IBM

Guidelines for using ado CLI commands and documenting them correctly. Use when writing documentation that includes ado commands, verifying CLI syntax, or explaining ado CLI usage patterns to users.

Run ado operations on remote Ray clusters using --remote execution context files. Use when the user wants to create an operation, asks about remote clusters, wants to ship local plugins or data files to a cluster, or asks about execution context YAML files. Also applies proactively when creating an operation if execution context files are present in the workspace.

End-to-end workflow to examine and summarize an ado operation — fetch operation and space YAML, summarise configuration, export entities/requests/results to CSV, perform simple analysis, and interpret failures and data quality. Use when the user asks to summarize, analyse, debug, or review an operation; wants insights from measurement data; or provides an operation ID or asks to use --use-latest for the current operation.

Builds a picture of work in an ado project: activity volume, spaces and operations created over time, experiments and operation configs used etc. Use to create a project/context overview report, summarize what the team has been doing in an ado project, report trends across spaces/operations, or to onboard onto an ado project.

End-to-end workflow to examine and summarise an ado discoveryspace — fetch space YAML, describe entity and measurement space structure, assess sampling coverage, export measurement data, and find related resources. Use when the user asks to inspect, summarise, debug, or analyse a discoveryspace; wants to understand dimensions, experiments, or sampling coverage; provides a space ID or asks to use --use-latest for the current space.

Query ado metadata and measurement data using CLI commands. Use when the user needs to find resources, filter by metadata, retrieve entities and measurements, or get resource schemas. Covers metastore queries (operations, discoveryspaces, samplestores, datacontainers, actuatorconfigurations) and samplestore queries (entities and measurements).

Formulates problems for execution with ado by creating discoveryspace and operation YAML files. Guides through experiment selection, space creation, validation, operation configuration, and parameterization. Use when the user wants to create discoveryspace or operation YAML files, configure experiments, set up entity spaces, or formulate research, benchmarking or search problems.

Guidance for creating ado resource YAML files (discoveryspace, operation, actuatorconfiguration, samplestore). Covers metadata conventions, dynamic reference resolution with --use-latest/--with/--set, space design principles, avoiding duplicate resources, and validation. Use when creating or editing any ado resource YAML file.

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.

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.

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.

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.

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.

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".

Expert guidance for creating high-level solution architecture documents from business requirements, use cases, or problem statements. Produces three focused documents - business overview, technical architecture, and implementation plan - with sufficient detail for elaboration into detailed SOPs.

Analyzes watsonx Orchestrate (wxO) projects and generates a 3-report documentation set covering the overall solution, agents, and tools/connections/other components with Mermaid diagrams.

Expert guidance for generating watsonx Orchestrate native solutions from SOPs or simple prompts. Implements agents, flows, tools, and knowledge bases based on business requirements.

Build MCP servers for customer care agents following Watson Orchestrate specifications. Guides agents through tool creation, transaction patterns, authentication, widgets, and context management with strict adherence to reference specifications. Use when creating customer care MCP servers.

Expert guidance for building a Standard Operating Procedure (SOP) from a workflow diagram, Langflow JSON, n8n JSON, BPMN model or workflow description. Focuses on business problem, data requirements, and business logic in plain language.

Convert amounts between different currencies with current exchange rates

Get personalized travel destination recommendations based on preferences

Get current weather and forecast for any location worldwide

Use this skill when working with lenses and optics in Go using the fp-go library (github.com/IBM/fp-go/v2/optics/lens). Trigger on mentions of lenses, optics, MakeLens, MakeLensRef, MakeLensStrict, lens composition, immutable updates to nested structs, accessing nested data structures, Compose, ComposeRef, ComposeOption, FromNillable, FromNillableRef, Modify, getter/setter patterns, or functional updates to Go structs. Also trigger when the user needs to update deeply nested fields immutably or work with optional fields in struct hierarchies. Also trigger for `// fp-go:Lens` annotation or go generate for lens code generation.

Use this skill when working with logging in fp-go functional pipelines (github.com/IBM/fp-go/v2/logging). Trigger on mentions of logging in monadic contexts, ChainFirstIOK, ChainFirst with logging, side-effect logging, structured logging (SLog), context-embedded loggers, LoggingCallbacks, TapSLog, LogEntryExit, Printf/Logf in IO/ReaderIO/ReaderIOResult, or when the user needs to add logging to functional pipelines without breaking the data flow.

Takes a diagnosis from log-parser and writes a Slack incident post and an action checklist. Use this skill second, after log-parser has run. Also triggers on: "write the Slack post", "I need an incident update", "write up what happened", "give me the status message". Output is copy-paste ready — the engineer should not need to edit it.

Reads raw error logs and an alert message to figure out what broke and why. Use this skill first whenever an engineer pastes logs or says "something broke", "we have an incident", "error rate spiked", or "here are the logs". Run this BEFORE incident-brief-summarizer. Outputs a short diagnosis.

Cost-optimized conversation analysis using regex pre-filtering and focused LLM analysis for problematic conversations

Step-by-step guidance for contributing a new algorithm stack python package to Algorithm Nexus. It ensures all configuration files are properly created, validates the structure of the required nexus package, and helps classify and add the algorithm stack package as a dependency. Use when users want to create a Nexus package for their python library or add their python library to algorithm nexus.