CtrlK
BlogDocsLog inGet started
Tessl Logo

rill-explore

Detailed instructions and examples for developing explore dashboard resources in Rill

64

1.29x
Quality

43%

Does it follow best practices?

Impact

100%

1.29x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/rill-explore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

64%

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

This skill provides solid, actionable YAML examples for creating explore dashboards in Rill, with good progression from minimal to full configurations. Its main weaknesses are the inlined JSON schema bloating the token budget, some unnecessary explanatory content that Claude wouldn't need, and the absence of validation/verification steps after creating or modifying an explore dashboard.

Suggestions

Move the full JSON schema to a separate REFERENCE.md file and link to it, keeping only the annotated example in the main skill body.

Add a validation step after creating an explore (e.g., how to verify the dashboard renders correctly or how to check for configuration errors).

Remove the 'When to use explores vs canvases' section and the introductory paragraph about DAG positioning — Claude can infer these from context.

DimensionReasoningScore

Conciseness

The content includes some unnecessary explanations (e.g., 'Explore dashboards are lightweight resources that sit downstream of a metrics view in the project DAG' and the 'When to use explores vs canvases' section) and the full JSON schema at the end is very verbose. However, the core examples and instructions are reasonably efficient.

2 / 3

Actionability

Provides fully executable YAML examples that are copy-paste ready, including a minimal example, an annotated full example, and an inline explore example. The concrete configurations with real property names and values make this highly actionable.

3 / 3

Workflow Clarity

The development approach section outlines steps but lacks explicit validation checkpoints. There's no guidance on how to verify the explore dashboard works correctly after creation, no error recovery steps, and no feedback loop for catching misconfigurations.

2 / 3

Progressive Disclosure

The content is reasonably structured with sections progressing from simple to complex, but the full JSON schema (~100 lines) is inlined rather than referenced as a separate file. The document would benefit from moving the schema reference to a separate file and keeping only the annotated example inline.

2 / 3

Total

9

/

12

Passed

Description

22%

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 too vague and lacks concrete actions, explicit trigger guidance, and natural user keywords. It reads more like a section heading than a functional skill description. The mention of 'Rill' and 'explore dashboard' provides some domain specificity but is insufficient for reliable skill selection.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about creating or configuring explore dashboards in Rill, defining metrics, dimensions, or measures in Rill YAML files.'

List specific concrete actions the skill covers, e.g., 'Defines explore dashboard YAML configurations, sets up dimensions and measures, configures time grains, and creates security policies for Rill dashboards.'

Include natural trigger terms users would say, such as 'Rill dashboard', 'explore YAML', 'metrics dashboard', 'dimensions', 'measures', '.yaml config'.

DimensionReasoningScore

Specificity

The description says 'detailed instructions and examples for developing explore dashboard resources' but does not list any concrete actions. It vaguely references 'developing' without specifying what that entails (e.g., creating, configuring, deploying, querying).

1 / 3

Completeness

The description partially addresses 'what' (developing explore dashboard resources) but is vague, and there is no 'Use when...' clause or equivalent explicit trigger guidance. Per the rubric, a missing 'Use when' clause caps completeness at 2, and the weak 'what' brings it down to 1.

1 / 3

Trigger Term Quality

It includes some relevant keywords like 'explore dashboard', 'Rill', and 'resources', which a user working with Rill might mention. However, it misses common variations and natural terms users might say (e.g., 'metrics', 'YAML config', 'dimensions', 'measures', 'rill.yaml', 'dashboard creation').

2 / 3

Distinctiveness Conflict Risk

The mention of 'Rill' and 'explore dashboard resources' provides some specificity, but 'developing resources' is generic enough that it could overlap with other Rill-related skills or general dashboard skills.

2 / 3

Total

6

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
rilldata/agent-skills
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.