Skip to content

datarobot-oss/datarobot-agent-skills

v1.30.0Apache-2.0

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: the Test Skills E2E workflow, tests/e2e, the e2e dependency group, the pre-commit hook, task setup, task test:e2e and .env.example.

[1.30.0] - 2026-10-29

Fixed

  • datarobot-gap-analysis: LLM checks (Layers 2 and 4) also run when dr opencode uses 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's run_worker and OpenCodeServer ask dr opencode --version once per process and, for opencode 2.x, runs workers with --server or --standalone instead of --attach, --dir and --pure, sends the prompt on stdin, protects the private server with a generated password and checks its /api/info route, 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, server and effect) 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 to agent_spec.yaml; existing agent_spec.md specs 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. --fix applies safe fixes on a gap-fixes/* branch; --verify re-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 --from reuses 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 the dr opencode runtime used by datarobot-gap-analysis and datarobot-agent-assist's swarm simulation: server lifecycle management, worker invocation, JSONL event parsing with token/cost accounting, and reasoning-effort injection. Published to PyPI from publish-pypi.yml whenever 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: Mention datarobot-gap-analysis as 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 the uv install with --locked, set the Python version in .python-version, and limited the lint and e2e workflows to read-only permissions. Added zizmor to task lint to 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 bare pytest runs 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 codes
  • datarobot-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 an infra/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 from ruff format, so upgrading ruff to 0.16 or later no longer adds rules or reformats skill docs.
  • repo: Raised requires-python to 3.12, adopted ruff's expanded default rules and fixed what they found in the skill scripts and tests: datetime.UTC, an explicit check= on subprocess.run, zip(strict=True), executable bits on scripts with a shebang, and parenthesized implicit string concatenations. zip in the list_llm_models.py table renderer now raises on mismatched lengths instead of truncating.

[1.23.0] - 2026-10-16

Fixed

  • datarobot-connectivity-jdbc-sql: Fixed tables and columns building 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 inline noqa and its reason.

[1.22.0] - 2026-10-15

Fixed

  • datarobot-agent-assist-simulate: Fixed tool_executor.py re-executing forever when the .venv interpreter reports a different sys.prefix, for example a .venv without pyvenv.cfg. It now re-execs at most once.

[1.21.0] - 2026-10-15

Fixed

  • datarobot-agent-assist-simulate: tool_executor.py now re-execs into the nearest .venv beside the tools file before importing it, so selective_e2e correctly resolves the agent's dependencies rather than the swarm's interpreter. Also handles async tool functions (via asyncio.run) and Pydantic return values (via model_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 .env and are masked in all output. Ships the standard-library scripts/jdbc_sql.py and 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.py runs its Pulumi, dr and task commands without a shell. A missing tool now fails with an error message instead of a shell exit code.

Fixed

  • repo: Fixed the preflight --help check 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 Verdict was 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: Added tests/integration/test_sdk_conformance.py, which resolves every DataRobot SDK call in SKILL.md python fences and skill scripts/*.py against the installed datarobot package and checks its signature. Methods that do not exist and calls with wrong arguments now fail task lint. It needs no DataRobot account.

Fixed

  • datarobot-predictions: Replaced the single-argument dr.Model.get, the nonexistent Model.get_features() and Project.get_time_series_info() with deployment.get_features() and dr.DatetimePartitioning.get in the samples and scripts. Batch scoring uses BatchPredictionJob.score(deployment=...).
  • datarobot-model-training: Fixed the time series pattern to use dr.DatetimePartitioningSpecification, removed the Dataset.create_from_file(name=...) argument (upload, then dataset.modify(name=...)), and replaced the nonexistent wait_for_completion() with wait_for_autopilot().
  • datarobot-data-preparation: Corrected the Dataset.create_from_file signature in the guide and in scripts/upload_dataset.py.
  • datarobot-feature-engineering: Fixed the two-argument dr.Model.get calls 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-library scripts/datastore_sql.py and references for the API contract, per-connector capabilities and dialects, and troubleshooting.

[1.17.0] - 2026-10-08

Changed

  • datarobot-workload-api: Made dr workload config/up the default deploy path from a project directory: documented the .datarobot.yaml manifest shape and managed-fields rule, promote, --sync-env, --spec-file, delete --purge, and added references/cli-command-map.md covering diagnose, events, settings, the logs filters and code 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 the curl | sh Pulumi 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-task curl | sh install with uv 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 into agent_spec.md and .env (gateway vs. deployed routing, setup_and_run failure paths, spec completeness), and added an on-prem / deployed-LLM example to agent-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 where tensile.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 pinned dr version — always run dr self update --force first, matching datarobot-agent-assist's handling. Added references/declarative-cli-deploy.md documenting dr 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 — noting up/config can return unknown command even on an otherwise-current CLI, independent of dr self update, with the manual flows as the fallback. Fixed the Code-to-Workload state directory (.datarobot/workload/, not .wapi/), codeRef field placement (imageBuildConfig.codeRef, not directly on the container — PATCH silently drops a misplaced value), dr workload logs --level semantics (minimum threshold, not exact match), and dr artifact code sync/build create/build logs behavior against the live v0.9.0 CLI (three-way diff with remote-wins auto-resolve, --wait, CANCELLED terminal 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 all references/*.md for 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>/). DONE always runs --report before any summary or menu; post-design next steps add Review rehearsal report. NOTE: observations persist via rehearsal.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: Deduplicated SKILL.md by 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.type may be held from the Clarification Phase before the first spec draft exists.
  • datarobot-agent-assist: Tool/service secrets stay in .env only — coding appends VAR_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_substituted now 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, so list_llm_models.py and setup_template.py --llm-base-url can wire up a template without a DataRobot endpoint or token. Also lets clone_template.py override the template repo via AGENT_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 from SKILL.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 read stats.prediction_count and stats.mean_response_time, which do not exist on the SDK 3.x ServiceStats object (AttributeError). Read them from the .metrics dict 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-reading DATAROBOT_API_TOKEN and DATAROBOT_ENDPOINT and passing them back in. The SDK reads those variables itself and then falls back to ~/.config/datarobot/drconfig.yaml, so this fixes setups where only drconfig.yaml is configured — what dr auth login (per datarobot-setup) writes. Previously most sites hardcoded a "https://app.datarobot.com" endpoint default, which supplied an endpoint with no matching token and failed with ValueError: Token must be specified if endpoint is specified (and was missing the /api/v2 suffix); datarobot-model-explainability used os.environ["DATAROBOT_API_TOKEN"] and failed the same setup with KeyError.

[1.5.3] - 2026-08-25

Fixed

  • datarobot-model-training: Update the sample code and helper scripts for the current datarobot SDK (3.x). set_target() → analyze_and_model() (sets the target and starts AutoPilot), the removed Project.start(autopilot_on=, max_wait=) → wait_for_autopilot(), project.status → project.stage, model.get_metrics() → model.metrics, and select the recommended model via ModelRecommendation.get(project.id).get_model() instead of a broken max(models, key=lambda m: m.metrics.get("AUC", 0)) that treats a per-partition dict as a scalar. list_models.py now sorts on the validation partition score (null-safe).

[1.5.1] - 2026-08-13

Fixed

  • datarobot-agent-assist: LLM_DEFAULT_MODEL now gets the datarobot/-prefixed llm_default_model value, not the catalog llmId the gateway 404s on. setup_template.py refuses an llmId; api_model stays unprefixed for the on-the-wire rehearsal.
  • datarobot-agent-assist: The model table leads with LLM_DEFAULT_MODEL (not the unusable llmId) and gives the deployment id its own column, shown only when a deployed entry is present.
  • datarobot-agent-assist: The dress rehearsal strips the datarobot/ 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.py verifies the model with a direct catalog API call (not dr llm-gateway list, which can fall back to a stored profile and answer about a different instance), rejects characters that would break the .env line, 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.md gains an optional llm_deployment_id, and setup_template.py gains --llm-deployment-id, writing LLM_DEPLOYMENT_ID, INFRA_ENABLE_LLM=deployed_llm.py, and USE_DATAROBOT_LLM_GATEWAY=0 so 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 every dr version the agent template accepts. dr llm-gateway list only 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.py refuses the shared datarobot-deployed-llm placeholder without a deployment id, instead of leaving the template on its gateway configuration to fail later at pulumi up with Model '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's llm_deployment_id. Resolving on model alone 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.py closes stdin on the dr subprocess, 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.md documented list_llm_models.py without 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_file printed its progress line and the dr dotenv setup output to stdout, so list_llm_models.py --json produced 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 a dr.UseCase when 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 update in auth setup, live progress narration during swarm run.

[1.4.0] - 2026-07-28

Added

  • datarobot-agent-assist: New agent-assist-simulate swarm skill — adversarial scenario generation, multi-turn simulation, convergence loop, and evaluation reporting.

Changed

  • datarobot-agent-assist: Move check_codespace.py into agent-assist-build/scripts/ alongside env_utils.py.
  • datarobot-agent-assist: Pin ruff==0.15.22 in dev dependencies to prevent silent version drift.

[1.3.10] - 2026-07-28

  • datarobot-agent-assist: Merge pre-coding spec gate into pre-coding-checklist.md Bootstrap 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. Trim SKILL.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_code guard and Windows stop in pre-coding, welcome menu resets design_messy_cwd.

[1.3.9] - 2026-07-22

  • datarobot-workload-api: Add references/web-uis-behind-the-edge.md for 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 injected WORKLOAD_ID; proton-id path needs an explicit override), is itself the auth gate and hijacks the Authorization header (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, and imageUri is build-managed (never hand-PATCH it or PATCH the spec mid-build). Trim SKILL.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. New check_codespace.py helper 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 required Agent.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 separate references/dress-rehearsal.md file 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 from datarobot.com and, if set, from $DATAROBOT_ENDPOINT to 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 new create_use_case.py helper) with the shell deployment now optional; extract the OTel config template into reference/dr_otel_config.md; make verify_otel_connection.py accept the experiment_container- (Use Case) entity prefix in addition to deployment-; 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 .env file 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 via dr workload code sync when no accessible registry). Modal SKILL.md + bundled scripts/ + deep references/.
  • 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 for datarobot.insights.ShapMatrix (in-memory matrix/columns or classmethod get_as_dataframe/get_as_csv); fix compute_shap_matrix.py --output export; fix anomaly assessment date-range example to use get_explanations() instead of get_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, ShapImpact source support, logit-link probability conversion, XEMP contribution wording, XEMP routing guidance, and XEMP max_explanations limit; raise the documented minimum SDK version to datarobot>=3.6.0 when referencing ShapDistributions.

[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 current datarobot.insights APIs, added data slice and anomaly assessment coverage, added SHAP and XEMP reference docs, and added a compute_shap_matrix.py helper script.

[1.2.0] - 2026-05-20

First tracked release. Skills included:

  • datarobot-agent-assist
  • datarobot-app-framework-cicd
  • datarobot-data-preparation
  • datarobot-external-agent-monitoring
  • datarobot-feature-engineering
  • datarobot-model-deployment
  • datarobot-model-explainability
  • datarobot-model-monitoring
  • datarobot-model-training
  • datarobot-predictions
  • datarobot-setup