datarobot-oss/datarobot-agent-skills
DataRobot skills for AI and machine-learning workflows, including model training, deployment, predictions, monitoring, explainability, data preparation, CI/CD, workload operations, and application observability.
Changelog
All notable changes to DataRobot agent skills are tracked here.
The format follows Keep a Changelog, and the
version numbers track the shared plugin version maintained across package.json,
.claude-plugin/, .cursor-plugin/plugin.json, .codex-plugin/plugin.json, and gemini-extension.json.
Each entry should be prefixed with the affected skill folder name (for example,
`datarobot-predictions`: ...) so it's easy to scan what changed per skill.
Version bumps, [Unreleased] renames, and releases are automated—see
CONTRIBUTING.md.
[Unreleased]
Removed
repo: Removed the datarobot-agent-tester e2e skill suite: theTest Skills E2Eworkflow,tests/e2e, thee2edependency group, the pre-commit hook,task setup,task test:e2eand.env.example.
[1.30.0] - 2026-10-29
Fixed
datarobot-gap-analysis: LLM checks (Layers 2 and 4) also run whendr opencodeuses opencode 2.x, and the report's token usage is filled in there too (datarobot-skills-utils 0.1.1).packages/datarobot-skills-utils: 0.1.1'srun_workerandOpenCodeServeraskdr opencode --versiononce per process and, for opencode 2.x, runs workers with--serveror--standaloneinstead of--attach,--dirand--pure, sends the prompt on stdin, protects the private server with a generated password and checks its/api/inforoute, reads token usage from the server when the event stream leaves it out, and reports opencode's own error message when a call fails. Commands for opencode 1.x are unchanged..opencode-plugin: export a default plugin definition (id,serverandeffect) so the plugin loads in OpenCode 2.x and still loads in 1.x.
[1.29.0] - 2026-10-23
Changed
datarobot-agent-assist: Specs are now written toagent_spec.yaml; existingagent_spec.mdspecs remain readable, with the YAML file preferred when both exist.
[1.28.0] - 2026-10-22
Added
datarobot-gap-analysis: New skill. Scores an agent repository (a GitHub URL or local path, DataRobot-built or not) against a seven-pillar enterprise-readiness framework (Security, Identity, AI Governance, Reliability, Ops, IT Conformance, Regulatory & Policy) using deterministic scanners (secrets, CVEs, IaC, licenses, Dockerfiles, CI gates), LLM code review, policy conformance checks, and a regulatory layer sourced live from the org's DataRobot risk-management policy (EU AI Act by default), each gap resolved to numbered fix steps and a docs link. Recommends a Patch/Hybrid/Re-platform path onto DataRobot's agent template without changing the repo's existing framework unless asked.--fixapplies safe fixes on agap-fixes/*branch;--verifyre-scores. Reports are Markdown and HTML.datarobot-gap-analysis: Layer-2 and secret-scanner findings are verified by a second LLM pass with line-accurate citations before being reported or fixed, so an unconfirmed secret is never auto-fixed. Large files reach the model as excerpts instead of head-truncated blobs, and each gateway model's output-token limit is raised so long replies no longer get cut mid-JSON.datarobot-gap-analysis: Reports open with a per-layer coverage summary and close with LLM Gateway token usage; timed-out checks list the command to rerun them.--fix --fromreuses saved findings instead of re-analyzing, and findings that aren't auto-fixed ship a copy-ready prompt for the developer's own coding agent instead of a one-shot LLM edit.packages/datarobot-skills-utils: New shared Python package (stdlib-only) providing thedr opencoderuntime used bydatarobot-gap-analysisanddatarobot-agent-assist's swarm simulation: server lifecycle management, worker invocation, JSONL event parsing with token/cost accounting, and reasoning-effort injection. Published to PyPI frompublish-pypi.ymlwhenever a release carries a new package version (0.1.0 is already published), versioned independently of the plugin, and resolved automatically from a sibling checkout, an installed copy, or an exact-pinned PyPI install.
Changed
datarobot-agent-assist: Mentiondatarobot-gap-analysisas a follow-up step after a successful deploy.repo: Pinned the tools and actions the CI workflows use (yamlfmt, license-eye, the claude, gemini and codex CLIs, and every GitHub Action by commit SHA), locked theuvinstall with--locked, set the Python version in.python-version, and limited the lint and e2e workflows to read-only permissions. Added zizmor totask lintto audit the workflows. Ruff and mypy updates now come from Dependabot in their own PR, and Dependabot waits 7 days after a release.repo: Configured pytest (testpaths, strict markers and config) so a barepytestruns the integration tests, and made the pre-commit hook run ruff on staged Python files before the skill e2e step.
[1.27.0] - 2026-10-19
datarobot-agent-assist: Added NO_COLOR=True to for shell commands to prevent ANSI color escape codesdatarobot-agent-assist: Revert application template version to 11.12.2.
[1.26.0] - 2026-10-19
datarobot-agent-assist: Bumped application template version to 11.12.7.
[1.25.0] - 2026-10-16
Added
datarobot-agent-assist-deploy-workload: New sub-skill that deploys a single-container agent with the Workload API (dr workload up) instead of Pulumi. It applies to projects without aninfra/Pulumi.yaml. Agent assist still uses Pulumi for the agent template, for agents that need a GPU, a standalone MCP server, guard models or many tools, and when the Workload API is off for the account.
[1.24.0] - 2026-10-16
Changed
repo: Pinned the ruff rule set to the pre-0.16 defaults plus import order, bugbear and security rules, and excluded Markdown fromruff format, so upgrading ruff to 0.16 or later no longer adds rules or reformats skill docs.repo: Raisedrequires-pythonto 3.12, adopted ruff's expanded default rules and fixed what they found in the skill scripts and tests:datetime.UTC, an explicitcheck=onsubprocess.run,zip(strict=True), executable bits on scripts with a shebang, and parenthesized implicit string concatenations.zipin thelist_llm_models.pytable renderer now raises on mismatched lengths instead of truncating.
[1.23.0] - 2026-10-16
Fixed
datarobot-connectivity-jdbc-sql: Fixedtablesandcolumnsbuilding SQL that a name with a backslash could break out of on Snowflake, Redshift and other dialects that read\'as an escaped quote. Backslashes are now doubled in every catalog value, and BigQuery, Databricks and Spark reject a backslash in a catalog or schema name. Documented each remaining string-built query with an inlinenoqaand its reason.
[1.22.0] - 2026-10-15
Fixed
datarobot-agent-assist-simulate: Fixedtool_executor.pyre-executing forever when the.venvinterpreter reports a differentsys.prefix, for example a.venvwithoutpyvenv.cfg. It now re-execs at most once.
[1.21.0] - 2026-10-15
Fixed
datarobot-agent-assist-simulate:tool_executor.pynow re-execs into the nearest.venvbeside the tools file before importing it, soselective_e2ecorrectly resolves the agent's dependencies rather than the swarm's interpreter. Also handles async tool functions (viaasyncio.run) and Pydantic return values (viamodel_dump) that previously caused serialization errors.
[1.20.0] - 2026-10-15
Added
datarobot-connectivity-jdbc-sql: New skill for running SQL through DataRobot against a database reached with a caller-supplied JDBC URL and driver properties, without registering a data connection. It tests connectivity, lists tables and columns with dialect-aware catalog SQL, runs read queries via/jdbcDataPreview/, and runs DML/DDL via/jdbcExecution/only after a dry-run plan and an explicit--confirm. Secrets come from environment variables or.envand are masked in all output. Ships the standard-libraryscripts/jdbc_sql.pyand references for the API contract, driver URL templates and dialect limits, and app integration, including a migration checklist for Talk to My Data.repo: Added offline preflight tests that run before the paid LLM judge. They check the agentskills.io frontmatter limits, that linked files and script paths exist, that Python and shell samples parse, that scripts start with--help, and that no skill file holds an internal host, employee email, private IP address or credential. The e2e CI job also prints skip reasons now.repo: Added ruff import-order, bugbear and security rules, a repo-wide shellcheck glob, actionlint for workflows,claude plugin validate skills, and Dependabot for GitHub Actions, uv and npm. CI now fails on Trivy secret findings and when the e2e job skips skills because the LLM gateway call failed.
Changed
datarobot-agent-assist:setup_template.pyruns its Pulumi,drandtaskcommands without a shell. A missing tool now fails with an error message instead of a shell exit code.
Fixed
repo: Fixed the preflight--helpcheck failing on modules inside a Python package. They use relative imports and cannot run as scripts, so the check now skips them.repo: Fixed false INCOMPLETE verdicts in the e2e skill gate. A judge report with## Overall Verdictwas read as INCOMPLETE because the report text mentioned "incomplete". The gate now reads the verdict line at any heading level.
[1.19.0] - 2026-10-15
Added
repo: Addedtests/integration/test_sdk_conformance.py, which resolves every DataRobot SDK call inSKILL.mdpython fences and skillscripts/*.pyagainst the installeddatarobotpackage and checks its signature. Methods that do not exist and calls with wrong arguments now failtask lint. It needs no DataRobot account.
Fixed
datarobot-predictions: Replaced the single-argumentdr.Model.get, the nonexistentModel.get_features()andProject.get_time_series_info()withdeployment.get_features()anddr.DatetimePartitioning.getin the samples and scripts. Batch scoring usesBatchPredictionJob.score(deployment=...).datarobot-model-training: Fixed the time series pattern to usedr.DatetimePartitioningSpecification, removed theDataset.create_from_file(name=...)argument (upload, thendataset.modify(name=...)), and replaced the nonexistentwait_for_completion()withwait_for_autopilot().datarobot-data-preparation: Corrected theDataset.create_from_filesignature in the guide and inscripts/upload_dataset.py.datarobot-feature-engineering: Fixed the two-argumentdr.Model.getcalls and the undefined helpers in the Quick Start.datarobot-workload-api: Tagged the credential injection payload as JSON so it parses.
[1.18.0] - 2026-10-13
Added
datarobot-connectivity-datastore-sql: New skill for running SQL through DataRobot data connections (datastores) with their stored credentials. It lists connections and credentials, browses schemas, tables and columns, previews tables, and runs read queries via/previewQuery/, falling back to/verifySQL/where the newer routes are not available. DML/DDL runs via/executeUpdate/only after a dry-run plan and an explicit--confirm. Ships the standard-libraryscripts/datastore_sql.pyand references for the API contract, per-connector capabilities and dialects, and troubleshooting.
[1.17.0] - 2026-10-08
Changed
datarobot-workload-api: Madedr workload config/upthe default deploy path from a project directory: documented the.datarobot.yamlmanifest shape and managed-fields rule,promote,--sync-env,--spec-file,delete --purge, and addedreferences/cli-command-map.mdcoveringdiagnose,events,settings, thelogsfilters andcode sync --push-only.
[1.16.0] - 2026-10-07
repo: Fixed OpenAI plugin listing: category set to Developer Tools (Coding is not a valid marketplace category).datarobot-app-framework-cicd: Replaced thecurl | shPulumi install in the state-management guide with Homebrew and a link to the official install docs.
[1.15.0] - 2026-10-06
repo: Fixed OpenAI plugin listing: brand color now meets 2:1 contrast on white (Indigo#5C41FF), category set to Coding, and listing text no longer references other AI agents.datarobot-setup: Required user confirmation before running the Linux/WSL installer scripts, and replaced the go-taskcurl | shinstall withuv tool install go-task-bin.
[1.14.0] - 2026-10-02
repo: Added automated public Codex plugin packaging, release attachment, and manifest synchronization.datarobot-agent-assist: Expanded integration test coverage for how LLM choices flow from catalog listings intoagent_spec.mdand.env(gateway vs. deployed routing,setup_and_runfailure paths, spec completeness), and added an on-prem / deployed-LLM example toagent-spec-examples.md.
[1.13.0] - 2026-09-30
Added
datarobot-external-agent-monitoring: Recommend intelligent trace analysis via Tensile (tensile>=0.12.0). Each framework reference file gains an Intelligent Trace Analysis via Tensile section showing wheretensile.otel.install(tracer=False)goes for that framework.
[1.12.0] - 2026-09-29
datarobot-agent-assist: Clarified that the "After Coding" next-steps menu must be reproduced verbatim (same wording, order, and numbers) rather than paraphrased or renumbered, after an observed case where the assistant referenced "option 3" for a menu item that was actually numbered differently.
[1.11.0] - 2026-09-24
repo: Added Codex plugin metadata and included the Codex manifest in the shared version bump workflow.datarobot-workload-api: Never gate CLI commands on a pinneddrversion — always rundr self update --forcefirst, matchingdatarobot-agent-assist's handling. Addedreferences/declarative-cli-deploy.mddocumentingdr workload config/dr workload up, the CLI-native one-command create/build/deploy/resize path that replaces most manual REST choreography for project-directory deploys — notingup/configcan returnunknown commandeven on an otherwise-current CLI, independent ofdr self update, with the manual flows as the fallback. Fixed the Code-to-Workload state directory (.datarobot/workload/, not.wapi/),codeReffield placement (imageBuildConfig.codeRef, not directly on the container — PATCH silently drops a misplaced value),dr workload logs --levelsemantics (minimum threshold, not exact match), anddr artifact code sync/build create/build logsbehavior against the live v0.9.0 CLI (three-way diff with remote-wins auto-resolve,--wait,CANCELLEDterminal status, structured JSON build logs). Documented the edge's forwarded identity headers and spoof-test results, sharing-role casing (OWNER/USER/CONSUMER, uppercase), the rolling-roll proton-watch trap, and that some instances omit Workload API paths from the public OpenAPI spec. Sharpened the web-UI auth-disable guardrail to require surfacing the tradeoff to the user, not disabling unilaterally.datarobot-workload-api: Rewrote SKILL.md and allreferences/*.mdfor token economy — terser phrasing, fewer filler words, tighter headings — with no change in technical content. SKILL.md dropped from 6647 to 6262 tokens (still under the 6700 hard cap); reference files dropped ~12% in word count combined.
[1.10.0] - 2026-09-22
datarobot-agent-assist: Unified and increased timeouts for git commands and long running task commands in helper scripts.
[1.9.0] - 2026-09-21
datarobot-agent-assist: Increased timeouts to prevent failing some of the long running scripts/tools.
[1.8.0] - 2026-09-02
Added
datarobot-agent-assist: Dress rehearsal exports a shareable Markdown report to<target_dir>/rehearsal_report/rehearsal_report.md(archived under.datarobot/rehearsal/<session_id>/).DONEalways runs--reportbefore any summary or menu; post-design next steps add Review rehearsal report.NOTE:observations persist viarehearsal.py --note. Session state lives under.datarobot/rehearsal/instead of the system temp dir.
Changed
datarobot-agent-assist: Bumped application template version to 11.11.6.datarobot-agent-assist: DeduplicatedSKILL.mdby pointing dress rehearsal, clone discipline, and spec validation at the reference files instead of restating them.datarobot-agent-assist: Welcome menu infers a clear free-text category (and asks when ambiguous).frontend.typemay be held from the Clarification Phase before the first spec draft exists.datarobot-agent-assist: Tool/service secrets stay in.envonly — coding appendsVAR_NAME=and asks the user to paste values in their editor, never in chat,agent_spec.md, or source.datarobot-agent-assist: Spec-only / messy-cwd classification treats dress-rehearsal artifacts (.datarobot/rehearsal/,rehearsal_report/) as design-phase files so they do not force a subdirectory clone.
Fixed
datarobot-agent-assist: Rehearsal reports pair parallel tool returns with the matching call (previously every return was labeled with the last tool).model_substituted/simulation_substitutednow compare against the originally requested model so a runtime fallback does not leave a stale flag.
[1.7.0] - 2026-09-02
Added
datarobot-agent-assist: Support an OpenAI-completions-compatible external LLM (AGENT_ASSIST_LLM_MODEL_NAME,AGENT_ASSIST_LLM_API_KEY,AGENT_ASSIST_LLM_BASE_URL) as a model source alongside the LLM Gateway and deployed models, solist_llm_models.pyandsetup_template.py --llm-base-urlcan wire up a template without a DataRobot endpoint or token. Also letsclone_template.pyoverride the template repo viaAGENT_ASSIST_TEMPLATE_REPO_URL/_BRANCH/_TAG, with branch now taking priority over tag when both are set.
[1.6.0] - 2026-08-26
Added
datarobot-llm-gateway: Added a new skill which helps setting up llm gateway, it lists available llm models directly fromSKILL.md. The CLI handles auth via its own credential store, and syncs env variables.
[1.5.5] - 2026-08-26
Fixed
datarobot-model-monitoring: The Pattern 1 health-check example readstats.prediction_countandstats.mean_response_time, which do not exist on the SDK 3.xServiceStatsobject (AttributeError). Read them from the.metricsdict instead (stats.metrics["totalPredictions"],stats.metrics["responseTime"]). Also corrected the SDK reference list:model.get_metrics()→model.metrics(a dict of{metric: {partition: score}});get_metrics()does not exist.
[1.5.4] - 2026-08-25
Fixed
- All skills: helper scripts and examples now call plain
dr.Client()instead of re-readingDATAROBOT_API_TOKENandDATAROBOT_ENDPOINTand passing them back in. The SDK reads those variables itself and then falls back to~/.config/datarobot/drconfig.yaml, so this fixes setups where onlydrconfig.yamlis configured — whatdr auth login(perdatarobot-setup) writes. Previously most sites hardcoded a"https://app.datarobot.com"endpoint default, which supplied an endpoint with no matching token and failed withValueError: Token must be specified if endpoint is specified(and was missing the/api/v2suffix);datarobot-model-explainabilityusedos.environ["DATAROBOT_API_TOKEN"]and failed the same setup withKeyError.
[1.5.3] - 2026-08-25
Fixed
datarobot-model-training: Update the sample code and helper scripts for the currentdatarobotSDK (3.x).set_target()→analyze_and_model()(sets the target and starts AutoPilot), the removedProject.start(autopilot_on=, max_wait=)→wait_for_autopilot(),project.status→project.stage,model.get_metrics()→model.metrics, and select the recommended model viaModelRecommendation.get(project.id).get_model()instead of a brokenmax(models, key=lambda m: m.metrics.get("AUC", 0))that treats a per-partition dict as a scalar.list_models.pynow sorts on the validation partition score (null-safe).
[1.5.1] - 2026-08-13
Fixed
datarobot-agent-assist:LLM_DEFAULT_MODELnow gets thedatarobot/-prefixedllm_default_modelvalue, not the catalogllmIdthe gateway 404s on.setup_template.pyrefuses anllmId;api_modelstays unprefixed for the on-the-wire rehearsal.datarobot-agent-assist: The model table leads withLLM_DEFAULT_MODEL(not the unusablellmId) and gives the deployment id its own column, shown only when a deployed entry is present.datarobot-agent-assist: The dress rehearsal strips thedatarobot/prefix before reading a provider, so a prefixed spec keeps its cross-provider guard instead of matching nothing and rehearsing against an arbitrary catalog pick.datarobot-agent-assist:setup_template.pyverifies the model with a direct catalog API call (notdr llm-gateway list, which can fall back to a stored profile and answer about a different instance), rejects characters that would break the.envline, and treats a disabled gateway as a cue to pick a deployed LLM.
[1.5.0] - 2026-08-10
Added
datarobot-agent-assist: Make a DataRobot-deployed LLM selectable end to end.agent_spec.mdgains an optionalllm_deployment_id, andsetup_template.pygains--llm-deployment-id, writingLLM_DEPLOYMENT_ID,INFRA_ENABLE_LLM=deployed_llm.py, andUSE_DATAROBOT_LLM_GATEWAY=0so the template routes to the deployment instead of the LLM Gateway. Model selection recommends a deployed LLM when the gateway is empty or disabled, which is the normal shape of an on-prem install.
Fixed
datarobot-agent-assist: DataRobot-deployed LLMs are listed on everydrversion the agent template accepts.dr llm-gateway listonly reports them from v0.2.79 while the template's minimum is 0.2.77, and a non-empty gateway was enough to skip the direct-API fallback, so the deployed source silently did not exist on an older CLI.datarobot-agent-assist:setup_template.pyrefuses the shareddatarobot-deployed-llmplaceholder without a deployment id, instead of leaving the template on its gateway configuration to fail later atpulumi upwithModel 'datarobot-deployed-llm' not found in catalog. The placeholder is matched case-insensitively, since the value comes from LLM-authored spec text.datarobot-agent-assist: The dress rehearsal resolves a deployed LLM through the spec'sllm_deployment_id. Resolving onmodelalone matched whichever deployment the catalog indexed last and reported it as an exact match, so a spec could silently rehearse against a different deployment than the one selected.datarobot-agent-assist:list_llm_models.pycloses stdin on thedrsubprocess, so a credential prompt fails immediately rather than waiting out the timeout, and it names the requested instance alongside the CLI's log lines, making visible the case where the CLI ignored the passed credentials and listed a different instance.datarobot-agent-assist: Deployment labels are collapsed to one pipe-free line when rendering the model table; an embedded newline in user-authored label text split a row apart.datarobot-agent-assist:SKILL.mddocumentedlist_llm_models.pywithout its required--target-dir, and its Helper Scripts section referenced an undefined<scripts_dir>placeholder instead of the<skill_scripts_dir>the skill resolves. Both made the documented invocations dead instructions.datarobot-agent-assist:ensure_env_fileprinted its progress line and thedr dotenv setupoutput to stdout, solist_llm_models.py --jsonproduced unparseable output on a target directory with no.env. Both now go to stderr.
[1.4.3] - 2026-08-05
Changed
datarobot-agent-assist-simulate: Refine UX for swarm simulation.
[1.4.2] - 2026-08-04
datarobot-model-training: Create/associate adr.UseCasewhen creating datasets and projects, so projects aren't orphaned in the DataRobot UI.
[1.4.1] - 2026-08-03
Changed
datarobot-agent-assist-simulate: UX improvements — domain-aware Q2, grouped scenario list,dr dotenv updatein auth setup, live progress narration during swarm run.
[1.4.0] - 2026-07-28
Added
datarobot-agent-assist: Newagent-assist-simulateswarm skill — adversarial scenario generation, multi-turn simulation, convergence loop, and evaluation reporting.
Changed
datarobot-agent-assist: Movecheck_codespace.pyintoagent-assist-build/scripts/alongsideenv_utils.py.datarobot-agent-assist: Pinruff==0.15.22in dev dependencies to prevent silent version drift.
[1.3.10] - 2026-07-28
datarobot-agent-assist: Merge pre-coding spec gate intopre-coding-checklist.mdBootstrap step 2 (removes duplicate "Before Coding Begins" section). Add missing-spec recovery, path validation, session flags, workspace ask-don't-guess for Code, and journey deduplication. TrimSKILL.md: move CLI setup, helper scripts, plugin tool mapping, dress rehearsal prompt, path resolution, and agent_spec schema into references. Flow polish: Code-no-spec merges with Path resolution step 1, schema read hook in Spec Display,design_to_codeguard and Windows stop in pre-coding, welcome menu resetsdesign_messy_cwd.
[1.3.9] - 2026-07-22
datarobot-workload-api: Addreferences/web-uis-behind-the-edge.mdfor serving a browser-facing web app (UI + backend) through the workload endpoint — the edge gateway strips the path prefix (inbound shim + base-path derived from the injectedWORKLOAD_ID; proton-id path needs an explicit override), is itself the auth gate and hijacks theAuthorizationheader (so disable the app's own auth and trust the edge), shared-origin_xsrf/CSRF collisions, and WebSocket pass-through. Correct artifact-replacement guidance: same-artifact replacement is allowed for drafts,PATCH /settings/rolling-redeploys onto a rebuilt image, andimageUriis build-managed (never hand-PATCH it or PATCH the spec mid-build). TrimSKILL.md~18% to stay within the context-window budget.
[1.3.8] - 2026-07-17
datarobot-agent-assist: Warn when the ports needed for local agent testing (5173, 8080, 8842) are not exposed inside a DataRobot Codespace, and stop with guidance when Agent Assist runs from an unsupported working directory. Newcheck_codespace.pyhelper wired into the Pre-requisite Check; no-op outside a Codespace.
[1.3.7] - 2026-07-14
datarobot-external-agent-monitoring: Fix PydanticAI instrumentation — modern PydanticAI makes OpenTelemetry instrumentation opt-in, so configuring a provider alone emitted no spans; document the requiredAgent.instrument_all()call.
[1.3.6] - 2028-07-14
datarobot-agent-assist: Implement pre-coding-checklist, pre-deployment-checklist & workspace-resolution flows.
[1.3.5] - 2028-07-08
datarobot-agent-assist: Bumped application template version to 11.10.7.
[1.3.4] - 2028-07-01
datarobot-agent-assist: Improved rehearsal flow to properly handle missing LLM model cases and improved user-facing messaging; refactored Dress Rehearsal instructions into separatereferences/dress-rehearsal.mdfile to reduce SKILL.md token count while preserving all behavior and control-flow reliability.datarobot-discover: New skill for discovering DataRobot resources — fetches the live catalog fromdatarobot.comand, if set, from$DATAROBOT_ENDPOINTto surface skills, MCP servers, agents, and platform resources without search index dependency.
[1.3.3] - 2026-06-25
datarobot-external-agent-monitoring: Support instrumenting existing (brownfield) agents — built on DataRobot or elsewhere — via the "Add tracing to my agent" trigger; resolve agentless invocations to the current IDE workspace; make a DataRobot Use Case the primary telemetry target (validate an existing Use Case ID, or create a net new one via the newcreate_use_case.pyhelper) with the shell deployment now optional; extract the OTel config template intoreference/dr_otel_config.md; makeverify_otel_connection.pyaccept theexperiment_container-(Use Case) entity prefix in addition todeployment-; defer Use Case creation/validation to the post-approval execute step (prerequisites only collect the choice) to avoid premature or duplicate creation; collect the API token via the project.envfile rather than chat (never asked for or echoed in the transcript).datarobot-setup: Broaden trigger to cover credential failures; add env var and auth validity checks to pre-flight.datarobot-workload-api: New skill for the DataRobot Workload API — create/configure, diagnose (CrashLoopBackOff/ImagePullBackOff/OOMKilled/exec format error), observe (logs/traces/metrics/stats), and artifact lifecycle (draft→lock→production, rolling replacement,promote, Code-to-Workload viadr workload code syncwhen no accessible registry). ModalSKILL.md+ bundledscripts/+ deepreferences/.datarobot-setup: Broaden trigger to cover credential failures; add env var and auth validity checks to pre-flight.datarobot-model-explainability: Correct SHAP export guidance fordatarobot.insights.ShapMatrix(in-memorymatrix/columnsor classmethodget_as_dataframe/get_as_csv); fixcompute_shap_matrix.py--outputexport; fix anomaly assessment date-range example to useget_explanations()instead ofget_latest_explanations(); fix Model diagnostics examples (get_confusion_chart,get_feature_effect); document insights diagnostics (RocCurve,LiftChart,ConfusionMatrix); correct documented SHAP caveats for blenders, the >1000-feature limit,ShapImpactsource support, logit-link probability conversion, XEMP contribution wording, XEMP routing guidance, and XEMPmax_explanationslimit; raise the documented minimum SDK version todatarobot>=3.6.0when referencingShapDistributions.
[1.3.1] - 2026-06-02
datarobot-setup: Corrected issues with setup commands.
[1.3.0] - 2026-05-27
datarobot-model-explainability: Updated SHAP guidance to use the currentdatarobot.insightsAPIs, added data slice and anomaly assessment coverage, added SHAP and XEMP reference docs, and added acompute_shap_matrix.pyhelper script.
[1.2.0] - 2026-05-20
First tracked release. Skills included:
datarobot-agent-assistdatarobot-app-framework-cicddatarobot-data-preparationdatarobot-external-agent-monitoringdatarobot-feature-engineeringdatarobot-model-deploymentdatarobot-model-explainabilitydatarobot-model-monitoringdatarobot-model-trainingdatarobot-predictionsdatarobot-setup