Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

$pwd:

di-agent-knowledge-engine-streamsets

Name: Di Agent Knowledge Engine Streamsets
Author: IBM

// Reference for StreamSets Data Collector engines and StreamSets environments — StreamSets environment configuration, StreamSets engine deployment (Docker/Podman), StreamSets job execution, StreamSets engine communication methods (tunneling/direct), StreamSets high availability and failover, StreamSets monitoring and resource management. Use ONLY when the user explicitly mentions StreamSets, Data Collector, or a StreamSets-specific concern.

Exécuter dans Manus

$ git log --oneline --stat

stars:0

forks:0

updated:28 mai 2026 à 19:54

Explorateur de fichiers

5 fichiers

SKILL.md

readonly

name

di-agent-knowledge-engine-streamsets

description

Reference for StreamSets Data Collector engines and StreamSets environments — StreamSets environment configuration, StreamSets engine deployment (Docker/Podman), StreamSets job execution, StreamSets engine communication methods (tunneling/direct), StreamSets high availability and failover, StreamSets monitoring and resource management. Use ONLY when the user explicitly mentions StreamSets, Data Collector, or a StreamSets-specific concern.

StreamSets Engine

Flow authoring: This skill covers engine infrastructure and operations only. For building or modifying StreamSets flows, use your path's flow authoring skill.

When to Use This Skill

Configuring or troubleshooting StreamSets environments and engines
Engine deployment (Docker/Podman), communication methods (tunneling vs. direct)
Job lifecycle: execution, monitoring, failover, offset management
High availability setup and resource management

Engine Characteristics

Container-based: Runs as Docker/Podman containers in your network
Data ownership: All processing occurs within your infrastructure
Continuous processing: Jobs run continuously, processing data as it arrives
High availability: Multiple engines support failover and load distribution
Flexible communication: Tunneling (default) or direct connection methods

Key Concepts

Environments: Configure engines and compute resources for projects
Engines: Data Collector containers that execute flows
Jobs: Flow executions that run continuously on engines
Offsets: Track processing progress for resumable execution
VPCs: Virtual CPUs allocated to engine containers

Architecture

Browser ↔ watsonx.data integration ↔ Engine (in your network)
Engines process data locally, send metrics to watsonx.data integration
Jobs fail over automatically between engines (6.4+)
Resource thresholds prevent engine overload

Quick Start

Create environment → environments.md
Run engine → engines.md
Execute job → jobs.md

References

Environments - Environment creation and configuration
Engines - Engine deployment, management, and monitoring
Jobs - Job execution and lifecycle management
Technical Reference - System requirements, commands, and troubleshooting

related-skills.json

même dépôt

di-agent-bug-report.md

from "IBM/ibm-watsonx-data-integration-skills"

Generates a Markdown bug report for an IBM watsonx.data integration session. User can invoke directly. The agent may propose it (and must wait for explicit acceptance) only after exhausting recovery options on a failure. Skip for non-watsonx.data integration sessions.

2026-05-280

di-agent-flow-datastage.md

from "IBM/ibm-watsonx-data-integration-skills"

Reference for creating DataStage (batch) flows with the watsonx.data integration SDK. The SDK is verbose and permits exhaustive stage and property access: use it to author flows pyflow's compact DSL can't express, and to edit or optimize existing DataStage flows, including ones bootstrapped with pyflow.

2026-05-280

di-agent-flow-pyflow.md

from "IBM/ibm-watsonx-data-integration-skills"

Complete API spec for pyflow, IBM's LLM-only Python DSL for authoring new batch or streaming flows on DataStage or StreamSets. The compact surface is built for high LLM authoring reliability — bootstrap here first, and fall back to the verbose engine-specific SDK only when pyflow cannot express a needed feature.

2026-05-280

di-agent-knowledge-engine-datastage.md

from "IBM/ibm-watsonx-data-integration-skills"

Q&A reference for the DataStage parallel engine — parallelism, partitioning theory, APT configuration files, concurrent job execution, restart/recovery, disk/resource tuning, dataset performance, flow optimization (partitioning/sorting/memory), and per-stage semantics. Use for conceptual engine questions and stage property lookups regardless of authoring tool.

2026-05-280

di-agent-query-substrait.md

from "IBM/ibm-watsonx-data-integration-skills"

Use when the user asks to generate a Substrait query plan, create a Substrait plan from natural language, convert a data query to Substrait JSON, write a Substrait DSL pipeline, translate a data request into a query plan, process a test entry from a JSONL dataset. Covers writing DSL code, calling MCP tools (compile_substrait_dsl, get_substrait_dsl_examples, load_test_entry), and self-correcting on compile errors. Trigger on: "generate substrait", "generate substrait dsl", "generate functional plan", "generate fp", "process entry", "run entry", "generate dsl".

2026-05-280

package.json

"author": "IBM"

"repository": "IBM/ibm-watsonx-data-integration-skills"

Ouvrir le dépôt GitHub Voir les dépôts du créateur

$ install --global

$ download --local

Exécuter dans Manus

name

di-agent-knowledge-engine-streamsets

description

StreamSets Engine

Flow authoring: This skill covers engine infrastructure and operations only. For building or modifying StreamSets flows, use your path's flow authoring skill.

When to Use This Skill

Configuring or troubleshooting StreamSets environments and engines
Engine deployment (Docker/Podman), communication methods (tunneling vs. direct)
Job lifecycle: execution, monitoring, failover, offset management
High availability setup and resource management

Engine Characteristics

Container-based: Runs as Docker/Podman containers in your network
Data ownership: All processing occurs within your infrastructure
Continuous processing: Jobs run continuously, processing data as it arrives
High availability: Multiple engines support failover and load distribution
Flexible communication: Tunneling (default) or direct connection methods

Key Concepts

Environments: Configure engines and compute resources for projects
Engines: Data Collector containers that execute flows
Jobs: Flow executions that run continuously on engines
Offsets: Track processing progress for resumable execution
VPCs: Virtual CPUs allocated to engine containers

Architecture

Browser ↔ watsonx.data integration ↔ Engine (in your network)
Engines process data locally, send metrics to watsonx.data integration
Jobs fail over automatically between engines (6.4+)
Resource thresholds prevent engine overload

Quick Start

Create environment → environments.md
Run engine → engines.md
Execute job → jobs.md

References

Environments - Environment creation and configuration
Engines - Engine deployment, management, and monitoring
Jobs - Job execution and lifecycle management
Technical Reference - System requirements, commands, and troubleshooting

di-agent-knowledge-engine-streamsets

StreamSets Engine

When to Use This Skill

Engine Characteristics

Key Concepts

Architecture

Quick Start

References

Plus depuis ce dépôt

Plus depuis ce dépôt

StreamSets Engine

When to Use This Skill

Engine Characteristics

Key Concepts

Architecture

Quick Start

References