CtrlK
BlogDocsLog inGet started
Tessl Logo

rill-explore

Detailed instructions and examples for developing explore dashboard resources in Rill

75

1.29x
Quality

Does it follow best practices?

Impact

100%

1.29x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is well-structured and highly actionable with strong concrete YAML examples, but it keeps a large reference schema inline and lacks validation checkpoints in its workflow. Splitting the schema into a referenced file and adding a verification step would improve it.

Suggestions

Move the full JSON schema into a separate reference file (e.g. references/explore-schema.yaml) and link to it from a short 'Reference documentation' section to improve progressive disclosure.

Add an explicit validation/verification checkpoint to the Development approach, such as confirming the explore renders against its metrics view before considering it done.

Trim the introductory sentences that restate what an explore dashboard is, since that concept is already known, to tighten conciseness.

DimensionReasoningScore

Conciseness

The guidance sections are lean and actionable, but roughly the last 135 lines are a raw JSON schema dump inline, which is verbose reference material that could be tightened or moved to a separate file rather than earning every token its place.

2 / 3

Actionability

It provides concrete, copy-paste-ready YAML examples (minimal and fully annotated) with explicit property names and values, giving fully executable guidance rather than vague direction.

3 / 3

Workflow Clarity

The Development approach gives a clear 1-2-3 sequence, but there are no validation or verification checkpoints (e.g. confirming the explore renders), so checkpoints remain implicit despite the sequence being present.

2 / 3

Progressive Disclosure

Sections are reasonably organized and signaled, but no bundle files exist and the large JSON schema is inline content that would be better split into a separate reference file, matching the 'API reference that could be in a separate file' anchor.

2 / 3

Total

9

/

12

Passed

Description

57%

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 specific to a clear niche and names a concrete action, but it omits any explicit use-when trigger guidance and under-covers the natural terms a user would actually say. Adding a trigger clause and broader keywords would round it out.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when building or modifying Rill explore dashboards or when the user mentions Rill dashboards, metrics views, or drill-down analysis.'

Broaden trigger terms to include natural variations users would say, such as 'dashboard', 'metrics view', 'drill-down', and 'slice-and-dice analysis'.

Enumerate concrete actions (e.g. configuring dimensions/measures, time ranges, defaults, and security) to lift specificity from one named action to multiple specific actions.

DimensionReasoningScore

Specificity

It names a concrete domain ("explore dashboard resources in Rill") and the action "developing", but does not list multiple distinct concrete actions, so it sits at the names-domain-and-some-actions level rather than the multiple-specific-actions level.

2 / 3

Completeness

It states what the skill does (developing explore dashboards with instructions and examples) but provides no "Use when..." trigger guidance, so the when half is missing and completeness is capped at 2.

2 / 3

Trigger Term Quality

Relevant terms like "explore dashboard" and "Rill" appear, but common user variations ("dashboard", "metrics view", "drill-down", "slice-and-dice") are absent, leaving some relevant keywords without full coverage.

2 / 3

Distinctiveness Conflict Risk

Tied to a named tool (Rill) and a specific dashboard type, it occupies a clear niche with distinct triggers and is unlikely to fire for unrelated skills.

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.

Validation16 / 16 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.