rill-explore

Detailed instructions and examples for developing explore dashboard resources in Rill

0.98x

Quality

50%

Does it follow best practices?

Impact

81%

0.98x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/rill-explore/SKILL.md

Quality

Content

50%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 content provides strong, executable YAML examples but is hurt by an inlined ~130-line JSON schema that should live in a reference file, by some over-explanation of concepts Claude already knows, and by the absence of any validation/verification step in the development workflow.

Suggestions

Move the full JSON schema block into a ./references/explore-schema.yaml (or .json) file and link to it with a single 'See references/explore-schema.yaml for the full schema' line, keeping only the key examples inline.

Trim concept exposition Claude already knows (e.g. the 'explore dashboards are resources that configure...' and 'reconcile logic is fast (validation only)' sentences) to leaner statements.

Add an explicit validation checkpoint to the workflow, e.g. 'After editing, run `rill project reconcile` and confirm the explore resource validates with no errors before considering the change done.'

Dimension	Reasoning	Score
Conciseness	The body explains concepts Claude can infer (what an explore dashboard is, that reconciliation is 'fast (validation only)', the 'when to use explores vs canvases' comparison) and inlines a ~130-line JSON schema block that is pure reference padding, making it noticeably verbose despite some efficient annotated examples.	2 / 5
Actionability	Multiple concrete, copy-pasteable YAML examples (inline explore, annotated full example, minimal example) cover the common cases with real property values like 'P30D', 'comparison_mode: time', and field-selector forms, with only minor gaps around validation of the resulting resource.	4 / 5
Workflow Clarity	The 'Development approach' section lists a rough 3-step sequence (reference metrics view, select dimensions/measures, optionally configure defaults) but there are no validation checkpoints, and the guideline capping destructive/batch-config skills without validation at 3 applies since edits to project resources are applied in batch via reconcile with no verify step shown.	3 / 5
Progressive Disclosure	No bundle files exist (no references/scripts/assets dirs), yet a large JSON schema reference is inlined directly in the body — content that clearly belongs in a separate reference file — with only thin section headers and no signaled one-level-deep reference links, matching the 'content that clearly belongs in separate files is inlined' anchor.	2 / 5
	Total	11 / 20 Passed

Description

51%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 is third-person and clearly names the Rill explore-dashboard domain, but it lacks any 'Use when...' trigger guidance and its action vocabulary is generic. It is decent but well below the strong examples which pair concrete actions with explicit trigger phrases.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating or editing Rill explore dashboards, configuring metrics-view dimensions/measures, or when the user mentions Rill dashboards.'

Replace the generic verb 'developing' with concrete actions: 'Configure Rill explore dashboards: select dimensions and measures, set time ranges, defaults, and security policies.'

Include common natural terms users say ('Rill dashboard', 'metrics view', 'slice-and-dice') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('explore dashboard resources in Rill') and the actions 'developing' and 'examples', but actions are generic with only two verbs and no enumeration of concrete capabilities like configuring dimensions, measures, time ranges, or security.	3 / 5
Completeness	It has a clear 'what' (developing explore dashboard resources in Rill with instructions and examples) but no 'when'/'Use when' clause at all, so per the missing-trigger-guidance rule completeness is capped at 3.	3 / 5
Trigger Term Quality	'explore dashboard resources in Rill' captures the core noun but misses the natural phrases a user would say (e.g. 'Rill dashboard', 'metrics view', 'slice and dice') and any file-extension or resource-type triggers; coverage is relevant but incomplete.	3 / 5
Distinctiveness Conflict Risk	The Rill-specific 'explore dashboard resources' niche is fairly distinct and unlikely to fire for unrelated skills, with only minor overlap risk against a hypothetical canvas/dashboard skill in the same tool.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rilldata/agent-skills
Path: skills/rill-explore/SKILL.md
Commit: 84f7d7c

Reviewed: about 7 hours ago

Table of Contents

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.