CtrlK
BlogDocsLog inGet started
Tessl Logo

ds-project-setup

Create and configure Data Science Projects on OpenShift AI with namespace setup, S3 data connections, pipeline server, and model serving enablement. Use when: - "Create a data science project" - "Set up a new namespace for ML work" - "Add an S3 data connection to my project" - "Configure the pipeline server" - "Enable model serving on my project" Bootstraps an RHOAI Data Science Project with proper labels, data connections, pipeline infrastructure, and model serving configuration. NOT for deploying models (use /model-deploy). NOT for creating workbenches (use /workbench-manage). NOT for managing pipelines after setup (use /pipeline-manage).

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

An excellent operational skill body: fully concrete tool invocations with parameters, fallbacks, verification, and error recovery, and a well-sequenced HITL workflow. The residual gaps are minor — slight tool-list redundancy and a Common Issues section inlined despite an existing common-issues.md reference file.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational specifics (MCP tool parameters, fallback paths, polling intervals, error-handling branches) and wastes few tokens on concepts Claude already knows. It is not a 5 because of minor trimmable redundancy: each tool's purpose is stated once in Prerequisites and again in its workflow step, and the DNS naming constraint ('lowercase, no spaces, max 63 chars') is repeated nearly verbatim in Steps 1 and 2. It clearly exceeds the score-3 anchor, which expects 'some unnecessary explanation'.

4 / 5

Actionability

Every step names the exact MCP tool, enumerates all REQUIRED/OPTIONAL parameters, gives the OpenShift fallback with concrete labelSelector/apiVersion values, and specifies verification calls plus polling cadence ('Poll every 15 seconds until ready or timeout (5 minutes)'). Error handling includes exact user-facing messages. This matches the fully-executable anchor; the only content deferred (DSPA YAML) is appropriately delegated to a clearly signaled reference template with its fill-in parameters enumerated inline.

5 / 5

Workflow Clarity

A clearly sequenced 5-step workflow with explicit validation after each creation step (get_project_details, list_data_connections, DSPA condition polling, get_project_status), explicit user-confirmation checkpoints ('WAIT for user decision', 'WAIT for user to confirm'), and error-recovery branches including a feedback loop back to Step 3 when the pipeline prerequisite is missing. This matches the score-5 anchor (clear sequence, explicit validation, feedback loops) rather than the score-4 anchor, which tolerates 'minor validation gaps' that are not present here.

5 / 5

Progressive Disclosure

Good structure: a workflow-focused body with clearly signaled, one-level-deep references to real files (skill-conventions.md for shared conventions, openshift-fallback-templates.md with anchored sections for YAML templates), and appropriate offloading of templates and shared conventions. It is not a 5 because the ~45-line inline 'Common Issues' section duplicates material that belongs in the existing references/common-issues.md (which is present in the bundle but never linked from the body), and two other bundle files (live-doc-lookup.md, known-model-profiles.md) are not navigable from this skill — minor organization gaps consistent with the score-4 anchor.

4 / 5

Total

18

/

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 verbatim 'Use when' triggers, and explicit negative boundaries against sibling skills. The only weakness is modest synonym coverage for triggers (no 'RHOAI', 'OpenShift AI', or 'ML environment' phrasing), which keeps trigger term quality at 4 rather than 5.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'namespace setup, S3 data connections, pipeline server, and model serving enablement' — plus labels and configuration details, giving comprehensive coverage of the skill's capabilities. It matches the anchor for multiple specific concrete actions rather than the score-4 anchor, which allows 'minor gaps in coverage'; no capability area of the skill is left out.

5 / 5

Completeness

It explicitly answers both 'what' ('Create and configure Data Science Projects on OpenShift AI with namespace setup, S3 data connections, pipeline server, and model serving enablement') and 'when' (an explicit 'Use when:' clause with five concrete trigger phrases), matching the score-5 anchor exactly. It is not a 4 because the 'when' guidance is not merely present but given as verbatim trigger phrases, and negative scope ('NOT for deploying models...') further sharpens it.

5 / 5

Trigger Term Quality

Trigger phrases are quoted user utterances ('Create a data science project', 'Set up a new namespace for ML work', 'Add an S3 data connection to my project', 'Configure the pipeline server', 'Enable model serving on my project') — natural phrasings with good coverage. It falls just short of the score-5 anchor because common synonyms are missing: no mention of 'RHOAI project', 'OpenShift AI', 'ML environment', or 'project bootstrap' wording a user might naturally say.

4 / 5

Distinctiveness Conflict Risk

A clear niche (RHOAI Data Science Project bootstrapping) with distinct triggers, reinforced by explicit deconfliction clauses: 'NOT for deploying models (use /model-deploy)', 'NOT for creating workbenches (use /workbench-manage)', 'NOT for managing pipelines after setup (use /pipeline-manage)'. This is stronger than the score-4 anchor ('minor overlap risk') since sibling-skill boundaries are explicitly disambiguated.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
RHEcosystemAppEng/agentic-plugins
Reviewed

Table of Contents

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.