Tessl • The package manager for agent skills

SkillPublic

databricks-docs

Databricks documentation reference via llms.txt index. Use when other skills do not cover a topic, looking up unfamiliar Databricks features, or needing authoritative docs on APIs, configurations, or platform capabilities.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.databricks/aitools/skills/databricks-docs/SKILL.md

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

Quality

Content

75%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 a lean, well-structured overview that gives concrete retrieval guidance and clear lookup sequences appropriate for a single-purpose reference skill. It is held back from top marks only by minor trim opportunities, a missing concrete fetch example, and light error-handling guidance.

Suggestions

Add a copy-paste-ready WebFetch example for the llms.txt URL so the core action is fully executable.

Include a brief fallback note for when a topic is not found in the index or a page fetch fails.

Tighten the 'Role of This Skill' section so the reference-vs-action framing is stated once instead of repeated.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and does not over-explain concepts Claude already knows, but the 'Role of This Skill' section restates the reference-vs-action framing multiple times, leaving minor trim opportunities.	4 / 5
Actionability	Gives a concrete URL, names the tool (WebFetch), and provides a 3-step lookup process plus a real CLI example ("databricks pipelines create"); a concrete WebFetch invocation example would close the remaining gap.	4 / 5
Workflow Clarity	The fetch-index -> search -> fetch-pages -> apply sequence is clear and unambiguous for this read-only lookup skill, with minor gaps around what to do when a section is absent or a fetch fails.	4 / 5
Progressive Disclosure	Well-organized overview with clearly signaled one-level-deep links to sibling skills; the body is appropriately self-contained, though the bundled image assets are not referenced from the body.	4 / 5
	Total	16 / 20 Passed

Description

78%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 clearly and explicitly answers both what the skill does and when to use it, with strong trigger phrasing and good distinctiveness as a fallback reference. It is slightly weaker on specificity, since the concrete action reduces to a single lookup verb across several contexts.

Suggestions

Broaden specificity beyond a single lookup verb by naming a couple of concrete retrieval actions (e.g., 'search the docs index, fetch specific pages, cross-reference API/config details').

Add one or two natural synonyms or user-style phrasings (e.g., 'Databricks docs', 'look up Databricks APIs') to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and mechanism ("Databricks documentation reference via llms.txt index") plus 1-2 action types ("looking up unfamiliar Databricks features", "needing authoritative docs"), but the underlying action is a single lookup/reference verb applied to varied contexts rather than a comprehensive set of concrete actions.	3 / 5
Completeness	Explicitly states what ("Databricks documentation reference via llms.txt index") and when with concrete trigger phrases ("Use when other skills do not cover a topic, looking up unfamiliar Databricks features, or needing authoritative docs...").	5 / 5
Trigger Term Quality	Includes natural terms a user would say ("Databricks features", "authoritative docs on APIs, configurations, or platform capabilities") with good coverage; a few synonyms or file/extension-style variants are missing, and "llms.txt index" is technical jargon.	4 / 5
Distinctiveness Conflict Risk	Has a clear reference/fallback niche signaled by "Use when other skills do not cover a topic", but retains minor overlap risk with the broader databricks skill family.	4 / 5
	Total	16 / 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-docs/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-docs

Table of Contents

Is this your skill?