workbench-manage

Create and manage Jupyter notebook workbenches on OpenShift AI with image selection, resource configuration, PVC storage, and lifecycle management. Use when: - "Create a notebook workbench" - "Spin up a Jupyter environment for data science" - "Start / stop my workbench" - "What notebook images are available?" - "Delete a workbench I no longer need" Handles Notebook CR lifecycle: create with configurable images and resources, start/stop, attach storage, and delete with data loss warnings. NOT for deploying models (use /model-deploy). NOT for creating projects (use /ds-project-setup). NOT for managing pipelines (use /pipeline-manage).

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced operational guide with strong validation and HITL discipline around destructive operations. Its weakness is repetition: duplicated fallback boilerplate and per-call parameter restating inflate the token cost without adding information.

Suggestions

State the OpenShift PVC fallback once (in Prerequisites or a short convention note) and reference it by name from Steps 3/5/6 instead of repeating the full three-sentence fallback each time.

Collapse the repeated per-call parameter blocks by defining a convention (e.g., all rhoai tools take `namespace` plus the target resource `name`) once in Prerequisites, then only listing call-specific parameters in the workflow.

Move the three inlined Issue subsections into references/common-issues.md (keeping only a one-line pointer each), and either link or remove the orphaned known-model-profiles.md and live-doc-lookup.md reference files.

Dimension	Reasoning	Score
Conciseness	No concept-explaining fluff, but the PVC fallback sentence ("If rhoai unavailable or returns error: Use `resources_list`/`resources_create_or_update`/`resources_delete`... See openshift-fallback-templates.md#pvc...") is repeated nearly verbatim three times, and dozens of per-call parameter blocks ("namespace - REQUIRED", "name - REQUIRED") restate what the Prerequisites section already enumerated.	3 / 5
Actionability	Every step names the exact MCP tool, concrete parameter values (apiVersion, kind, labelSelector, JSONPath fields like `.spec.tags[].from.name`), verbatim user-facing prompts, and specific fallback patterns — copy-paste-ready guidance for an instruction-only skill.	5 / 5
Workflow Clarity	Steps 1–6 are clearly sequenced with intent routing, and validation checkpoints appear throughout: namespace validation, PVC Bound/Pending verification, startup polling with an explicit give-up window, state-change verification after stop, and mandatory confirmation gates with data-loss warnings before every destructive operation.	5 / 5
Progressive Disclosure	References are real bundle files, one level deep, and clearly signaled with purpose; however the three inlined "Issue" subsections duplicate content delegated to common-issues.md, and known-model-profiles.md and live-doc-lookup.md exist in the bundle but are never referenced from the body.	4 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete capability list, explicit trigger phrases, and explicit NOT-for boundaries that prevent mis-triggering against sibling skills. The only gap is missing natural trigger terms for the list/status operations the skill supports.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with comprehensive coverage: "image selection, resource configuration, PVC storage, and lifecycle management" and "create with configurable images and resources, start/stop, attach storage, and delete with data loss warnings".	5 / 5
Completeness	Explicitly answers both "what" (two capability summaries covering the Notebook CR lifecycle) and "when" via an explicit "Use when:" clause with concrete trigger phrases, matching the top anchor's shape.	5 / 5
Trigger Term Quality	Five natural quoted triggers ("Create a notebook workbench", "Spin up a Jupyter environment for data science", "Start / stop my workbench", "What notebook images are available?", "Delete a workbench I no longer need") cover the core operations, but natural terms for listing workbenches and checking status — both advertised capabilities — are missing.	4 / 5
Distinctiveness Conflict Risk	Clear Jupyter workbench niche with explicit negative boundaries ("NOT for deploying models (use /model-deploy)", "NOT for creating projects", "NOT for managing pipelines") routing adjacent intents to sibling skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: RHEcosystemAppEng/agentic-plugins
Path: rh-ai-engineer/skills/workbench-manage/SKILL.md
Commit: e46c4fa

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.