IBM

@ibm source repo

84 skills
0 followers
9 hours ago last updated

▌
Grill Me · ibm
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.

0
installs
▌
Verify · ibm
Run verification checks for the galaxium-travels repo. Use after every implementation. Use when the user asks to verify, validate, run tests, check lint, or confirm that changes are correct. Knows which checks are cheap (ruff, pytest, frontend lint) vs expensive (e2e). Runs cheap checks by default; only runs e2e when explicitly asked or when changes touch cross-service boundaries.

0
installs
▌
Grill And Share · ibm
Use when the user wants to stress-test and document a plan for demo purposes - asks up to 3 focused questions, then produces a Markdown summary, optionally posts it to the originating GitHub issue as a comment, and finally generates the HTML planning document. Trigger phrases: grill and share, stress-test this plan, review and publish plan, grill my plan.

0
installs
▌
Setup · ibm bundle
Mandatory first workflow for ANY task in an unfinalized CEN Starter checkout (.template/ exists; cen.finalized is false in package.json) — including direct feature requests such as "build a todo app" or "add a page". Pause feature work, guide the user through outcome-focused configuration choices, apply the matching flavors, bootstrap, verify the running app, and finalize with explicit approval before building anything.

0
installs
▌
Add Wxo Chat · ibm bundle
Add a watsonx Orchestrate embedded web chat to this app — asks which layout flavour the user wants (float, custom, fullscreen, or docview), then scaffolds the components, env vars, and route. Use when the user asks to embed watsonx Orchestrate, add a WXO chat interface, or integrate a watsonx Orchestrate agent into the frontend.

0
installs
▌
Prepare Workstation · ibm bundle
Prepare a computer for CEN Starter development by diagnosing and installing the standard workstation baseline: Git, GitHub CLI, Node.js, pnpm, Rancher Desktop, OpenShift and IBM Cloud CLIs, IBM Bob, and supporting editor extensions. Use when prerequisites are missing, containers are unavailable, setup fails before the app starts, or a user needs beginner-friendly workstation help on macOS, Windows, WSL, Linux, or a managed company device.

0
installs
▌
Template Maintenance · ibm
Maintain the CEN Starter template repository itself — keep flavors applying, add flavors, release versions. Template repo only; not for projects created from it (deleted at finalize).

0
installs
▌
Skills App Discovery Enhanced · ibm bundle
Use when the user wants to analyse a legacy monolithic application (Java/.NET) and generate discovery artifacts — such as tech stack summaries, architecture overviews, API inventories, data models, dependency maps, and migration readiness reports. Optionally loads the discovery graph into Neo4j for querying by the skills-microservices-architect skill.

0
installs
▌
Skills Microservices Designer · ibm bundle
Use when the user wants to generate detailed microservice design artifacts — OpenAPI specifications, SQL ownership schemas, design documents, and design review guidelines — from architectural artifacts (architecture specifications, microservices catalog, bounded context map, data ownership matrix) produced by the Microservices Architect. Requires a microservices catalog CSV and optionally Neo4j graph evidence and MinIO discovery documents.

0
installs
▌
Skills Microservices Architect · ibm
Use when the user wants to decompose a monolithic application into microservices — walks through graph-first evidence retrieval from Neo4j, bounded context identification, service design, data ownership, and generation of a full microservices portfolio (catalog CSV, bounded context map, service architecture specifications, spec review guidelines, data ownership matrix, migration roadmap). Requires a completed app discovery graph in Neo4j and discovery documents in MinIO.

0
installs
▌
Skills Microservices Developer · ibm bundle
Use when the user wants to generate production-ready microservice implementation code from approved architecture and design artifacts — retrieves architecture specifications, OpenAPI, SQL schemas, and design documents from MinIO, generates and validates GitHub Spec Kit artifacts (spec.md, plan.md, tasks.md), invokes GitHub Spec Kit implementation, and enforces enterprise coding standards and governance throughout. Retrieves enterprise coding standards from MinIO and enforces them throughout code generation.

2
installs
▌
Code Engine Specialist · ibm bundle
Deploys, configures, and troubleshoots IBM Cloud Code Engine workloads using the ibmcloud ce CLI. Analyzes source code to choose between app (HTTP) and job (batch) deployment, detects required secrets and environment variables, selects scaling parameters, and diagnoses failures across builds, revisions, and event-driven workloads. Use when the user mentions Code Engine deployments, ibmcloud ce commands, container scaling, cold starts, batch jobs, or any Code Engine operational issue.

0
installs
▌
Weather Forecast · ibm bundle
Get current weather and forecast for any location worldwide

0
installs
▌
Currency Converter · ibm bundle
Convert amounts between different currencies with current exchange rates

0
installs
▌
Travel Recommendations · ibm bundle
Get personalized travel destination recommendations based on preferences

0
installs
▌
Docpipe Custom Operator · ibm bundle
Create, load, package, or modify an external custom operator for docpipe. Use when a consumer needs an AbstractOperator supplied through DOCPIPE_CUSTOM_OPERATORS, DocpipeFlowManager, package entry points, S3, or register_operator_provider without modifying the built-in DOCPIPE_OPERATORS registry. Do not use for built-in operators or ingest source connectors.

0
installs
▌
Feature Testing Workflow · ibm bundle
Exercise observable docpipe feature behavior without depending on pytest or existing test cases. Use for operator, pipeline, ingest-provider, orchestration, REST API, or Python API validation by building a small runnable scenario, executing a public entrypoint, checking runtime artifacts or service state, and reporting reproducible evidence. Do not use when the user specifically asks to write automated tests.

0
installs
▌
Docpipe Operator Development · ibm bundle
Create or modify built-in docpipe operators that ship from src/docpipe. Use when implementing transform behavior, metadata and validation, DOCPIPE_OPERATORS registration, tests, a runnable flow, documentation, and changelog updates. Do not use for externally loaded custom operators or ingest source connectors.

0
installs
▌
Docpipe Ingest Source Adapter · ibm bundle
Add or modify an ingest document source provider for IngestSourceOperator. Use when creating its Pydantic configuration, DocumentSourcePort adapter, factory registration, lazy binary retrieval, provider tests, runnable flow, dependency and documentation updates. Do not use for ordinary transform operators or storage destination adapters.

0
installs
▌
Text2sparql · ibm
End-to-end Text-to-SPARQL skill that orchestrates wikidata-search, graph-exploration, sparql-generation, and sparql-execution to convert a natural-language question into a validated, executable SPARQL query over Wikidata. Use when the user asks a natural-language question and expects a working SPARQL query as output.

0
installs
▌
Wikidata Search · ibm bundle
Wikidata search skill that resolves entity names and relation phrases to Wikidata item IDs (QIDs) and property IDs (PIDs) using the Wikidata API. Use when you need to find Wikidata identifiers for entities or properties mentioned in a natural-language question.

0
installs
▌
Sparql Execution · ibm bundle
SPARQL execution skill that sends queries to the Wikidata Query Service, captures results, validates them against the user's intent, and performs iterative repair when queries fail or return implausible results. Use when you have a candidate SPARQL query ready to execute.

0
installs
▌
Few Shot Examples · ibm bundle
Few-shot examples skill that provides reusable examples of common Wikidata SPARQL patterns. Use before generating SPARQL to find relevant examples that demonstrate how similar questions have been answered, covering patterns like direct lookups, reverse relations, subclass traversal, qualifiers, and aggregations.

0
installs
▌
Graph Exploration · ibm bundle
Graph exploration skill that inspects the Wikidata knowledge graph around seed entities using small diagnostic SPARQL queries. Use to verify property directions, discover graph paths, inspect qualifiers, and build evidence for the final query structure.

0
installs
▌
Sparql Generation · ibm bundle
SPARQL generation skill that constructs a SPARQL query from resolved Wikidata entities, properties, and graph paths. Use when you have verified Wikidata IDs and need to assemble them into a syntactically correct SPARQL query with proper triple patterns, filters, and aggregations.

0
installs
▌
Fp Go · ibm
Use this skill whenever writing, reviewing, or refactoring Go code that uses the fp-go library (github.com/IBM/fp-go/v2). Trigger on any mention of fp-go, functional programming in Go, monads in Go, Option/Either/Result types in Go, IOResult, ReaderIOResult, data-last composition, Pipe/Flow, or do-notation with Bind/ApS in Go. Also trigger when the user wants to convert idiomatic Go error handling into functional pipelines, or asks about optics (lens, prism, traversal) in Go.

0
installs
▌
Fp Go MCP · ibm
Use this skill when working with the fp-go MCP (Model Context Protocol) server located in github.com/IBM/fp-go/gen/v2. Trigger on mentions of MCP server, fp-go MCP tools, list_skills, use_skill, search_examples, get_example, configuring fp-go for Claude Desktop, or when the user needs to access fp-go examples and skills programmatically. This skill explains how to configure and use the MCP server to access fp-go documentation, examples, and skills.

0
installs
▌
Fp Go HTTP · ibm
Use this skill when making HTTP requests in fp-go using the ReaderIOResult-based HTTP client (github.com/IBM/fp-go/v2/context/readerioresult/http). Trigger on mentions of fp-go HTTP, MakeClient, MakeGetRequest, MakeRequest, ReadJSON, ReadText, ReadAll, ReadFullResponse, the HTTP request builder (WithURL, WithJSON, WithBearer, WithHeader, WithQueryArg), parallel requests with TraverseArray or TraverseTuple2, or building context-aware, composable HTTP pipelines that propagate errors through the Result monad.

0
installs
▌
Fp Go Lens · ibm
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.

0
installs
▌
Fp Go Logging · ibm
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.

0
installs
▌
Fp Go Pipe Flow · ibm bundle
Guides writing, refactoring, and reviewing fp-go v2 code that uses functional composition via Pipe and Flow. Apply this skill whenever the user asks to write new fp-go code, refactor imperative Go into functional style, explain a Pipe/Flow pipeline, add do-notation (Do/Bind/ApS), use the reader monad, create lenses for struct fields, or generate unit tests for functional pipelines. Trigger on any mention of: Pipe, Flow, reader monad, kleisli, do-notation, Bind, ApS, fp-go pipeline, point-free style, lens composition in Go.

0
installs
▌
Fp Go Pr Review · ibm
Use this skill when reviewing pull requests for fp-go code (github.com/IBM/fp-go/v2). Trigger on mentions of PR review, code review, pull request validation, fp-go best practices validation, functional programming review, or when the user asks to review changes on a PR branch. This skill validates that changes follow fp-go conventions including data-last composition, point-free style, proper monad usage, lens patterns, and idiomatic functional patterns.

0
installs
▌
Di Agent Bug Report · ibm
Generates a Markdown bug report for an IBM watsonx.data integration session. User can invoke directly. The agent MUST propose it (and must wait for explicit acceptance) after 3 or more consecutive calls to the same tool or the same sequence of tools result in a failure or the same error. Skip for non-watsonx.data integration sessions.

0
installs
▌
Di Agent Flow Pyflow · ibm
API spec for pyflow, IBM's LLM-optimized Python DSL for authoring DataStage and StreamSets flows. Its compact surface and compile-time validation offer context efficiency, fast feedback, and correctness guarantees. Load this only after the di-agent-flow-lifecycle router has selected the pyflow authoring backend — this is a language reference, not a decision about whether to use it. If you have not routed yet, load di-agent-flow-lifecycle instead.

0
installs
▌
Di Agent Flow Datastage · ibm bundle
Reference for the verbose watsonx.data integration SDK for DataStage (batch) flows, with exhaustive stage and property access — the full engine stage catalog. Load this only after the di-agent-flow-lifecycle router has selected the datastage-sdk authoring backend — this is a syntax and stage reference, not a decision about whether to use it. If you have not routed yet, load di-agent-flow-lifecycle instead.

0
installs
▌
Di Agent Flow Lifecycle · ibm bundle
Entry point for ALL flow work in watsonx.data integration — creating, editing, running, diagnosing a failed run, or backing up/restoring a flow. Load this FIRST whenever a request touches a data flow. It gathers intent — including which engine the flow runs on — routes to exactly one lifecycle state, and applies a fixed precedence order so routing is consistent run to run.

0
installs
▌
Di Agent Parameter Sets · ibm bundle
Guide for creating, editing, and using parameter sets (paramsets) in IBM watsonx.data integration. Covers parameter types, value sets, PROJDEF, local parameters, runtime parameters, flow parameters, #param# and ${param} reference syntax for both DataStage (batch) and StreamSets (streaming) flows, and parameterizing connection properties with external parameter sets. Use when the user wants to create, list, update, or delete parameter sets; manage value sets; attach parameter sets to flows or connections; parameterize connection properties; or reference parameters inside a flow or connection.

0
installs
▌
Di Agent Datastage Investigation · ibm
Deep investigation of a failed run of a DataStage job already in operation — a scheduled or production job, or any job whose failure the user asks you to investigate. Works end-to-end from MCP tools: logs, job config, flow structure, connection health. Produces a root-cause diagnosis, not a fix. NOT for a run that failed while a flow was being built or edited — those are handled by the di-agent-flow-lifecycle skill, which runs its own investigation and loads this one only when a production-depth analysis is needed.

0
installs
▌
Di Agent Knowledge Engine Datastage · ibm bundle
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.

0
installs
▌
Sop Builder · ibm
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.

0
installs
▌
Wxo Builder · ibm
Expert guidance for generating watsonx Orchestrate native solutions from SOPs or simple prompts. Implements agents, flows, tools, and knowledge bases based on business requirements.

0
installs
▌
Wxo Analyzer · ibm
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.

0
installs
▌
Solution Architect · ibm
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.

0
installs
▌
Telemetry Analyzer · ibm bundle
Use when the user wants to analyze agent telemetry traces to find bugs and get fix recommendations — walks through exporting traces from a local or remote watsonx Orchestrate server, parsing raw OTel JSON or Langfuse-format trace JSON directly, and reasoning over them to identify failures and suggest fixes.

0
installs
▌
Customercare MCP Builder · ibm bundle
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.

0
installs
▌
Agent Instructions Evaluator · ibm bundle
Evaluate an agent instructions or agent definition for achievability and produce a structured, evidence-backed report artifact with per-dimension scores, findings, deterministic signals, and high-impact recommendations.

0
installs
▌
Code Completion · ibm bundle
Use this skill whenever you are given a Python code file with missing code and asked to complete it — whether that is a single incomplete line, an API invocation, or an entire function body. This skill completes the missing code by first generating doctests as a validation oracle, then generating the code, then iteratively fixing the code until it passes its own doctests before delivering the result. Trigger for: - Any prompt containing a Python code file where code is missing or truncated - Requests like "complete this function", "fill in the missing code", "implement this" - JSON records with a "prompt" field containing Python code and a "metadata" field with either "function_name" (function body task) or "line_no" (line completion task) - Any RepoEval-style code completion benchmark instance - Situations where generated code must be validated before delivery Do not trigger for: - General code questions or explanations with no missing code to fill in - Requests to write entirely new files from scratch with

0
installs
▌
Code Completion Role Reinforced Engineer · ibm bundle
Use this skill whenever you are given a Python code file with missing code and asked to complete it — whether that is a single incomplete line, an API invocation, or an entire function body. This skill completes the missing code by first generating doctests as a validation oracle, then generating the code, then iteratively fixing the code until it passes its own doctests before delivering the result. Trigger for: - Any prompt containing a Python code file where code is missing or truncated - Requests like "complete this function", "fill in the missing code", "implement this" - JSON records with a "prompt" field containing Python code and a "metadata" field with either "function_name" (function body task) or "line_no" (line completion task) - Any RepoEval-style code completion benchmark instance - Situations where generated code must be validated before delivery Do not trigger for: - General code questions or explanations with no missing code to fill in - Requests to write entirely new files from scratch with

0
installs
▌
Code Completion No Orchestration · ibm bundle
ABLATION VARIANT — ORCHESTRATION REMOVED. This is the doctest-driven code-completion skill with the Orchestration pattern ablated out. The iterative Recovery Loop is preserved (write code, run doctests, fix on failure, repeat until they pass or the budget is spent). What is removed is all of the orchestration scaffolding: the staged 11-step recipe, the explicit task-routing step, the 5-tier classification taxonomy, the staged quality gates, and the multi-file progressive-disclosure structure (doctest_generator.md, recovery_loop.md, injection.md). Everything now lives in this one flat file with no predefined step sequence. Use this skill whenever you are given a Python code file with missing code and asked to complete it.

0
installs
▌
Code Completion No Recovery Loop · ibm bundle
ABLATION VARIANT — RECOVERY LOOP REMOVED. This is the doctest-driven code-completion skill with the iterative Recovery Loop pattern ablated out. Everything else (Orchestration: the staged pipeline, task routing, 5-tier classification, multi-file progressive disclosure; and the Quality Gates) is preserved exactly as in the full skill. Use this skill whenever you are given a Python code file with missing code and asked to complete it. It generates doctests as a validation oracle, generates the code, runs the doctests ONCE to record a pass/fail signal, and then delivers the first candidate. It does NOT diagnose failures and it does NOT iterate or repair. Trigger for: - Any prompt containing a Python code file where code is missing or truncated - Requests like "complete this function", "fill in the missing code", "implement this" - JSON records with a "prompt" field and a "metadata" field with either "function_name" (function body task) or "line_no" (line completion task) - Any RepoEval-style code completion benc

0
installs
▌
Code Completion Role Reinforced Codegolf · ibm bundle
Use this skill whenever you are given a Python code file with missing code and asked to complete it — whether that is a single incomplete line, an API invocation, or an entire function body. This skill completes the missing code by first generating doctests as a validation oracle, then generating the code, then iteratively fixing the code until it passes its own doctests before delivering the result. Trigger for: - Any prompt containing a Python code file where code is missing or truncated - Requests like "complete this function", "fill in the missing code", "implement this" - JSON records with a "prompt" field containing Python code and a "metadata" field with either "function_name" (function body task) or "line_no" (line completion task) - Any RepoEval-style code completion benchmark instance - Situations where generated code must be validated before delivery Do not trigger for: - General code questions or explanations with no missing code to fill in - Requests to write entirely new files from scratch with

0
installs
▌
Lcb Doctest Driven Development · ibm bundle
Doctest-driven code generation for competitive-programming problems. The orchestrator first designs a quality gate of doctests (happy-path AND self-devised edge cases), verifies their expected values with a reference solution, injects them into the code generation prompt, then runs a reflection recovery loop until the code passes the gate. Use for any single-function / single-program coding task where correctness on unseen edge cases matters. The code-generating model never sees the hidden grading tests.

0
installs
▌
Lcb Doctest · ibm
LCB Doctest-Driven Skill

0
installs
▌
Code Completion No Progressive Disclosure · ibm bundle
Use this skill whenever you are given a Python code file with missing code and asked to complete it — whether that is a single incomplete line, an API invocation, or an entire function body. This skill completes the missing code by first generating doctests as a validation oracle, then generating the code, then iteratively fixing the code until it passes its own doctests before delivering the result. Trigger for: - Any prompt containing a Python code file where code is missing or truncated - Requests like "complete this function", "fill in the missing code", "implement this" - JSON records with a "prompt" field containing Python code and a "metadata" field with either "function_name" (function body task) or "line_no" (line completion task) - Any RepoEval-style code completion benchmark instance - Situations where generated code must be validated before delivery Do not trigger for: - General code questions or explanations with no missing code to fill in - Requests to write entirely new files from scratch with

0
installs
▌
Unit Test · ibm
Run the ibm-licensing-operator controller unit/integration tests (Ginkgo suites in ./controllers) against a live Kubernetes cluster via envtest with USE_EXISTING_CLUSTER=true. Use to validate controller or API changes before committing or opening a PR.

0
installs
▌
Code Review · ibm
Perform a thorough, precise code review of a GitHub pull request, in the agent thread, using the `gh` CLI. Give it a PR number (preferred) or a branch name - it fetches the PR and diff with `gh`, runs an explicit review loop, decides PASS or CHANGES REQUESTED, and returns a prioritized list of required fixes. Optionally takes a short description of the change to focus the review. Use when asked to review a PR, a branch's PR, or "the diff" before merging. Repo-agnostic.

0
installs
▌
Setup Tools · ibm
Install, verify, and clean the local development toolchain (operator-sdk, opm, controller-gen, kustomize, yq, linters, detect-secrets) for the ibm-licensing-operator repo. Use for first-time setup, onboarding, when a build fails because a tool is missing or the wrong version, or to reset a broken toolchain.

0
installs
▌
Code Quality · ibm
Format, tidy, vet, lint, and secret-scan the ibm-licensing-operator codebase before committing or opening a PR. Runs the same checks the pre-commit git hook and CI enforce (golangci-lint, shellcheck, yamllint, mdl, go vet, detect-secrets). Use before every commit, when preparing a PR, or after any code/YAML/script/markdown change.

0
installs
▌
Contributing · ibm
How to contribute high-quality changes to the ibm-licensing-operator repo - the end-to-end workflow, DCO sign-off, the pre-PR quality checklist, when generated files must be committed, copyright headers, branching, and version bumps. Use when preparing a change, a commit, or a pull request, or when unsure what the repo expects before pushing.

0
installs
▌
Build And Deploy · ibm
Build the ibm-licensing-operator binary/image and run or deploy it against a Kubernetes cluster for local development and testing. Use to compile the operator, run the controller locally against a cluster, build and push a dev image to the scratch registry, or install CRDs and deploy the operator into a cluster.

0
installs
▌
Build Helm Charts · ibm
Build the development Helm charts for the License Service family (License Service, License Service Reporter, License Service Scanner) used for the "License Service without an IBM Cloud Pak" / no-operator deployment path. Use to package and test Helm-based deployments after changing the chart sources under deploy/argo-cd, helm-migration, or helm-no-operator.

0
installs
▌
Refresh Agents Md · ibm
Keep the root AGENTS.md agent guide accurate and in sync with the repo - refresh it after changes to the Makefile targets, toolchain versions, api/ or controllers/ architecture, config/bundle layout, the versioning scheme, or the .bob/skills/ catalog. Use when AGENTS.md is stale, when onboarding guidance drifts from reality, or after adding/removing/renaming a skill.

0
installs
▌
Generate Manifests · ibm
Regenerate all derived artifacts after changing the ibm-licensing-operator API types or config - DeepCopy code, CRDs, RBAC, the OLM bundle/CSV, and the ArgoCD GitOps YAMLs. Use after editing anything in api/ or controllers/ (new fields, kubebuilder markers, RBAC markers, samples) so generated files stay in sync and can be committed.

0
installs
▌
Operator Sdk Guide · ibm
Explains how operator-sdk and kubebuilder work specifically for the ibm-licensing-operator - its CRDs, controllers, reconcile flow, scheme/manager wiring, kubebuilder markers, and the code-generation chain. Use to understand the operator's architecture, where to add a field or controller behavior, what a kubebuilder marker does here, or how the CRD/RBAC/bundle artifacts are generated.

0
installs
▌
Implementation Plan · ibm
Turn a task description into a detailed, actionable implementation plan written to a markdown file. Give it the task (a path to a description file, or inline prompt text - what needs to be done, where, and the constraints) and where to save the plan; the skill reads the task, grounds itself in the actual codebase, runs a planning loop, and writes a structured, step-by-step plan to the file the caller chose. It plans only - it does not implement. Use when asked to "plan", "write an implementation plan", "design an approach", or "break down" a task before coding. Repo-agnostic.

0
installs
▌
License Service Architecture · ibm
How License Service is split across three separate repositories - the operator (this repo), the operand (the containerized License Service application), and the commons (a shared library) - and how they interplay at build time and runtime. Use to understand which repo owns what, where a change belongs, and how the pieces fit together. Does NOT assume the repos are checked out together or live in the same directory/catalog.

0
installs
▌
Review · ibm
Review committed changes in the current branch. Use when the user asks to review, audit, or critique a branch — covers code quality, skill quality, bugs, linting issues, and adherence to project guidelines. Produces a structured review report written to a markdown file.

0
installs
▌
Using Ado CLI · ibm
Reference for ado CLI command syntax, flags, and usage patterns — get, create, edit, show, describe, output flags (-o, --output-file), convenience flags (--use-latest KIND, --set, --with), and debugging with -l. Use when writing, verifying, or debugging ado CLI commands; looking up correct command syntax or flags; or when unsure which ado command or flag to use. For listing catalogs or answering data questions, use the query-ado-data skill. For running a single experiment on one point, use the run-experiment skill.

0
installs
▌
Query Ado Data · ibm
Covers how to query ado catalog listings (available experiments and operators), the ado metastores (resource metadata queries) and ado samplestores (measurement data queries). via the ado CLI tool. Use when: the user asks what experiments, actuators or operators are available; to list projects or context or check the active context or project; to list or find ado resources like spaces, operations or datacontainers; to get ado resource schemas; to filter resources by their metadata or labels; or to retrieve/export entities and measurement data.

0
installs
▌
Run Experiment · ibm
Use the run_experiment tool to execute one experiment on a single point (entity) without creating a discoveryspace or operation. Use when smoke testing or functionally validating an actuator, custom experiment, or actuator configuration; debugging experiment execution or entity validation; or when a single measurement is wanted without ado metastore tracking. For campaigns over many entities, see define-experiment-campaign; for the ado CLI itself, see using-ado-cli.

0
installs
▌
Remote Execution · ibm
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.

0
installs
▌
Plugin Development · ibm
Guidelines for developing ado plugins (actuators, operators, and custom experiments). Covers package structure, versioning, entry points, custom experiment decorators, testing, and linting. Use when creating, modifying, or reviewing a plugin under plugins/ or examples/; adding an actuator, operator, or custom experiment; or when the user asks how to extend ado.

0
installs
▌
Examining Ado Project · ibm
Understand the work done in an ado project/context: recent activity, research underway, study documents, spaces and operations over time, experiments and configs used. Use when the user asks for the latest or recent activity in a project; what research strands, studies, or work are underway; a project or context overview or status; trends across spaces/operations/studies; or to onboard onto an ado project.

0
installs
▌
Generate Release Notes · ibm
Generate a structured changelog for GitHub release notes from changes since the last release. Use when the user asks to generate release notes, a changelog, or a summary of changes since the last tag/release.

0
installs
▌
Resource YAML Creation · ibm
Guidance for creating ado resource YAML files (discoveryspace, operation, actuatorconfiguration, samplestore, document). Covers metadata conventions, dynamic reference resolution with --use-latest/--with/--set, space design principles, avoiding duplicate resources, document reports, and validation. Use when creating or editing any ado resource YAML file.

0
installs
▌
Ado Project Maintenance · ibm
Describes how to maintain an ado project including how to identify resources that are candidates for deletion, and how to label testing or provisional resources. Use when asked to clean up, tidy, or run maintenance on an ado project/context; to find what can be deleted; or to review/curate resource metadata.

0
installs
▌
Conduct Empirical Study · ibm
End-to-end workflow for using ado to conduct an empirical study — systematic exploration of entity spaces/configuration spaces via experiment campaigns and analysis of the results. Covers problem formulation, implementation of custom experiments or analysis operators, campaign execution (local or remote), and analysing results. Use when the user wants to run a multi-entity study, answer research questions empirically, benchmark systems, or collect data across a parameter space.

0
installs
▌
Examining Ado Operations · ibm
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.

0
installs
▌
Define Experiment Campaign · ibm bundle
Describes how to create experiment campaigns for addressing primary research questions using ado (creating ado discoveryspace and operation YAML). Guides experiment selection, parameterization, entity-space design, validation, and operator selection. Use when the user wants to create or configure an experiment campaign (choosing points to explore, experiments to use, sampling method), write discoveryspace or operation YAML to address a a research, benchmarking, or search problem.

0
installs
▌
Examining Discovery Spaces · ibm
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 used in a space, or sampling coverage; provides a space ID or asks to use --use-latest for the current space.

0
installs
▌
Create Research Study Document · ibm
Describes how to create documents (document resources) that track an in-progress research study: motivation, question, objectives, materials, study labels, and a todo list of next steps. Use when starting a study, creating a study document, updating study todos/objectives, or when the user mentions a study document by name (e.g. study-$ID) or asks about study tracking.

0
installs
▌
Data Product Creation · ibm bundle
Use this skill when a user wants to create, publish, or set up a new data product in IBM watsonx.data intelligence (wxdi) / Data Product Hub. Trigger when the user says things like "create a data product", "publish a dataset as a data product", "I want to share this data as a product", "set up a data product for X", "onboard this asset to the catalog as a product", or "build a data product from my data". This skill uses a file-based specification approach where data product definitions are created as JSON/YAML files in the workspace, reviewed and refined iteratively, then batch-submitted to DPH. This enables version control, collaboration, and reusability.

1
install
▌
Lineage · ibm
Use this skill to explore upstream/downstream data lineage and historical lineage changes through a guided 3-phase workflow - asset identification → lineage graph traversal → historical version comparison. Handles both direct lineage search and catalog-first lookup with ID conversion. Triggers when user asks about data relationships, sources, or consumers using phrases like - "what feeds", "what feeds into", "what feeds in", "where does X come from", "what sources", "what produces", "upstream", "downstream", "lineage", "impact analysis", "data pipeline", "trace this data", "what depends on", "what consumes", "what changed", "data flow", "source to target", "pipeline history", "lineage changes", "show lineage for", "get lineage of", "what is impacted"

1
install
▌
Onboard And Enrich · ibm
Use this skill to orchestrate a 4-phase data cataloging or metadata onboarching and metadata enrichment workflow i.e. project setup → connection configuration → metadata import → metadata enrichment. The user can choose to start from any phase and the skill will guide them through the remaining phases.

1
install

84 published skills