rill-explore
Detailed instructions and examples for developing explore dashboard resources in Rill
61
40%
Does it follow best practices?
Impact
100%
1.29xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/rill-explore/SKILL.mdQuality
Discovery
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 both concrete actions and explicit trigger guidance. While it mentions the specific tool (Rill) and resource type (explore dashboards), it fails to enumerate what specific tasks it covers and when Claude should select it. It reads more like a section heading than a functional skill description.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about creating or configuring explore dashboards in Rill, including YAML configuration, metrics, dimensions, or dashboard layout.'
List specific concrete actions the skill covers, e.g., 'Configures explore dashboard YAML resources, defines time dimensions, sets up metrics and dimension selectors, customizes dashboard themes and security policies.'
Include natural keyword variations users might say, such as 'Rill dashboard', 'explore YAML', 'dashboard config', 'rill developer', '.yaml dashboard file'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'detailed instructions and examples for developing explore dashboard resources' but does not list any concrete actions. 'Developing' is vague and no specific operations (e.g., creating charts, configuring metrics, defining dimensions) are mentioned. | 1 / 3 |
Completeness | The description weakly addresses 'what' (developing explore dashboard resources) but completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also vague, so this scores a 1. | 1 / 3 |
Trigger Term Quality | It includes 'explore dashboard' and 'Rill' which are relevant domain-specific keywords a user might mention. However, it lacks common variations or natural phrases users might say (e.g., 'dashboard layout', 'metrics explorer', 'YAML config', 'rill.yaml'). | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Rill' and 'explore dashboard resources' provides some specificity that distinguishes it from generic dashboard skills, but it could still overlap with other Rill-related skills (e.g., modeling, metrics definitions) since 'developing' is broad. | 2 / 3 |
Total | 6 / 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.
The skill provides strong actionable examples with well-annotated YAML configurations that Claude can directly use. However, it suffers from poor progressive disclosure by inlining a large JSON schema that should be in a separate reference file, and the workflow lacks validation checkpoints for verifying that created explore dashboards are correct. Some introductory content explains concepts that are better left implicit.
Suggestions
Move the full JSON schema to a separate SCHEMA.md or REFERENCE.md file and replace it with a brief link, keeping only the most essential properties summarized inline.
Add validation steps to the workflow, such as how to verify the explore dashboard renders correctly and common error patterns (e.g., referencing non-existent metrics views or dimensions).
Remove or condense the introductory paragraphs about what explore dashboards are and their reconcile logic—Claude doesn't need this background context to create them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary explanations (e.g., the introduction explaining what explore dashboards are and their reconcile logic, the 'when to use explores vs canvases' section). The full JSON schema at the end is very lengthy and could be referenced externally. However, the examples and core guidance are reasonably tight. | 2 / 3 |
Actionability | The skill 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 give Claude everything needed to produce working explore dashboards. | 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 (e.g., referencing non-existent dimensions or measures). | 2 / 3 |
Progressive Disclosure | The full JSON schema (~100 lines) is inlined directly in the SKILL.md rather than being placed in a separate reference file. This creates a monolithic document where reference material dominates the content. The schema should be in a separate REFERENCE.md or SCHEMA.md file with a clear link from the main skill. | 1 / 3 |
Total | 8 / 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
- rilldata/agent-skills
- Commit
65ccd1f
- 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.