Tessl • The package manager for agent skills

SkillPublic

databricks-pipelines

Develop Lakeflow Spark Declarative Pipelines (formerly Delta Live Tables) on Databricks. Use when building batch or streaming data pipelines with Python or SQL. Invoke BEFORE starting implementation.

Quality

83%

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-pipelines in databricks/databricks-agent-skills

Quality

Content

78%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 well-engineered, highly actionable skill body with excellent command coverage and explicit workflow checkpoints. Its main defects are the systematically broken reference links in the API tables, a redundant/empty 'Language-specific guides' section, and duplicated API-reference sections.

Suggestions

Fix the 18 broken 'Skill' links in the API tables: replace paths like streaming-table/streaming-table-python.md with the actual references/streaming-table-python.md locations (all target files exist under references/).

Remove or populate the empty 'Language-specific guides' section; its lone sentence ('a framework for building batch and streaming data pipelines') restates the description and adds no value.

Consolidate the 'Comprehensive API Reference' section and the end-of-doc 'Pipeline API Reference' index into one navigation section to eliminate the duplicated reference listings.

Dimension	Reasoning	Score
Conciseness	The body is dense and high-signal (decision tree, traps, API mapping tables) and assumes Claude's competence, but the empty 'Language-specific guides' section holds only a generic one-sentence product definition, and the 'Comprehensive API Reference' tables and end-of-doc 'Pipeline API Reference' index duplicate each other's role.	4 / 5
Actionability	Fully executable guidance throughout: copy-paste commands ('databricks pipelines init', 'bundle validate/deploy/run'), a complete init-config.json example, scheduling job YAML, exact API signatures, and field constraints. It stays above anchor 4 because specific examples cover the common cases end-to-end.	5 / 5
Workflow Clarity	A clear validate → deploy → run → check-status sequence with explicit checkpoints ('You must deploy before running', full refresh flagged as dangerous and requiring explicit user selection). Below anchor 5 because no failure/poll-retry feedback loop is given in the body — it is delegated to references/workflows.md.	4 / 5
Progressive Disclosure	The bundle is strong in structure — 40 real one-level-deep reference files with a grouped, annotated index — but scored against the actual bundle, all 18 'Skill' links in the API tables point to non-existent paths (e.g., streaming-table/streaming-table-python.md) instead of the real references/ locations, breaking navigation from the most-used section. This exceeds the 'minor organization gaps' of anchor 4.	3 / 5
	Total	16 / 20 Passed

Description

82%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 description that clearly and explicitly states what the skill does, when to use it, and the old-product-name synonym. The only improvement space is listing a couple more concrete capability actions and natural trigger variations.

Dimension	Reasoning	Score
Specificity	It names the domain plus one concrete action ('Develop ... Pipelines on Databricks') with modifiers (batch/streaming, Python/SQL), but does not list several specific actions as anchors 4-5 require. It is above anchor 2 because the action is stated concretely rather than generically.	3 / 5
Completeness	Explicitly answers what ('Develop Lakeflow Spark Declarative Pipelines ... on Databricks') and when ('Use when building batch or streaming data pipelines with Python or SQL'), plus invocation timing ('Invoke BEFORE starting implementation') — matching the anchor-5 pattern with concrete trigger phrases, not merely the weaker 'when' of anchor 4.	5 / 5
Trigger Term Quality	Good natural-term coverage: 'batch or streaming data pipelines', 'Python or SQL', 'Databricks', and the rename synonym '(formerly Delta Live Tables)'. Below anchor 5 because common variations like 'DLT' and 'medallion' are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche: Databricks' specific declarative pipeline product with its rename mapping, giving distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	17 / 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: 52 missing	Warning

	Total	14 / 16 Passed

Repository: databricks/devhub
Path: .databricks/aitools/skills/databricks-pipelines/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-pipelines

Table of Contents

Is this your skill?