CtrlK
BlogDocsLog inGet started
Tessl Logo

discover-tools

Discover available tools and resources in Databricks workspace. Use when: (1) User asks 'what tools are available', (2) Before writing agent code, (3) Looking for MCP servers, Genie spaces, UC functions, or vector search indexes, (4) User says 'discover', 'find resources', or 'what can I connect to'.

100

Quality

100%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Discovery

100%

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

This is a well-crafted skill description that clearly defines its scope (Databricks workspace resource discovery), lists specific resource types it covers, and provides explicit trigger conditions with natural user phrases. The numbered 'Use when' clause with both user utterances and contextual triggers makes it easy for Claude to select appropriately.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and resources: discovering tools, MCP servers, Genie spaces, UC functions, and vector search indexes in a Databricks workspace.

3 / 3

Completeness

Clearly answers both 'what' (discover available tools and resources in Databricks workspace) and 'when' with an explicit numbered list of trigger conditions including user phrases and contextual situations like 'before writing agent code'.

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'what tools are available', 'discover', 'find resources', 'what can I connect to', plus specific resource types like 'MCP servers', 'Genie spaces', 'UC functions', 'vector search indexes'.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: Databricks workspace resource discovery. The specific resource types (MCP servers, Genie spaces, UC functions, vector search indexes) and the discovery/inventory focus make it unlikely to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Implementation

100%

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

This is an excellent, lean skill that does exactly what it needs to: tell Claude how to discover available tools before writing agent code. It's concise, actionable with real CLI commands, well-organized with a useful reference table, and properly cross-references related skills without over-explaining. No significant weaknesses.

DimensionReasoningScore

Conciseness

Every token earns its place. No unnecessary explanations of what UC functions or vector search indexes are—assumes Claude knows these concepts. The table format is efficient for conveying resource type mappings.

3 / 3

Actionability

Provides concrete, copy-paste ready commands with clear options and flags. The MCP URL patterns in the table give specific, actionable information for constructing endpoints. Next steps point to specific skills for follow-up actions.

3 / 3

Workflow Clarity

This is a single-task skill (run discovery), and the single action is unambiguous. The workflow is clear: run discovery first, then follow next steps. The numbered next steps provide a logical sequence for what comes after discovery.

3 / 3

Progressive Disclosure

Well-structured with clear sections (Run Discovery → What Gets Discovered → Next Steps). References to other skills (modify-agent, add-tools, run-locally, create-tools) are one level deep and clearly signaled with bold skill names and descriptions of what each provides.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
databricks/app-templates
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.