[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DHDA2PPEXKDP6JJM4774WQ":3,"skill-same:01M7DHDA2PPEXKDP6JJM4774WQ":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":13,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7DHDA2PPEXKDP6JJM4774WQ","azure-eventhub-py",null,"Azure Event Hubs SDK for Python streaming. Use for high-throughput event ingestion, producers, consumers, and checkpointing.\nTriggers: \"event hubs\", \"EventHubProducerClient\", \"EventHubConsumerClient\", \"streaming\", \"partitions\".","ak2dev\u002Fagentguard","ak2dev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F233005497?v=4","01M7DGWK3E3XCC276C6YRFSN05","01M7DGWK4J2A9WQ44CS5CRP4R6",0,"MIT","https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Fbench\u002Fcorpus\u002Fbenign\u002Freal-ms-azure-eventhub-py\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: azure-eventhub-py\ndescription: |\n  Azure Event Hubs SDK for Python streaming. Use for high-throughput event ingestion, producers, consumers, and checkpointing.\n  Triggers: \"event hubs\", \"EventHubProducerClient\", \"EventHubConsumerClient\", \"streaming\", \"partitions\".\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: azure-eventhub\n---\n\n# Azure Event Hubs SDK for Python\n\nBig data streaming platform for high-throughput event ingestion.\n\n## Installation\n\n```bash\npip install azure-eventhub azure-identity\n# For checkpointing with blob storage\npip install azure-eventhub-checkpointstoreblob-aio\n```\n\n## Environment Variables\n\n```bash\nEVENT_HUB_FULLY_QUALIFIED_NAMESPACE=\u003Cnamespace>.servicebus.windows.net  # Required for all auth methods\nEVENT_HUB_NAME=my-eventhub  # Required for all auth methods\nSTORAGE_ACCOUNT_URL=https:\u002F\u002F\u003Caccount>.blob.core.windows.net  # Required for checkpoint storage\nCHECKPOINT_CONTAINER=checkpoints  # Required for checkpoint storage\nAZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production\n```\n\n## Authentication & Lifecycle\n\n> **🔑 Two rules apply to every code sample below:**\n>\n> 1. **Prefer `DefaultAzureCredential`.** It works locally (Azure CLI \u002F VS Code \u002F Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account\u002FAPI keys — they bypass Entra audit and rotation.\n>    - Local dev: `DefaultAzureCredential` works as-is.\n>    - Production: set `AZURE_TOKEN_CREDENTIALS=prod` (or `AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>`) to constrain the credential chain to production-safe credentials.\n> 2. **Wrap every client in a context manager** so HTTP transports, sockets, and token caches are released deterministically:\n>    - Sync: `with \u003CClient>(...) as client:`\n>    - Async: `async with \u003CClient>(...) as client:` **and** `async with DefaultAzureCredential() as credential:` (from `azure.identity.aio`)\n>\n> Snippets may abbreviate this setup, but production code should always follow both rules.\n\n```python\nfrom azure.identity import DefaultAzureCredential, ManagedIdentityCredential\nfrom azure.eventhub import EventHubProducerClient, EventHubConsumerClient\n\n# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\ncredential = DefaultAzureCredential(require_envvar=True)\n# Or use a specific credential directly in production:\n# See https:\u002F\u002Flearn.microsoft.com\u002Fpython\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-python#credential-classes\n# credential = ManagedIdentityCredential()\nnamespace = \"\u003Cnamespace>.servicebus.windows.net\"\neventhub_name = \"my-eventhub\"\n\n# Producer\nwith EventHubProducerClient(\n    fully_qualified_namespace=namespace,\n    eventhub_name=eventhub_name,\n    credential=credential\n) as producer:\n    # Use producer here (see following sections for operations)\n    ...\n\n# Consumer\nwith EventHubConsumerClient(\n    fully_qualified_namespace=namespace,\n    eventhub_name=eventhub_name,\n    consumer_group=\"$Default\",\n    credential=credential\n) as consumer:\n    # Use consumer here (see following sections for operations)\n    ...\n```\n\n## Client Types\n\n| Client | Purpose |\n|--------|---------|\n| `EventHubProducerClient` | Send events to Event Hub |\n| `EventHubConsumerClient` | Receive events from Event Hub |\n| `BlobCheckpointStore` | Track consumer progress |\n\n## Send Events\n\n```python\nfrom azure.eventhub import EventHubProducerClient, EventData\nfrom azure.identity import DefaultAzureCredential\n\nwith EventHubProducerClient(\n    fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n    eventhub_name=\"my-eventhub\",\n    credential=DefaultAzureCredential()\n) as producer:\n    # Create batch (handles size limits)\n    event_data_batch = producer.create_batch()\n    \n    for i in range(10):\n        try:\n            event_data_batch.add(EventData(f\"Event {i}\"))\n        except ValueError:\n            # Batch is full, send and create new one\n            producer.send_batch(event_data_batch)\n            event_data_batch = producer.create_batch()\n            event_data_batch.add(EventData(f\"Event {i}\"))\n    \n    # Send remaining\n    producer.send_batch(event_data_batch)\n```\n\n### Send to Specific Partition\n\n```python\n# By partition ID\nevent_data_batch = producer.create_batch(partition_id=\"0\")\n\n# By partition key (consistent hashing)\nevent_data_batch = producer.create_batch(partition_key=\"user-123\")\n```\n\n## Receive Events\n\n### Simple Receive\n\n```python\nfrom azure.eventhub import EventHubConsumerClient\n\ndef on_event(partition_context, event):\n    print(f\"Partition: {partition_context.partition_id}\")\n    print(f\"Data: {event.body_as_str()}\")\n    partition_context.update_checkpoint(event)\n\nwith EventHubConsumerClient(\n    fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n    eventhub_name=\"my-eventhub\",\n    consumer_group=\"$Default\",\n    credential=DefaultAzureCredential()\n) as consumer:\n    consumer.receive(\n        on_event=on_event,\n        starting_position=\"-1\",  # Beginning of stream\n    )\n```\n\n### With Blob Checkpoint Store (Production)\n\n```python\nfrom azure.eventhub import EventHubConsumerClient\nfrom azure.eventhub.extensions.checkpointstoreblob import BlobCheckpointStore\nfrom azure.identity import DefaultAzureCredential\n\ncheckpoint_store = BlobCheckpointStore(\n    blob_account_url=\"https:\u002F\u002F\u003Caccount>.blob.core.windows.net\",\n    container_name=\"checkpoints\",\n    credential=DefaultAzureCredential()\n)\n\nwith EventHubConsumerClient(\n    fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n    eventhub_name=\"my-eventhub\",\n    consumer_group=\"$Default\",\n    credential=DefaultAzureCredential(),\n    checkpoint_store=checkpoint_store\n) as consumer:\n    def on_event(partition_context, event):\n        print(f\"Received: {event.body_as_str()}\")\n        # Checkpoint after processing\n        partition_context.update_checkpoint(event)\n\n    consumer.receive(on_event=on_event)\n```\n\n## Async Client\n\n```python\nfrom azure.eventhub.aio import EventHubProducerClient, EventHubConsumerClient\nfrom azure.identity.aio import DefaultAzureCredential\nimport asyncio\n\nasync def send_events():\n    credential = DefaultAzureCredential()\n    \n    async with EventHubProducerClient(\n        fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n        eventhub_name=\"my-eventhub\",\n        credential=credential\n    ) as producer:\n        batch = await producer.create_batch()\n        batch.add(EventData(\"Async event\"))\n        await producer.send_batch(batch)\n\nasync def receive_events():\n    async def on_event(partition_context, event):\n        print(event.body_as_str())\n        await partition_context.update_checkpoint(event)\n    \n    async with EventHubConsumerClient(\n        fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n        eventhub_name=\"my-eventhub\",\n        consumer_group=\"$Default\",\n        credential=DefaultAzureCredential()\n    ) as consumer:\n        await consumer.receive(on_event=on_event)\n\nasyncio.run(send_events())\n```\n\n## Event Properties\n\n```python\nevent = EventData(\"My event body\")\n\n# Set properties\nevent.properties = {\"custom_property\": \"value\"}\nevent.content_type = \"application\u002Fjson\"\n\n# Read properties (on receive)\nprint(event.body_as_str())\nprint(event.sequence_number)\nprint(event.offset)\nprint(event.enqueued_time)\nprint(event.partition_key)\n```\n\n## Get Event Hub Info\n\n```python\nwith producer:\n    info = producer.get_eventhub_properties()\n    print(f\"Name: {info['name']}\")\n    print(f\"Partitions: {info['partition_ids']}\")\n    \n    for partition_id in info['partition_ids']:\n        partition_info = producer.get_partition_properties(partition_id)\n        print(f\"Partition {partition_id}: {partition_info['last_enqueued_sequence_number']}\")\n```\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.xxx` sync clients with `azure.xxx.aio` async clients in the same call path. Choose one mode per module.\n2. **Always use context managers for clients and async credentials.** Wrap every client in `with Client(...) as client:` (sync) or `async with Client(...) as client:` (async) for proper cleanup. For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use `DefaultAzureCredential`** for portable auth across local dev and Azure (avoid connection strings \u002F API keys when possible).\n4. **Use batches** for sending multiple events\n5. **Use checkpoint store** in production for reliable processing\n6. **Use async client** for high-throughput scenarios\n7. **Use partition keys** for ordered delivery within a partition\n8. **Handle batch size limits** — catch ValueError when batch is full\n9. **Set appropriate consumer groups** for different applications\n\n## Reference Files\n\n| File | Contents |\n|------|----------|\n| [references\u002Fcheckpointing.md](references\u002Fcheckpointing.md) | Checkpoint store patterns, blob checkpointing, checkpoint strategies |\n| [references\u002Fpartitions.md](references\u002Fpartitions.md) | Partition management, load balancing, starting positions |\n| [scripts\u002Fsetup_consumer.py](scripts\u002Fsetup_consumer.py) | CLI for Event Hub info, consumer setup, and event sending\u002Freceiving |\n","# Azure Event Hubs SDK for Python\n\nBig data streaming platform for high-throughput event ingestion.\n\n## Installation\n\n```bash\npip install azure-eventhub azure-identity\n# For checkpointing with blob storage\npip install azure-eventhub-checkpointstoreblob-aio\n```\n\n## Environment Variables\n\n```bash\nEVENT_HUB_FULLY_QUALIFIED_NAMESPACE=\u003Cnamespace>.servicebus.windows.net  # Required for all auth methods\nEVENT_HUB_NAME=my-eventhub  # Required for all auth methods\nSTORAGE_ACCOUNT_URL=https:\u002F\u002F\u003Caccount>.blob.core.windows.net  # Required for checkpoint storage\nCHECKPOINT_CONTAINER=checkpoints  # Required for checkpoint storage\nAZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production\n```\n\n## Authentication & Lifecycle\n\n> **🔑 Two rules apply to every code sample below:**\n>\n> 1. **Prefer `DefaultAzureCredential`.** It works locally (Azure CLI \u002F VS Code \u002F Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account\u002FAPI keys — they bypass Entra audit and rotation.\n>    - Local dev: `DefaultAzureCredential` works as-is.\n>    - Production: set `AZURE_TOKEN_CREDENTIALS=prod` (or `AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>`) to constrain the credential chain to production-safe credentials.\n> 2. **Wrap every client in a context manager** so HTTP transports, sockets, and token caches are released deterministically:\n>    - Sync: `with \u003CClient>(...) as client:`\n>    - Async: `async with \u003CClient>(...) as client:` **and** `async with DefaultAzureCredential() as credential:` (from `azure.identity.aio`)\n>\n> Snippets may abbreviate this setup, but production code should always follow both rules.\n\n```python\nfrom azure.identity import DefaultAzureCredential, ManagedIdentityCredential\nfrom azure.eventhub import EventHubProducerClient, EventHubConsumerClient\n\n# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\ncredential = DefaultAzureCredential(require_envvar=True)\n# Or use a specific credential directly in production:\n# See https:\u002F\u002Flearn.microsoft.com\u002Fpython\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-python#credential-classes\n# credential = ManagedIdentityCredential()\nnamespace = \"\u003Cnamespace>.servicebus.windows.net\"\neventhub_name = \"my-eventhub\"\n\n# Producer\nwith EventHubProducerClient(\n    fully_qualified_namespace=namespace,\n    eventhub_name=eventhub_name,\n    credential=credential\n) as producer:\n    # Use producer here (see following sections for operations)\n    ...\n\n# Consumer\nwith EventHubConsumerClient(\n    fully_qualified_namespace=namespace,\n    eventhub_name=eventhub_name,\n    consumer_group=\"$Default\",\n    credential=credential\n) as consumer:\n    # Use consumer here (see following sections for operations)\n    ...\n```\n\n## Client Types\n\n| Client | Purpose |\n|--------|---------|\n| `EventHubProducerClient` | Send events to Event Hub |\n| `EventHubConsumerClient` | Receive events from Event Hub |\n| `BlobCheckpointStore` | Track consumer progress |\n\n## Send Events\n\n```python\nfrom azure.eventhub import EventHubProducerClient, EventData\nfrom azure.identity import DefaultAzureCredential\n\nwith EventHubProducerClient(\n    fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n    eventhub_name=\"my-eventhub\",\n    credential=DefaultAzureCredential()\n) as producer:\n    # Create batch (handles size limits)\n    event_data_batch = producer.create_batch()\n    \n    for i in range(10):\n        try:\n            event_data_batch.add(EventData(f\"Event {i}\"))\n        except ValueError:\n            # Batch is full, send and create new one\n            producer.send_batch(event_data_batch)\n            event_data_batch = producer.create_batch()\n            event_data_batch.add(EventData(f\"Event {i}\"))\n    \n    # Send remaining\n    producer.send_batch(event_data_batch)\n```\n\n### Send to Specific Partition\n\n```python\n# By partition ID\nevent_data_batch = producer.create_batch(partition_id=\"0\")\n\n# By partition key (consistent hashing)\nevent_data_batch = producer.create_batch(partition_key=\"user-123\")\n```\n\n## Receive Events\n\n### Simple Receive\n\n```python\nfrom azure.eventhub import EventHubConsumerClient\n\ndef on_event(partition_context, event):\n    print(f\"Partition: {partition_context.partition_id}\")\n    print(f\"Data: {event.body_as_str()}\")\n    partition_context.update_checkpoint(event)\n\nwith EventHubConsumerClient(\n    fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n    eventhub_name=\"my-eventhub\",\n    consumer_group=\"$Default\",\n    credential=DefaultAzureCredential()\n) as consumer:\n    consumer.receive(\n        on_event=on_event,\n        starting_position=\"-1\",  # Beginning of stream\n    )\n```\n\n### With Blob Checkpoint Store (Production)\n\n```python\nfrom azure.eventhub import EventHubConsumerClient\nfrom azure.eventhub.extensions.checkpointstoreblob import BlobCheckpointStore\nfrom azure.identity import DefaultAzureCredential\n\ncheckpoint_store = BlobCheckpointStore(\n    blob_account_url=\"https:\u002F\u002F\u003Caccount>.blob.core.windows.net\",\n    container_name=\"checkpoints\",\n    credential=DefaultAzureCredential()\n)\n\nwith EventHubConsumerClient(\n    fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n    eventhub_name=\"my-eventhub\",\n    consumer_group=\"$Default\",\n    credential=DefaultAzureCredential(),\n    checkpoint_store=checkpoint_store\n) as consumer:\n    def on_event(partition_context, event):\n        print(f\"Received: {event.body_as_str()}\")\n        # Checkpoint after processing\n        partition_context.update_checkpoint(event)\n\n    consumer.receive(on_event=on_event)\n```\n\n## Async Client\n\n```python\nfrom azure.eventhub.aio import EventHubProducerClient, EventHubConsumerClient\nfrom azure.identity.aio import DefaultAzureCredential\nimport asyncio\n\nasync def send_events():\n    credential = DefaultAzureCredential()\n    \n    async with EventHubProducerClient(\n        fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n        eventhub_name=\"my-eventhub\",\n        credential=credential\n    ) as producer:\n        batch = await producer.create_batch()\n        batch.add(EventData(\"Async event\"))\n        await producer.send_batch(batch)\n\nasync def receive_events():\n    async def on_event(partition_context, event):\n        print(event.body_as_str())\n        await partition_context.update_checkpoint(event)\n    \n    async with EventHubConsumerClient(\n        fully_qualified_namespace=\"\u003Cnamespace>.servicebus.windows.net\",\n        eventhub_name=\"my-eventhub\",\n        consumer_group=\"$Default\",\n        credential=DefaultAzureCredential()\n    ) as consumer:\n        await consumer.receive(on_event=on_event)\n\nasyncio.run(send_events())\n```\n\n## Event Properties\n\n```python\nevent = EventData(\"My event body\")\n\n# Set properties\nevent.properties = {\"custom_property\": \"value\"}\nevent.content_type = \"application\u002Fjson\"\n\n# Read properties (on receive)\nprint(event.body_as_str())\nprint(event.sequence_number)\nprint(event.offset)\nprint(event.enqueued_time)\nprint(event.partition_key)\n```\n\n## Get Event Hub Info\n\n```python\nwith producer:\n    info = producer.get_eventhub_properties()\n    print(f\"Name: {info['name']}\")\n    print(f\"Partitions: {info['partition_ids']}\")\n    \n    for partition_id in info['partition_ids']:\n        partition_info = producer.get_partition_properties(partition_id)\n        print(f\"Partition {partition_id}: {partition_info['last_enqueued_sequence_number']}\")\n```\n\n## Best Practices\n\n1. **Pick sync OR async and stay consistent.** Do not mix `azure.xxx` sync clients with `azure.xxx.aio` async clients in the same call path. Choose one mode per module.\n2. **Always use context managers for clients and async credentials.** Wrap every client in `with Client(...) as client:` (sync) or `async with Client(...) as client:` (async) for proper cleanup. For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n3. **Use `DefaultAzureCredential`** for portable auth across local dev and Azure (avoid connection strings \u002F API keys when possible).\n4. **Use batches** for sending multiple events\n5. **Use checkpoint store** in production for reliable processing\n6. **Use async client** for high-throughput scenarios\n7. **Use partition keys** for ordered delivery within a partition\n8. **Handle batch size limits** — catch ValueError when batch is full\n9. **Set appropriate consumer groups** for different applications\n\n## Reference Files\n\n| File | Contents |\n|------|----------|\n| [references\u002Fcheckpointing.md](references\u002Fcheckpointing.md) | Checkpoint store patterns, blob checkpointing, checkpoint strategies |\n| [references\u002Fpartitions.md](references\u002Fpartitions.md) | Partition management, load balancing, starting positions |\n| [scripts\u002Fsetup_consumer.py](scripts\u002Fsetup_consumer.py) | CLI for Event Hub info, consumer setup, and event sending\u002Freceiving |\n",{"name":5,"license":14,"metadata":23,"description":27},{"author":24,"package":25,"version":26},"Microsoft","azure-eventhub","1.0.0","Azure Event Hubs SDK for Python streaming. Use for high-throughput event ingestion, producers, consumers, and checkpointing.\nTriggers: \"event hubs\", \"EventHubProducerClient\", \"EventHubConsumerClient\", \"streaming\", \"partitions\".\n","main","634c25395a24b98cd6125453ad4abb65517bcabb","bench\u002Fcorpus\u002Fbenign\u002Freal-ms-azure-eventhub-py","https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard","https:\u002F\u002Fsite-bionic8.vercel.app","https:\u002F\u002Fgithub.com\u002Fak2dev","2026-11-11 02:37:06",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add ak2dev\u002Fagentguard --skill azure-eventhub-py",{"tool":41,"command":42},"bunx","bunx skills add ak2dev\u002Fagentguard --skill azure-eventhub-py",{"tool":44,"command":45},"pnpm","pnpm dlx skills add ak2dev\u002Fagentguard --skill azure-eventhub-py","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Fbench\u002Fcorpus\u002Fbenign\u002Freal-ms-azure-eventhub-py\u002FSKILL.md",true,[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fcheckpointing.md","REFERENCE","参考文档",10018,"https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Fbench\u002Fcorpus\u002Fbenign\u002Freal-ms-azure-eventhub-py\u002Freferences\u002Fcheckpointing.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fpartitions.md",10630,"https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Fbench\u002Fcorpus\u002Fbenign\u002Freal-ms-azure-eventhub-py\u002Freferences\u002Fpartitions.md",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Fsetup_consumer.py","SCRIPT","脚本",13609,"https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Fbench\u002Fcorpus\u002Fbenign\u002Freal-ms-azure-eventhub-py\u002Fscripts\u002Fsetup_consumer.py",[66,74,79,84,89,95],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7DJ7GBSJBJ32GXNQXVAMNYK","csv-tool","Summarize CSV files and report column statistics.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Ffixtures\u002Frules\u002FAG-SYS-002\u002Fpositive\u002Ffault\u002Fcsv-tool\u002FSKILL.md",[],[],{"skillNo":75,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7DJ7F00PA7EHFM39RVCC8R5","https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Ffixtures\u002Frules\u002FAG-SYS-002\u002Fnegative\u002Fnormal\u002Fcsv-tool\u002FSKILL.md",[],[],{"skillNo":80,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M7DJ7DP7KDW7MYY5Q0R0JFEN","https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Ffixtures\u002Frules\u002FAG-SYS-001\u002Fpositive\u002Ftoo-large\u002Fcsv-tool\u002FSKILL.md",[],[],{"skillNo":85,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M7DJ7C3VA0KQ8Q9ESNX6AJHE","https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Ffixtures\u002Frules\u002FAG-SYS-001\u002Fnegative\u002Fsmall\u002Fcsv-tool\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M7DJ7AQZTGY5YADQX73TRB7K","pdf","https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Ffixtures\u002Frules\u002FAG-SKL-TYP-002\u002Fpositive\u002Fother-publisher\u002Fpdf\u002FSKILL.md",[],[],{"skillNo":96,"name":91,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M7DJ7831XDVWS4W9SAAKBJHX","https:\u002F\u002Fgithub.com\u002Fak2dev\u002Fagentguard\u002Fblob\u002Fmain\u002Ffixtures\u002Frules\u002FAG-SKL-TYP-002\u002Fnegative\u002Fsame-publisher\u002Fpdf\u002FSKILL.md",[],[]]