CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-iceberg

Apache Iceberg tables on Databricks — Managed Iceberg tables, External Iceberg Reads (fka Uniform), Compatibility Mode, Iceberg REST Catalog (IRC), Iceberg v3, Snowflake interop, PyIceberg, OSS Spark, external engine access and credential vending. Use when creating Iceberg tables, enabling External Iceberg Reads (uniform) on Delta tables (including Streaming Tables and Materialized Views via compatibility mode), configuring external engines to read Databricks tables via Unity Catalog IRC, integrating with Snowflake catalog to read Foreign Iceberg tables

68

Quality

82%

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

65%

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

A dense, actionable reference body with excellent executable SQL and a strong decision-routing structure. It is held back by verbosity in one long rule bullet, missing validation checkpoints for destructive DDL operations, and five referenced bundle files that are not actually present in the skill bundle.

Suggestions

Ship the five referenced files (1-managed-iceberg-tables.md ... 5-external-engine-interop.md) in references/, or remove the dangling links — the progressive-disclosure promise currently resolves to nothing.

Add a validation/verification checkpoint to the UniForm and CREATE TABLE flows (e.g., confirm 'delta.universalFormat.enabledFormats' = 'iceberg' and check Iceberg metadata via DESCRIBE EXTENDED before declaring success), since enabling UniForm and disabling deletion vectors are destructive/irreversible-ish operations.

Split the oversized PARTITIONED BY vs CLUSTER BY rule bullet into a short rule plus a compact two-row comparison table to remove the embedded parenthetical padding.

DimensionReasoningScore

Conciseness

Mostly efficient — critical rules, concept table, executable SQL, and a capability matrix all earn their place — but the PARTITIONED BY/CLUSTER BY rule bullet is a long padded run-on with embedded parentheticals that could be split and tightened; not level 3 because not every token earns its place.

2 / 3

Actionability

Provides fully executable, copy-paste-ready SQL in three CREATE TABLE variants and an ALTER TABLE SET TBLPROPERTIES block, plus concrete values ('delta.enableDeletionVectors' = false, 'Iceberg library 1.9.0+'); not level 2 because the guidance is complete and executable rather than pseudocode.

3 / 3

Workflow Clarity

A 'When to Use' router and 'Critical Rules' preflight checks give a usable sequence, but the DDL/UniForm operations (enabling UniForm, disabling deletion vectors) are potentially destructive and lack explicit validate->fix->retry checkpoints; capped at 2 per the destructive-operations guideline.

2 / 3

Progressive Disclosure

Structure and signaling are excellent (Reference Files table + When-to-Use routing, one level deep), but the five referenced bundle files (1-managed-iceberg-tables.md through 5-external-engine-interop.md) do not exist in references/, scripts/, or assets/, so the navigation points to missing files; not level 1 because the SKILL.md overview itself is well organized, but the dangling references keep it from a clean 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.

A strong, specific description that names concrete capabilities and provides an explicit 'Use when...' trigger clause covering the main Iceberg-on-Databricks scenarios. It is comprehensive and well-scoped with low conflict risk.

DimensionReasoningScore

Specificity

Names many concrete capabilities — 'Managed Iceberg tables, External Iceberg Reads (fka Uniform), Compatibility Mode, Iceberg REST Catalog (IRC), Iceberg v3, Snowflake interop, PyIceberg, OSS Spark, external engine access and credential vending' — matching the 'lists multiple specific concrete actions' anchor; not level 2 because coverage is comprehensive rather than partial.

3 / 3

Completeness

Explicitly answers both what (the feature list) and when via an explicit 'Use when creating Iceberg tables, enabling External Iceberg Reads... configuring external engines... integrating with Snowflake catalog' clause; not level 2 because the trigger guidance is explicit, not implied.

3 / 3

Trigger Term Quality

Includes natural terms a user would say — 'creating Iceberg tables,' 'enabling External Iceberg Reads (uniform),' 'Delta tables,' 'Streaming Tables and Materialized Views,' 'configuring external engines,' 'Snowflake catalog' — giving good coverage; not level 2 because common variations are well represented.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (Apache Iceberg on Databricks) with distinct triggers unlikely to fire for unrelated skills; not level 2 because the scope is tightly bounded to a specific product surface.

3 / 3

Total

12

/

12

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

relative_links

Relative link issues: 12 missing, 4 suspicious

Warning

Total

15

/

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.