CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-agent-bricks

Create Agent Bricks: Knowledge Assistants (KA) for document Q&A and Supervisor Agents for multi-agent orchestration (MAS).

65

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.databricks/aitools/skills/databricks-agent-bricks/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

93%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.

The body is an exemplary lean, actionable reference — copy-paste commands with concrete payloads and well-organized one-level references — with only minor gaps in explicit feedback loops for batch provisioning.

DimensionReasoningScore

Conciseness

Lean and token-efficient — almost entirely executable commands, tables, and task-specific gotchas with no padding or explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

Fully executable, copy-paste-ready bash with concrete JSON payloads, a tool-type mapping table, and jq filters covering the common KA and Supervisor flows.

5 / 5

Workflow Clarity

Clear sequences with status checks and an explicit endpoint-readiness gate, but no explicit validate→fix→retry feedback loop for the sync/provisioning steps, so it sits just below a 5.

4 / 5

Progressive Disclosure

Body is a concise overview with a Reference table pointing to two real, one-level-deep reference files, both clearly signaled and easy to navigate.

5 / 5

Total

19

/

20

Passed

Description

65%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.

The description is specific and distinctive, naming two concrete Agent Bricks capabilities in third person, but it lacks any explicit 'Use when...' trigger guidance, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when creating Agent Bricks, Knowledge Assistants for document Q&A, or Supervisor Agents for multi-agent orchestration in Databricks.'

Include common synonyms/variations (e.g. 'RAG assistant', 'multi-agent system', 'MAS') to broaden trigger-term coverage toward a 5.

DimensionReasoningScore

Specificity

Names the domain (Agent Bricks) and two concrete capabilities — 'Knowledge Assistants (KA) for document Q&A' and 'Supervisor Agents for multi-agent orchestration' — matching the 1-2 concrete actions anchor; not a 4 because only two actions with no finer-grained sub-tasks.

3 / 5

Completeness

Has a clear 'what' but no 'Use when...' clause; per the guidelines a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Good coverage of natural product terms a user would say ('Agent Bricks', 'Knowledge Assistants', 'document Q&A', 'Supervisor Agents', 'multi-agent orchestration'); not a 5 because common synonyms and lay variations are absent.

4 / 5

Distinctiveness Conflict Risk

Distinctive Databricks product names (Agent Bricks, Knowledge Assistants, Supervisor Agents) carve a clear niche with minimal conflict risk against other skills.

5 / 5

Total

15

/

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.

Validation15 / 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
databricks/devhub
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.