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.
58
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./databricks-skills/databricks-docs/SKILL.mdQuality
Discovery
75%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 well-structured with a clear 'what' and 'when' clause, and it effectively positions itself as a fallback documentation reference for Databricks topics. Its main weaknesses are moderate specificity in the actions it performs and limited trigger term coverage for the breadth of Databricks features users might ask about.
Suggestions
Add more specific concrete actions, e.g., 'Retrieves API reference details, configuration parameters, SQL syntax, and platform feature documentation from Databricks docs.'
Expand trigger terms to include common Databricks-specific keywords users might mention, such as 'Unity Catalog', 'Delta Lake', 'DBSQL', 'workspace', 'cluster configuration', 'notebook', or 'jobs API'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks documentation) and the general action (documentation reference via llms.txt index), but does not list multiple specific concrete actions like 'look up API endpoints, retrieve configuration guides, find platform feature docs'. | 2 / 3 |
Completeness | Clearly answers both 'what' (Databricks documentation reference via llms.txt index) and 'when' (when other skills don't cover a topic, looking up unfamiliar Databricks features, or needing authoritative docs on APIs/configurations/platform capabilities) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Databricks', 'APIs', 'configurations', 'platform capabilities', and 'docs', but misses common user variations like 'Databricks SQL', 'Unity Catalog', 'Delta Lake', 'workspace settings', or specific feature names users might naturally mention. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche as a Databricks-specific documentation fallback skill, and the 'Use when other skills do not cover a topic' clause positions it as a secondary reference, reducing conflict with more specific Databricks skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably well-structured reference skill that clearly communicates its purpose and relationship to other skills. Its main weaknesses are the lack of concrete, executable examples (e.g., an actual WebFetch invocation or a demonstration of parsing the llms.txt output) and some mild verbosity in explaining its role. The progressive disclosure and cross-referencing to related skills are strong points.
Suggestions
Add a concrete, executable example showing the actual WebFetch tool invocation to retrieve llms.txt and how to parse/search the result (e.g., a specific tool call with expected output format).
Trim the 'Role of This Skill' section—the bullet list largely restates what 'reference resource' means, which Claude already understands. Merge the key point ('prefer MCP tools for actions') into the intro paragraph.
In the 'How to Use' section, replace the vague 'search for relevant sections/links' with a concrete example showing how to find a specific topic in the llms.txt index (e.g., searching for 'Delta Live Tables' and what the matching entry looks like).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some unnecessary explanation (e.g., 'This is a reference skill, not an action skill' and the bullet list restating what a reference is). The 'Role of This Skill' section is somewhat redundant with the intro. However, it's not egregiously verbose—most sections are reasonably tight. | 2 / 3 |
Actionability | It provides a concrete URL and mentions using WebFetch, but lacks executable examples (no actual fetch command, no code snippet showing how to parse or search the llms.txt content). The guidance is directional rather than copy-paste ready—steps like 'search for relevant sections/links' are vague. | 2 / 3 |
Workflow Clarity | The two example scenarios provide a reasonable sequence of steps, but they are high-level and lack validation checkpoints or error handling. The 'How to Use' section has a 3-step process but it's generic ('search for relevant sections' is not a concrete step). For a reference skill this is adequate but not exemplary. | 2 / 3 |
Progressive Disclosure | The skill is well-organized with clear sections, provides a concise overview, and has well-signaled one-level-deep references to related skills. The documentation structure section serves as a useful navigation guide. For a skill with no bundle files, this is appropriately structured. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- databricks-solutions/ai-dev-kit
- Commit
93cb4e3
- 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.