CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-zerobus-ingest

Build Zerobus Ingest clients for near real-time data ingestion into Databricks Delta tables via gRPC. Use when creating producers that write directly to Unity Catalog tables without a message bus, working with the Zerobus Ingest SDK in Python/Java/Go/TypeScript/Rust, generating Protobuf schemas from UC tables, or implementing stream-based ingestion with ACK handling and retry logic.

66

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body is well-structured with a good workflow and decision matrix, but is weakened by verbosity/duplicated sections, a broken unfenced code block, and bundle reference files that do not exist. Tightening the prose, fixing the Common Libraries block, and supplying the missing guide files would lift it materially.

Suggestions

Repair the broken "Common Libraries" / "Smart Installation Approach" section: wrap the install logic in a properly fenced ```python block with valid syntax, and remove the duplicated context-reuse/failure-handling sections that already appear in the Workflow.

Provide the five referenced bundle files (1-setup-and-authentication.md, 2-python-client.md, 3-multilanguage-clients.md, 4-protobuf-schema.md, 5-operations-and-limits.md) so the progressive-disclosure navigation actually resolves.

Move inline time-sensitive version numbers and the GA date out of the main prose into a dedicated "Versions / Limits" section, and trim concept explanations (gRPC, at-least-once, durability ACKs) that Claude already knows.

DimensionReasoningScore

Conciseness

Mostly useful but padded with conceptual explanation ("Zerobus uses gRPC as its transport protocol..."), duplicated sections (Context Reuse Pattern, Handling Failures, Installing Libraries overlap the Workflow), inline time-sensitive versions/dates not in a deprecated section, and a garbled unfenced "Smart Installation Approach" block — below the lean score-3 bar but above purely verbose score 1.

2 / 3

Actionability

Provides a concrete minimal Python example, library versions, a decision matrix, and a specific common-issues table, but the "Common Libraries" section contains broken/unfenced non-executable code and some guidance stays abstract ("Edit the local Python file to fix the issue"), so it is not fully copy-paste ready.

2 / 3

Workflow Clarity

The numbered Workflow (steps 0-6) includes an explicit feedback loop ("If execution fails: Edit the local file to fix the error, then re-execute") and context reuse for Databricks execution, satisfying the validate/fix/retry checkpoint requirement that score 2 lacks.

3 / 3

Progressive Disclosure

There is a clear overview, a decision matrix, and a well-signaled one-level-deep guide table, but every referenced bundle file (1-setup-and-authentication.md through 5-operations-and-limits.md) is absent from the bundle, so navigation is broken — better organized than a monolithic wall (score 1) but not the complete, navigable structure of score 3.

2 / 3

Total

9

/

12

Passed

Description

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.

The description is specific, third-person, and cleanly answers both what the skill does and when to use it with an explicit "Use when" trigger clause. It is a strong, distinct description with no notable weaknesses.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "Build Zerobus Ingest clients", "creating producers that write directly to Unity Catalog tables", "generating Protobuf schemas from UC tables", "implementing stream-based ingestion with ACK handling and retry logic" — matching the score-3 anchor rather than the partial actions of score 2.

3 / 3

Completeness

Explicitly answers both what ("Build Zerobus Ingest clients for near real-time data ingestion into Databricks Delta tables via gRPC") and when via an explicit "Use when..." clause with multiple triggers, so it clears the cap that score 2 imposes when the trigger clause is missing.

3 / 3

Trigger Term Quality

Covers natural terms a user needing this would say — "near real-time data ingestion", "Databricks Delta tables", "gRPC", "Unity Catalog tables", "Protobuf schemas", "stream-based ingestion", "ACK handling and retry logic" plus five languages — giving broad coverage rather than the partial set at score 2.

3 / 3

Distinctiveness Conflict Risk

Targets a clear, named product niche (Zerobus Ingest direct-to-Delta via gRPC without a message bus) with distinct triggers unlikely to overlap with general skills, rather than the somewhat-generic score-2 case.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 17 missing, 5 suspicious

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
databricks-solutions/ai-dev-kit
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.