[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75JGX2FD0Y4WNZ6CZWMDJF9":3,"skill-same:01M75JGX2FD0Y4WNZ6CZWMDJF9":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M75JGX2FD0Y4WNZ6CZWMDJF9","powerdrill-data-analysis",null,"This skill should be used when the user wants to analyze, explore, visualize, or query data using Powerdrill. Covers listing, creating, and deleting datasets; uploading local files as data sources; creating analysis sessions; running natural-language data analysis queries; and retrieving charts, tables, and insights. Triggers on requests like \"analyze my data\", \"query my dataset\", \"upload this file for analysis\", \"list my datasets\", \"create a dataset\", \"visualize sales trends\", \"continue my previous analysis\", \"delete this dataset\", or any data exploration task mentioning Powerdrill.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fjavainthinking\u002Fpowerdrill-skills\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: powerdrill-data-analysis\ndescription: This skill should be used when the user wants to analyze, explore, visualize, or query data using Powerdrill. Covers listing, creating, and deleting datasets; uploading local files as data sources; creating analysis sessions; running natural-language data analysis queries; and retrieving charts, tables, and insights. Triggers on requests like \"analyze my data\", \"query my dataset\", \"upload this file for analysis\", \"list my datasets\", \"create a dataset\", \"visualize sales trends\", \"continue my previous analysis\", \"delete this dataset\", or any data exploration task mentioning Powerdrill.\nlicense: MIT\ncompatibility: claude\nmetadata:\n  audience: human\n  workflow: powerdrill\n---\n\n# Powerdrill Data Analysis Skill\n\nAnalyze data using the Powerdrill API via the Python client at `scripts\u002Fpowerdrill_client.py`. All operations use the Powerdrill REST API v2 (`https:\u002F\u002Fai.data.cloud\u002Fapi`).\n\n## Prerequisites & Setup\n\nBefore using any Powerdrill functions, the user must have:\n\n1. **A Powerdrill Teamspace** - Created by following: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=I-0yGD9HeDw\n2. **API Credentials** - Obtained by following: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qs-GsUgjb1g\n\nSet these environment variables before running any script:\n\n```bash\nexport POWERDRILL_USER_ID=\"your_user_id\"\nexport POWERDRILL_PROJECT_API_KEY=\"your_project_api_key\"\n```\n\nThe only Python dependency is `requests`. Install with: `pip install requests`\n\nIf a call fails with an authentication error, verify the two environment variables are set and the API key is valid.\n\n## How to Use\n\nImport the client module and call functions directly. All functions read credentials from the environment automatically.\n\n```python\nimport sys\nsys.path.insert(0, \"\u002Fabsolute\u002Fpath\u002Fto\u002Fscripts\")  # adjust to actual location\nfrom powerdrill_client import *\n```\n\nOr run via CLI:\n\n```bash\npython scripts\u002Fpowerdrill_client.py \u003Ccommand> [args]\n```\n\n## Available Functions\n\n### Datasets\n\n#### `list_datasets(page_number=1, page_size=10, search=None) -> dict`\nList datasets in the user's account. Typically the first step in any workflow.\n\n```python\nresult = list_datasets(search=\"sales\")\nfor ds in result[\"data\"][\"records\"]:\n    print(ds[\"id\"], ds[\"name\"])\n```\n\n#### `create_dataset(name, description=\"\") -> dict`\nCreate a new empty dataset. Returns `{\"data\": {\"id\": \"dset-...\"}}`.\n\n```python\nds = create_dataset(\"Q4 Sales Data\", \"Quarterly sales analysis\")\ndataset_id = ds[\"data\"][\"id\"]\n```\n\n#### `get_dataset_overview(dataset_id) -> dict`\nGet dataset summary, exploration questions, and keywords. Use after data sources are synced.\n\n```python\noverview = get_dataset_overview(dataset_id)\nprint(overview[\"data\"][\"summary\"])\nfor q in overview[\"data\"][\"exploration_questions\"]:\n    print(f\"  - {q}\")\n```\n\n#### `get_dataset_status(dataset_id) -> dict`\nCheck how many data sources are synced\u002Fsyncing\u002Finvalid.\n\n```python\nstatus = get_dataset_status(dataset_id)\n# status[\"data\"] = {\"synched_count\": 3, \"synching_count\": 0, \"invalid_count\": 0}\n```\n\n#### `delete_dataset(dataset_id) -> dict`\nPermanently delete a dataset and all its data sources. **Irreversible** - always confirm with the user first.\n\n### Data Sources\n\n#### `list_data_sources(dataset_id, page_number=1, page_size=10, status=None) -> dict`\nList files within a dataset. Filter by status: `synched`, `synching`, `invalid`.\n\n```python\nsources = list_data_sources(dataset_id, status=\"synched\")\n```\n\n#### `create_data_source(dataset_id, name, *, url=None, file_object_key=None) -> dict`\nCreate a data source from a public URL or an uploaded file key. Provide exactly one of `url` or `file_object_key`.\n\n```python\n# From public URL\nds = create_data_source(dataset_id, \"report.pdf\", url=\"https:\u002F\u002Fexample.com\u002Freport.pdf\")\n\n# From uploaded file (see upload_local_file)\nds = create_data_source(dataset_id, \"data.csv\", file_object_key=key)\n```\n\n#### `upload_local_file(file_path) -> str`\nUpload a local file via multipart upload. Returns `file_object_key` for use with `create_data_source()`.\n\nSupported formats: `.csv`, `.tsv`, `.md`, `.mdx`, `.json`, `.txt`, `.pdf`, `.pptx`, `.docx`, `.xls`, `.xlsx`\n\n#### `upload_and_create_data_source(dataset_id, file_path) -> dict`\nConvenience function: uploads a local file then creates the data source in one call.\n\n```python\nresult = upload_and_create_data_source(dataset_id, \"\u002Fpath\u002Fto\u002Fsales.csv\")\ndatasource_id = result[\"data\"][\"id\"]\n```\n\n#### `wait_for_dataset_sync(dataset_id, max_attempts=30, delay_seconds=3.0) -> dict`\nPoll until all data sources in the dataset are synced. Raises `RuntimeError` on timeout or if invalid sources are detected.\n\n```python\nupload_and_create_data_source(dataset_id, \"data.csv\")\nwait_for_dataset_sync(dataset_id)  # blocks until synced\n```\n\n### Sessions\n\n#### `create_session(name, output_language=\"AUTO\", job_mode=\"AUTO\", max_contextual_job_history=10) -> dict`\nCreate an analysis session. Required before running jobs.\n\n```python\nsession = create_session(\"Sales Analysis Session\")\nsession_id = session[\"data\"][\"id\"]\n```\n\n#### `list_sessions(page_number=1, page_size=10, search=None) -> dict`\nList existing sessions. Use to find a previous session for resumption.\n\n#### `delete_session(session_id) -> dict`\nDelete a session. Use during cleanup after analysis is complete.\n\n### Jobs (Data Analysis)\n\n#### `create_job(session_id, question, dataset_id=None, datasource_ids=None, stream=False, output_language=\"AUTO\", job_mode=\"AUTO\") -> dict`\nRun a natural-language analysis query. This is the core analysis function.\n\n**Non-streaming** (default): returns full response with all blocks.\n\n```python\nresult = create_job(session_id, \"What are the top 5 products by revenue?\", dataset_id=dataset_id)\nfor block in result[\"data\"][\"blocks\"]:\n    if block[\"type\"] == \"MESSAGE\":\n        print(block[\"content\"])\n    elif block[\"type\"] == \"TABLE\":\n        print(f\"Table: {block['content']['url']}\")\n    elif block[\"type\"] == \"IMAGE\":\n        print(f\"Chart: {block['content']['url']}\")\n```\n\n**Streaming**: returns parsed result with accumulated text and separate blocks.\n\n```python\nresult = create_job(session_id, \"Summarize trends\", dataset_id=dataset_id, stream=True)\nprint(result[\"text\"])        # accumulated MESSAGE text\nfor b in result[\"blocks\"]:   # TABLE, IMAGE, etc.\n    print(b[\"type\"], b[\"content\"])\n```\n\n**Response block types:**\n- `MESSAGE` - Analytical text\n- `CODE` - Code snippets (Markdown)\n- `TABLE` - `{name, url, expires_at}` - download before expiration\n- `IMAGE` - `{name, url, expires_at}` - download before expiration\n- `SOURCES` - Citation references\n- `QUESTIONS` - Suggested follow-up questions\n- `CHART_INFO` - Chart configuration and data\n\n### Cleanup\n\n#### `cleanup(session_id=None, dataset_id=None) -> None`\nDelete session and\u002For dataset after analysis. Always call this when done.\n\n```python\ncleanup(session_id=session_id, dataset_id=dataset_id)\n```\n\n#### `cleanup_session(session_id) -> None` \u002F `cleanup_dataset(dataset_id) -> None`\nDelete individual resources. Errors are logged but not raised.\n\n## Recommended Workflows\n\n### Full analysis workflow (upload, analyze, cleanup)\n\n```python\nfrom powerdrill_client import *\n\n# 1. Create dataset and upload data\nds = create_dataset(\"My Analysis\")\ndataset_id = ds[\"data\"][\"id\"]\n\nupload_and_create_data_source(dataset_id, \"\u002Fpath\u002Fto\u002Fdata.csv\")\nwait_for_dataset_sync(dataset_id)\n\n# 2. Create session and run analysis\nsession = create_session(\"Analysis Session\")\nsession_id = session[\"data\"][\"id\"]\n\nresult = create_job(session_id, \"What are the key trends?\", dataset_id=dataset_id)\nfor block in result[\"data\"][\"blocks\"]:\n    if block[\"type\"] == \"MESSAGE\":\n        print(block[\"content\"])\n\n# 3. Ask follow-up questions (same session for context)\nresult = create_job(session_id, \"Break this down by region\", dataset_id=dataset_id)\n\n# 4. Cleanup when done\ncleanup(session_id=session_id, dataset_id=dataset_id)\n```\n\n### Analyze existing dataset\n\n```python\nfrom powerdrill_client import *\n\n# 1. Find the dataset\ndatasets = list_datasets(search=\"sales\")\ndataset_id = datasets[\"data\"][\"records\"][0][\"id\"]\n\n# 2. Explore it\noverview = get_dataset_overview(dataset_id)\nprint(overview[\"data\"][\"summary\"])\n\n# 3. Create session and analyze\nsession = create_session(\"Quick Analysis\")\nsession_id = session[\"data\"][\"id\"]\n\nresult = create_job(session_id, overview[\"data\"][\"exploration_questions\"][0], dataset_id=dataset_id)\n\n# 4. Cleanup session when done (keep dataset)\ncleanup_session(session_id)\n```\n\n### CLI usage\n\n```bash\n# List datasets\npython scripts\u002Fpowerdrill_client.py list-datasets --search \"sales\"\n\n# Create dataset + upload file\npython scripts\u002Fpowerdrill_client.py create-dataset \"Test Data\"\npython scripts\u002Fpowerdrill_client.py upload-file dset-xxx \u002Fpath\u002Fto\u002Ffile.csv\npython scripts\u002Fpowerdrill_client.py wait-sync dset-xxx\n\n# Create session and run a job\npython scripts\u002Fpowerdrill_client.py create-session \"My Session\"\npython scripts\u002Fpowerdrill_client.py create-job SESSION_ID \"Summarize the data\" --dataset-id dset-xxx\n\n# Cleanup\npython scripts\u002Fpowerdrill_client.py cleanup --session-id SESSION_ID --dataset-id dset-xxx\n```\n\n## Error Handling\n\n- **Authentication errors:** Verify `POWERDRILL_USER_ID` and `POWERDRILL_PROJECT_API_KEY`. Direct the user to the setup videos above.\n- **Dataset not found:** Re-run `list_datasets()` to verify the ID. The dataset may have been deleted.\n- **Job execution failure:** Ensure the dataset has at least one synced data source (`wait_for_dataset_sync()`). Retry with a rephrased question.\n- **Upload timeout:** `wait_for_dataset_sync()` polls up to 30 attempts (90s). Use `get_dataset_status()` to check manually.\n- **Invalid data sources:** Check file format is supported. Re-upload with correct file type.\n- **Rate limiting:** Wait before retrying. Space out rapid sequential API calls.\n\n## Important Notes\n\n- Always create a session before running analysis jobs\n- Always call `cleanup()` to delete sessions and datasets after analysis is complete\n- Sessions maintain conversational context - reuse the same session for related follow-up questions\n- TABLE and IMAGE URLs in job responses expire - download or present results promptly\n- Call `wait_for_dataset_sync()` after uploading files, before running analysis\n- Dataset and session names are limited to 128 characters\n- Supported file formats: `.csv`, `.tsv`, `.md`, `.mdx`, `.json`, `.txt`, `.pdf`, `.pptx`, `.docx`, `.xls`, `.xlsx`\n","# Powerdrill Data Analysis Skill\n\nAnalyze data using the Powerdrill API via the Python client at `scripts\u002Fpowerdrill_client.py`. All operations use the Powerdrill REST API v2 (`https:\u002F\u002Fai.data.cloud\u002Fapi`).\n\n## Prerequisites & Setup\n\nBefore using any Powerdrill functions, the user must have:\n\n1. **A Powerdrill Teamspace** - Created by following: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=I-0yGD9HeDw\n2. **API Credentials** - Obtained by following: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qs-GsUgjb1g\n\nSet these environment variables before running any script:\n\n```bash\nexport POWERDRILL_USER_ID=\"your_user_id\"\nexport POWERDRILL_PROJECT_API_KEY=\"your_project_api_key\"\n```\n\nThe only Python dependency is `requests`. Install with: `pip install requests`\n\nIf a call fails with an authentication error, verify the two environment variables are set and the API key is valid.\n\n## How to Use\n\nImport the client module and call functions directly. All functions read credentials from the environment automatically.\n\n```python\nimport sys\nsys.path.insert(0, \"\u002Fabsolute\u002Fpath\u002Fto\u002Fscripts\")  # adjust to actual location\nfrom powerdrill_client import *\n```\n\nOr run via CLI:\n\n```bash\npython scripts\u002Fpowerdrill_client.py \u003Ccommand> [args]\n```\n\n## Available Functions\n\n### Datasets\n\n#### `list_datasets(page_number=1, page_size=10, search=None) -> dict`\nList datasets in the user's account. Typically the first step in any workflow.\n\n```python\nresult = list_datasets(search=\"sales\")\nfor ds in result[\"data\"][\"records\"]:\n    print(ds[\"id\"], ds[\"name\"])\n```\n\n#### `create_dataset(name, description=\"\") -> dict`\nCreate a new empty dataset. Returns `{\"data\": {\"id\": \"dset-...\"}}`.\n\n```python\nds = create_dataset(\"Q4 Sales Data\", \"Quarterly sales analysis\")\ndataset_id = ds[\"data\"][\"id\"]\n```\n\n#### `get_dataset_overview(dataset_id) -> dict`\nGet dataset summary, exploration questions, and keywords. Use after data sources are synced.\n\n```python\noverview = get_dataset_overview(dataset_id)\nprint(overview[\"data\"][\"summary\"])\nfor q in overview[\"data\"][\"exploration_questions\"]:\n    print(f\"  - {q}\")\n```\n\n#### `get_dataset_status(dataset_id) -> dict`\nCheck how many data sources are synced\u002Fsyncing\u002Finvalid.\n\n```python\nstatus = get_dataset_status(dataset_id)\n# status[\"data\"] = {\"synched_count\": 3, \"synching_count\": 0, \"invalid_count\": 0}\n```\n\n#### `delete_dataset(dataset_id) -> dict`\nPermanently delete a dataset and all its data sources. **Irreversible** - always confirm with the user first.\n\n### Data Sources\n\n#### `list_data_sources(dataset_id, page_number=1, page_size=10, status=None) -> dict`\nList files within a dataset. Filter by status: `synched`, `synching`, `invalid`.\n\n```python\nsources = list_data_sources(dataset_id, status=\"synched\")\n```\n\n#### `create_data_source(dataset_id, name, *, url=None, file_object_key=None) -> dict`\nCreate a data source from a public URL or an uploaded file key. Provide exactly one of `url` or `file_object_key`.\n\n```python\n# From public URL\nds = create_data_source(dataset_id, \"report.pdf\", url=\"https:\u002F\u002Fexample.com\u002Freport.pdf\")\n\n# From uploaded file (see upload_local_file)\nds = create_data_source(dataset_id, \"data.csv\", file_object_key=key)\n```\n\n#### `upload_local_file(file_path) -> str`\nUpload a local file via multipart upload. Returns `file_object_key` for use with `create_data_source()`.\n\nSupported formats: `.csv`, `.tsv`, `.md`, `.mdx`, `.json`, `.txt`, `.pdf`, `.pptx`, `.docx`, `.xls`, `.xlsx`\n\n#### `upload_and_create_data_source(dataset_id, file_path) -> dict`\nConvenience function: uploads a local file then creates the data source in one call.\n\n```python\nresult = upload_and_create_data_source(dataset_id, \"\u002Fpath\u002Fto\u002Fsales.csv\")\ndatasource_id = result[\"data\"][\"id\"]\n```\n\n#### `wait_for_dataset_sync(dataset_id, max_attempts=30, delay_seconds=3.0) -> dict`\nPoll until all data sources in the dataset are synced. Raises `RuntimeError` on timeout or if invalid sources are detected.\n\n```python\nupload_and_create_data_source(dataset_id, \"data.csv\")\nwait_for_dataset_sync(dataset_id)  # blocks until synced\n```\n\n### Sessions\n\n#### `create_session(name, output_language=\"AUTO\", job_mode=\"AUTO\", max_contextual_job_history=10) -> dict`\nCreate an analysis session. Required before running jobs.\n\n```python\nsession = create_session(\"Sales Analysis Session\")\nsession_id = session[\"data\"][\"id\"]\n```\n\n#### `list_sessions(page_number=1, page_size=10, search=None) -> dict`\nList existing sessions. Use to find a previous session for resumption.\n\n#### `delete_session(session_id) -> dict`\nDelete a session. Use during cleanup after analysis is complete.\n\n### Jobs (Data Analysis)\n\n#### `create_job(session_id, question, dataset_id=None, datasource_ids=None, stream=False, output_language=\"AUTO\", job_mode=\"AUTO\") -> dict`\nRun a natural-language analysis query. This is the core analysis function.\n\n**Non-streaming** (default): returns full response with all blocks.\n\n```python\nresult = create_job(session_id, \"What are the top 5 products by revenue?\", dataset_id=dataset_id)\nfor block in result[\"data\"][\"blocks\"]:\n    if block[\"type\"] == \"MESSAGE\":\n        print(block[\"content\"])\n    elif block[\"type\"] == \"TABLE\":\n        print(f\"Table: {block['content']['url']}\")\n    elif block[\"type\"] == \"IMAGE\":\n        print(f\"Chart: {block['content']['url']}\")\n```\n\n**Streaming**: returns parsed result with accumulated text and separate blocks.\n\n```python\nresult = create_job(session_id, \"Summarize trends\", dataset_id=dataset_id, stream=True)\nprint(result[\"text\"])        # accumulated MESSAGE text\nfor b in result[\"blocks\"]:   # TABLE, IMAGE, etc.\n    print(b[\"type\"], b[\"content\"])\n```\n\n**Response block types:**\n- `MESSAGE` - Analytical text\n- `CODE` - Code snippets (Markdown)\n- `TABLE` - `{name, url, expires_at}` - download before expiration\n- `IMAGE` - `{name, url, expires_at}` - download before expiration\n- `SOURCES` - Citation references\n- `QUESTIONS` - Suggested follow-up questions\n- `CHART_INFO` - Chart configuration and data\n\n### Cleanup\n\n#### `cleanup(session_id=None, dataset_id=None) -> None`\nDelete session and\u002For dataset after analysis. Always call this when done.\n\n```python\ncleanup(session_id=session_id, dataset_id=dataset_id)\n```\n\n#### `cleanup_session(session_id) -> None` \u002F `cleanup_dataset(dataset_id) -> None`\nDelete individual resources. Errors are logged but not raised.\n\n## Recommended Workflows\n\n### Full analysis workflow (upload, analyze, cleanup)\n\n```python\nfrom powerdrill_client import *\n\n# 1. Create dataset and upload data\nds = create_dataset(\"My Analysis\")\ndataset_id = ds[\"data\"][\"id\"]\n\nupload_and_create_data_source(dataset_id, \"\u002Fpath\u002Fto\u002Fdata.csv\")\nwait_for_dataset_sync(dataset_id)\n\n# 2. Create session and run analysis\nsession = create_session(\"Analysis Session\")\nsession_id = session[\"data\"][\"id\"]\n\nresult = create_job(session_id, \"What are the key trends?\", dataset_id=dataset_id)\nfor block in result[\"data\"][\"blocks\"]:\n    if block[\"type\"] == \"MESSAGE\":\n        print(block[\"content\"])\n\n# 3. Ask follow-up questions (same session for context)\nresult = create_job(session_id, \"Break this down by region\", dataset_id=dataset_id)\n\n# 4. Cleanup when done\ncleanup(session_id=session_id, dataset_id=dataset_id)\n```\n\n### Analyze existing dataset\n\n```python\nfrom powerdrill_client import *\n\n# 1. Find the dataset\ndatasets = list_datasets(search=\"sales\")\ndataset_id = datasets[\"data\"][\"records\"][0][\"id\"]\n\n# 2. Explore it\noverview = get_dataset_overview(dataset_id)\nprint(overview[\"data\"][\"summary\"])\n\n# 3. Create session and analyze\nsession = create_session(\"Quick Analysis\")\nsession_id = session[\"data\"][\"id\"]\n\nresult = create_job(session_id, overview[\"data\"][\"exploration_questions\"][0], dataset_id=dataset_id)\n\n# 4. Cleanup session when done (keep dataset)\ncleanup_session(session_id)\n```\n\n### CLI usage\n\n```bash\n# List datasets\npython scripts\u002Fpowerdrill_client.py list-datasets --search \"sales\"\n\n# Create dataset + upload file\npython scripts\u002Fpowerdrill_client.py create-dataset \"Test Data\"\npython scripts\u002Fpowerdrill_client.py upload-file dset-xxx \u002Fpath\u002Fto\u002Ffile.csv\npython scripts\u002Fpowerdrill_client.py wait-sync dset-xxx\n\n# Create session and run a job\npython scripts\u002Fpowerdrill_client.py create-session \"My Session\"\npython scripts\u002Fpowerdrill_client.py create-job SESSION_ID \"Summarize the data\" --dataset-id dset-xxx\n\n# Cleanup\npython scripts\u002Fpowerdrill_client.py cleanup --session-id SESSION_ID --dataset-id dset-xxx\n```\n\n## Error Handling\n\n- **Authentication errors:** Verify `POWERDRILL_USER_ID` and `POWERDRILL_PROJECT_API_KEY`. Direct the user to the setup videos above.\n- **Dataset not found:** Re-run `list_datasets()` to verify the ID. The dataset may have been deleted.\n- **Job execution failure:** Ensure the dataset has at least one synced data source (`wait_for_dataset_sync()`). Retry with a rephrased question.\n- **Upload timeout:** `wait_for_dataset_sync()` polls up to 30 attempts (90s). Use `get_dataset_status()` to check manually.\n- **Invalid data sources:** Check file format is supported. Re-upload with correct file type.\n- **Rate limiting:** Wait before retrying. Space out rapid sequential API calls.\n\n## Important Notes\n\n- Always create a session before running analysis jobs\n- Always call `cleanup()` to delete sessions and datasets after analysis is complete\n- Sessions maintain conversational context - reuse the same session for related follow-up questions\n- TABLE and IMAGE URLs in job responses expire - download or present results promptly\n- Call `wait_for_dataset_sync()` after uploading files, before running analysis\n- Dataset and session names are limited to 128 characters\n- Supported file formats: `.csv`, `.tsv`, `.md`, `.mdx`, `.json`, `.txt`, `.pdf`, `.pptx`, `.docx`, `.xls`, `.xlsx`\n",{"name":5,"license":15,"metadata":24,"description":7,"compatibility":27},{"audience":25,"workflow":26},"human","powerdrill","claude","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fjavainthinking\u002Fpowerdrill-skills",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill powerdrill-data-analysis",{"tool":43,"command":44},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill powerdrill-data-analysis",{"tool":46,"command":47},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill powerdrill-data-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fjavainthinking\u002Fpowerdrill-skills\u002FSKILL.md",true,[],[52,60,67,74,81,88],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":59},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":59},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":59},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":59},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":59},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":59},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]