch download\npython scripts/dataset.py batch-download datasets.txt --output-dir datasets/\n```\n\n### Dataset Conversion\n\nConvert between formats.\n\n```bash\n# CSV to Parquet\npython scripts/dataset.py convert data.csv --format parquet --output data.parquet\n\n# Excel to CSV\npython scripts/dataset.py convert data.xlsx --format csv --output data.csv\n\n# JSON to CSV\npython scripts/dataset.py convert data.json --format csv --output data.csv\n```\n\n### Dataset Splitting\n\nSplit datasets for ML workflows.\n\n```bash\n# Train/test split\npython scripts/dataset.py split data.csv --train 0.8 --test 0.2\n\n# Train/val/test split\npython scripts/dataset.py split data.csv --train 0.7 --val 0.15 --test 0.15\n\n# Stratified split\npython scripts/dataset.py split data.csv --stratify target_column --train 0.8 --test 0.2\n```\n\n### Dataset Merging\n\nCombine multiple datasets.\n\n```bash\n# Concatenate datasets\npython scripts/dataset.py merge file1.csv file2.csv --output combined.csv\n\n# Join on key\npython scripts/dataset.py merge left.csv right.csv --on id --how inner --output joined.csv\n```\n\n---\n\n## Best Practices\n\n### Search Strategy\n\n1. **Start broad** - Use general keywords first\n2. **Refine iteratively** - Add filters based on results\n3. **Check multiple sources** - Different repositories have different strengths\n4. **Review metadata** - Check size, format, license before downloading\n\n### Download Management\n\n1. **Check size first** - Use search to see dataset size\n2. **Preview before download** - When possible, preview samples\n3. **Organize by source** - Keep repository structure clear\n4. **Track downloads** - Use list command to manage local datasets\n\n### Data Quality\n\n1. **Always preview** - Check data before using\n2. **Generate data cards** - Document all datasets\n3. **Validate data** - Check for missing values, outliers\n4. **Keep metadata** - Save original descriptions and licenses\n\n### Storage\n\n1. **Use version control** - Track dataset versions\n2. **Compress when possible** - Use Parquet or HDF5 for large datasets\n3. **Clean regularly** - Remove unused datasets\n4. **Backup important data** - Keep copies of critical datasets\n\n---\n\n## Troubleshooting\n\n### Installation Issues\n\n**\"Missing required dependency\"**\n```bash\n# Install all dependencies\npip install kaggle datasets pandas huggingface-hub requests beautifulsoup4\n\n# Or use virtual environment\npython -m venv venv\nsource venv/bin/activate\npip install -r requirements.txt\n```\n\n**\"Kaggle API credentials not found\"**\n1. Go to https://www.kaggle.com/settings\n2. Click \"Create New API Token\"\n3. Save `kaggle.json` to:\n   - Linux/Mac: `~/.kaggle/`\n   - Windows: `%USERPROFILE%\\.kaggle\\`\n4. Set permissions: `chmod 600 ~/.kaggle/kaggle.json`\n\n**\"Hugging Face authentication required\"**\n```bash\n# Login to Hugging Face\nhuggingface-cli login\n\n# Or set token\nexport HF_TOKEN=\"your_token_here\"\n```\n\n### Search Issues\n\n**\"No results found\"**\n- Try broader search terms\n- Remove restrictive filters\n- Check spelling\n- Try different repository\n\n**\"Search timeout\"**\n- Check internet connection\n- Repository may be down temporarily\n- Try again in a few minutes\n\n### Download Issues\n\n**\"Download failed\"**\n- Check internet connection\n- Verify dataset still exists\n- Check available disk space\n- Try downloading specific files\n\n**\"Permission denied\"**\n- Some datasets require accepting terms\n- May need API credentials\n- Check dataset license\n\n**\"Out of memory\"**\n- Use streaming for large datasets\n- Download in chunks\n- Use Parquet instead of CSV\n\n### Preview Issues\n\n**\"Cannot load dataset\"**\n- Check file format\n- Verify file is not corrupted\n- Try specifying encoding: `--encoding utf-8`\n\n**\"Preview too slow\"**\n- Use smaller sample size\n- Preview first N rows only\n- Use format-specific tools\n\n---\n\n## Command Reference\n\n```bash\npython scripts/dataset.py <command> [OPTIONS]\n\nCOMMANDS:\n  kaggle              Kaggle operations (search, download, list)\n  huggingface         Hugging Face operations\n  uci                 UCI ML Repository operations\n  datagov             Data.gov operations\n  preview             Preview dataset statistics\n  datacard            Generate dataset documentation\n  list                List local datasets\n  batch-download      Download multiple datasets\n  convert             Convert dataset formats\n  split               Split dataset for ML\n  merge               Combine datasets\n\nKAGGLE:\n  search QUERY        Search Kaggle datasets\n    --file-type       Filter by file type\n    --license         Filter by license\n    --sort-by         Sort results\n    --max-results     Limit results\n  \n  download DATASET    Download Kaggle dataset\n    --file            Download specific file\n    --output-dir      Output directory\n\nHUGGING FACE:\n  search QUERY        Search HF datasets\n    --task            Filter by task\n    --language        Filter by language\n    --max-results     Limit results\n  \n  download DATASET    Download HF dataset\n    --split           Specific split\n    --config          Configuration\n    --streaming       Stream large datasets\n\nUCI:\n  search QUERY        Search UCI datasets\n    --task-type       Filter by task\n    --min-samples     Minimum samples\n  \n  download DATASET    Download UCI dataset\n\nPREVIEW:\n  preview FILE        Preview dataset\n    --detailed        Detailed statistics\n    --sample N        Sample size\n\nDATACARD:\n  datacard FILE       Generate data card\n    --output          Output file\n    --include-stats   Include statistics\n    --template        Custom template\n\nLIST:\n  list                List local datasets\n    --detailed        Show details\n    --source          Filter by source\n\nHELP:\n  --help              Show help\n```\n\n---\n\n## Examples by Use Case\n\n### Quick Dataset Search\n\n```bash\n# Find housing datasets\npython scripts/dataset.py kaggle search \"housing\"\n\n# Find NLP datasets\npython scripts/dataset.py huggingface search \"sentiment\" --task text-classification\n\n# Find classic ML datasets\npython scripts/dataset.py uci search \"classification\"\n```\n\n### Download and Preview\n\n```bash\n# Download from Kaggle\npython scripts/dataset.py kaggle download \"zillow/zecon\"\n\n# Preview the data\npython scripts/dataset.py preview datasets/kaggle/zillow/zecon/train.csv --detailed\n\n# Generate documentation\npython scripts/dataset.py datacard datasets/kaggle/zillow/zecon/train.csv\n```\n\n### Multi-Source Search\n\n```bash\n# Search all repositories\npython scripts/dataset.py kaggle search \"titanic\" --output kaggle.json\npython scripts/dataset.py huggingface search \"titanic\" --output hf.json\npython scripts/dataset.py uci search \"classification\" --output uci.json\n\n# Compare results\ncat kaggle.json hf.json uci.json\n```\n\n### Dataset Management\n\n```bash\n# List all downloaded datasets\npython scripts/dataset.py list --detailed\n\n# Preview multiple datasets\npython scripts/dataset.py preview *.csv\n\n# Generate data cards for all\npython scripts/dataset.py datacard *.csv --output-dir datacards/\n```\n\n---\n\n## Support\n\nFor issues or questions:\n1. Check this documentation\n2. Run `python scripts/dataset.py --help`\n3. Verify API credentials are set\n4. Check repository-specific documentation\n\n**Resources:**\n- OpenClawCLI: https://clawhub.ai/\n- Kaggle API: https://github.com/Kaggle/kaggle-api\n- Hugging Face Datasets: https://huggingface.co/docs/datasets/\n- UCI ML Repository: https://archive.ics.uci.edu/ml/\n- Data.gov API: https://www.data.gov/developers/apis","readmeExcerpt":"--- name: dataset-finder description: \"Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to \\\"find datasets\\\", \\\"search for data\\\", \\\"download dataset from Kaggle\\\", \\\"get data from Hugging Face\\\", \\\"find ML datasets\\\", or mentions of data repositories like Kaggle, UCI ML Repository, Data.gov, or Hugging Face. Also use for previewing d","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Standard installation\npip install kaggle datasets pandas huggingface-hub requests beautifulsoup4\n\n# If you encounter permission errors, use a virtual environment\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\npip install kaggle datasets pandas huggingface-hub requests beautifulsoup4"},{"language":"bash","snippet":"# Search datasets\npython scripts/dataset.py kaggle search \"house prices\"\n\n# Search with filters\npython scripts/dataset.py kaggle search \"NLP\" --file-type csv --sort-by hotness\n\n# Download dataset\npython scripts/dataset.py kaggle download \"zillow/zecon\"\n\n# Download specific files\npython scripts/dataset.py kaggle download \"username/dataset\" --file \"train.csv\"\n\n# List dataset files\npython scripts/dataset.py kaggle list \"username/dataset-name\""},{"language":"text","snippet":"1. House Prices - Advanced Regression Techniques\n   Owner: zillow/zecon\n   Size: 1.5 MB\n   Last updated: 2023-06-15\n   Downloads: 150,000+\n   URL: https://www.kaggle.com/datasets/zillow/zecon\n\n2. Housing Prices Dataset\n   Owner: username/housing-data\n   Size: 850 KB\n   Last updated: 2023-08-20\n   Downloads: 50,000+\n   URL: https://www.kaggle.com/datasets/username/housing-data"},{"language":"bash","snippet":"# Search datasets\npython scripts/dataset.py huggingface search \"sentiment analysis\"\n\n# Search with filters\npython scripts/dataset.py huggingface search \"NLP\" --task text-classification --language en\n\n# Download dataset\npython scripts/dataset.py huggingface download \"imdb\"\n\n# Download specific split\npython scripts/dataset.py huggingface download \"imdb\" --split train\n\n# Download specific configuration\npython scripts/dataset.py huggingface download \"glue\" --config mrpc\n\n# Stream large datasets\npython scripts/dataset.py huggingface download \"large-dataset\" --streaming"},{"language":"text","snippet":"1. IMDB Movie Reviews\n   Dataset ID: imdb\n   Tasks: sentiment-classification\n   Languages: en\n   Size: 84.1 MB\n   Downloads: 1M+\n   URL: https://huggingface.co/datasets/imdb\n\n2. Stanford Sentiment Treebank\n   Dataset ID: sst2\n   Tasks: sentiment-classification\n   Languages: en\n   Size: 7.4 MB\n   Downloads: 500K+\n   URL: https://huggingface.co/datasets/sst2"},{"language":"bash","snippet":"# Search datasets\npython scripts/dataset.py uci search \"classification\"\n\n# Search by characteristics\npython scripts/dataset.py uci search \"regression\" --min-samples 1000\n\n# Download dataset\npython scripts/dataset.py uci download \"iris\"\n\n# Download with metadata\npython scripts/dataset.py uci download \"wine-quality\" --include-metadata"}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to \"find datasets\", \"search for data\", \"download dataset from Kaggle\", \"get data from Hugging Face\", \"find ML datasets\", or mentions of data repositories like Kaggle, UCI ML Repository, Data.gov, or Hugging Face. Also use for previewing dataset statistics, generating data cards, or discovering datasets for machine learning projects. Requires OpenClawCLI installation from clawhub.ai. --- name: dataset-finder description: \"Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to \\\"find datasets\\\", \\\"search for data\\\", \\\"download dataset from Kaggle\\\", \\\"get data from Hugging Face\\\", \\\"find ML datasets\\\", or mentions of data repositories like Kaggle, UCI ML Repository, Data.gov, or Hugging Face. Also use for previewing d","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":437,"uniquenessScore":57,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","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":"2026-04-15T00:45:39.800Z","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":"2026-10-10T00:26:03.631Z","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"}]}}}