rill-metrics-view

Detailed instructions and examples for developing metrics view resources in Rill

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/rill-metrics-view/SKILL.md

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 skill is highly actionable with concrete, executable YAML examples and good dialect coverage, but it is held back by a large inline JSON schema dump that inflates tokens and by the absence of a sequenced, validated workflow and any progressive disclosure to separate reference files.

Suggestions

Move the full JSON schema dump into a separate REFERENCE.md and link to it from the body, keeping only the most-used fields inline to cut tokens and improve progressive disclosure.

Add a short numbered "Developing a metrics view" workflow with a validation checkpoint (e.g., create the YAML in metrics/, run `rill start`, confirm the auto-generated explore appears) to raise workflow clarity.

Trim redundancy between the prose explanations and the schema section so each property is documented once in the most useful form.

Dimension	Reasoning	Score
Conciseness	The instructional prose is lean and conveys Rill-specific syntax Claude would not already know, but the ~315-line raw JSON schema dump at the end largely duplicates the prose sections (dimensions, measures, cache, rollups, security) and is padded context that could be trimmed; this sits above 1 because the core teaching content earns its tokens.	2 / 3
Actionability	The body provides numerous copy-paste-ready, executable YAML snippets plus a complete annotated metrics view and dialect-specific examples (DuckDB FILTER, ClickHouse countIf, Druid APPROX_COUNT_DISTINCT), matching the fully-executable anchor.	3 / 3
Workflow Clarity	Sections are well organized (concepts, examples, advanced, dialects) but there is no sequenced develop workflow with validation checkpoints for building a metrics view; the only operational note ("Rill will ingest... next time you run rill start") is buried, so it is below 3 and above 1 because structure is present.	2 / 3
Progressive Disclosure	No bundle files exist and all content lives inline in one file; the large JSON schema reference is content that should be split into a separate reference file, but the body is organized into clear sections rather than being a poorly organized monolith, placing it at 2 rather than 1.	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 clearly identifies its Rill-specific niche and avoids conflict risk, but it is weak on concrete actions, trigger variations, and lacks an explicit use-when clause. It reads as a content summary rather than a capability-and-trigger statement.

Suggestions

Add a concrete action list, e.g. "Define dimensions, measures, timeseries, security policies, and rollups for Rill metrics view YAML files" instead of the abstract "developing".

Append an explicit trigger clause such as "Use when creating or editing Rill metrics views (.yaml), or when the user mentions Rill dashboards, measures, dimensions, or a semantic/metrics layer."

Include natural keyword variations (dashboards, measures, dimensions, semantic layer) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase "developing metrics view resources in Rill" names the domain concretely but the only action ("developing") is abstract and singular, matching the anchor that names a domain and some actions without being comprehensive; it is above 1 because the domain is clearly specified rather than vague.	2 / 3
Completeness	It states what the skill provides ("instructions and examples for developing metrics view resources") but gives no "Use when..." or equivalent trigger for when Claude should use it; per the judging guidelines a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	"metrics view" and "Rill" are natural terms a user would say, but the description omits common variations users also use (dashboards, measures, dimensions, semantic/metrics layer), so it has some relevant keywords but incomplete coverage.	2 / 3
Distinctiveness Conflict Risk	The description is tightly scoped to Rill metrics view resources, a clear niche with distinct triggers that is unlikely to fire for unrelated skills.	3 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (762 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 5 suspicious	Warning

	Total	14 / 16 Passed

Repository: rilldata/agent-skills
Path: skills/rill-metrics-view/SKILL.md
Commit: aa23a8e

Reviewed: 1 day 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.