Name: add-tools
Rating: 64 (1 reviews)
Author: databricks

add-tools

Add tools to your agent and grant required permissions in databricks.yml. Use when: (1) Adding MCP servers, Genie spaces, vector search, or UC functions to agent, (2) Permission errors at runtime, (3) User says 'add tool', 'connect to', 'grant permission', (4) Configuring databricks.yml resources.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./agent-migration-from-model-serving/.claude/skills/add-tools-openai/SKILL.md

Quality

Content

62%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.

Executable and well-structured content with concrete code, but it is undermined by a missing examples/ bundle that several sections point to, and the deploy workflow lacks validation checkpoints despite permission errors being the core failure mode.

Suggestions

Create the referenced examples/ directory with the ten listed YAML/MD files, or remove the references and inline the essential snippets directly in SKILL.md.

Add an explicit validation/verify step after 'databricks bundle deploy' (e.g. confirm the app has CAN_RUN/CAN_USE on the resource and retry on permission errors) to introduce a feedback loop.

Replace the time-sensitive 'Databricks CLI v0.298.0+' version note with a deprecation-style pointer or move it to a versioned reference file so it does not penalize conciseness as it ages.

Dimension	Reasoning	Score
Conciseness	Lean, assumes Claude's competence and avoids explaining basic concepts; the only mild over-explanation is restating that MLflow is already configured and the profile reminder, which are useful but borderline.	4 / 5
Actionability	Fully executable copy-paste-ready Python and YAML snippets cover the common cases (MCP server, databricks.yml grant, custom MCP app, timeout config), with specific commands and field values.	5 / 5
Workflow Clarity	A clear 3-step sequence exists but it lacks validation checkpoints — there is no verify-after-deploy step and no feedback loop for the common permission-error failure mode, capping clarity at 3 per the destructive/batch cap.	3 / 5
Progressive Disclosure	The body references an 'examples/' directory and a table of ten example files, but no examples/ directory or any bundle files exist in the skill — the references point to missing files, breaking navigation.	2 / 5
	Total	14 / 20 Passed

Description

88%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, specific description that clearly states both the action and a multi-part 'Use when' trigger list. It is largely distinguishable from sibling skills, with only minor overlap risk from the generic permission-error trigger.

Suggestions

Narrow the 'Permission errors at runtime' trigger to Databricks-specific permission errors to reduce overlap with sibling skills.

Add a couple of natural-language synonyms (e.g. 'wire up', 'register a tool') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Add tools to your agent and grant required permissions in databricks.yml' — with comprehensive coverage of the resource types (MCP servers, Genie spaces, vector search, UC functions).	5 / 5
Completeness	Explicitly answers both what ('Add tools to your agent and grant required permissions in databricks.yml') and when (a four-item 'Use when' list with concrete trigger phrases).	5 / 5
Trigger Term Quality	Strong natural triggers including 'add tool', 'connect to', 'grant permission', plus concrete resource names, but missing common synonyms/variations a user might say beyond these enumerated phrases.	4 / 5
Distinctiveness Conflict Risk	Clear niche around Databricks agent tooling with distinct triggers, but the broad 'permission errors at runtime' clause creates minor overlap risk with a sibling deploy/create-tools skill.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks/app-templates
Path: agent-migration-from-model-serving/.claude/skills/add-tools-openai/SKILL.md
Commit: fdc1b49

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.