Tessl • The package manager for agent skills

SkillPublic

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

Quality

87%

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

The canonical home for this skill is databricks-iceberg in databricks/databricks-agent-skills

Quality

Content

80%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.

A high-quality reference skill body: executable SQL, strong progressive disclosure, and efficient structure. Its main gap is the absence of validation checkpoints for the irreversible UniForm/CLUSTER BY table-property operations, which limits workflow clarity.

Suggestions

Add explicit validation checkpoints to the UniForm-enable and CLUSTER BY workflows (e.g., 'After ALTER TABLE, run DESCRIBE EXTENDED to confirm universalFormat.enabledFormats and Iceberg metadata generation before proceeding').

Tighten the long MUST bullet contrasting PARTITIONED BY vs CLUSTER BY into a short table or bulleted sub-points so the two syntax differences read at a glance.

Surface a brief 'verify reader compatibility before switching compression codec / format-version' step in the Common Issues entries that involve irreversible format changes.

Dimension	Reasoning	Score
Conciseness	Mostly lean and well-organized with tables, tight MUST/MUST NOT rules, and executable SQL, assuming Claude's prior knowledge; the long run-on critical-rule bullet contrasting PARTITIONED BY vs CLUSTER BY could be tightened to earn the top score.	4 / 5
Actionability	Provides copy-paste-ready, executable SQL across the common cases (managed Iceberg with PARTITIONED BY and CLUSTER BY on v2/v3, plus UniForm ALTER TABLE TBLPROPERTIES) alongside a capability matrix and a When-to-Use routing table.	5 / 5
Workflow Clarity	Routing via 'When to Use' and MUST/MUST NOT guardrails gives a clear decision sequence, but the destructive/irreversible table-property workflows (enabling UniForm, disabling deletion vectors, CLUSTER BY changes) lack explicit validate-then-proceed checkpoints, which caps this dimension per the batch/destructive guideline.	3 / 5
Progressive Disclosure	Serves as a concise overview pointing to five well-signaled, one-level-deep reference files through both a Reference Files table and a When-to-Use routing table; all referenced paths verified to exist and content is appropriately split.	5 / 5
	Total	17 / 20 Passed

Description

92%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, capability-dense description that explicitly pairs a comprehensive 'what' with concrete 'when' triggers and occupies a distinct niche. It is slightly jargon-heavy for a lay audience, which keeps trigger-term quality just short of exemplary.

Dimension	Reasoning	Score
Specificity	Enumerates comprehensive 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 anchor for multiple specific concrete actions with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (the feature list) and 'when' via a concrete 'Use when creating Iceberg tables, enabling External Iceberg Reads... configuring external engines... integrating with Snowflake' clause with specific trigger phrases.	5 / 5
Trigger Term Quality	Good natural-keyword coverage including synonyms ('Iceberg tables', 'UniForm'/'External Iceberg Reads', 'Snowflake', 'PyIceberg', 'Delta tables', 'Streaming Tables', 'Materialized Views'), but leans technical and lacks casual synonyms or file-extension-style triggers a less expert user might say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrowly scoped Iceberg-on-Databricks niche with Iceberg-specific triggers; the only mild overlap is the Unity Catalog mention, which is subordinate to the Iceberg framing and poses minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: databricks/devhub
Path: .databricks/aitools/skills/databricks-iceberg/SKILL.md
Revision: 2bc4d86

Reviewed: 19 days ago

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.

databricks-iceberg

Table of Contents

Is this your skill?