rill-metrics-view

Detailed instructions and examples for developing metrics view resources in Rill

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The content is highly actionable with concrete, copy-paste-ready YAML and a well-organized reference structure. Its main weaknesses are a large inline JSON schema dump that hurts conciseness and the absence of any bundle files to split out reference material for progressive disclosure.

Suggestions

Move the verbatim JSON schema into a separate references file (e.g., references/schema.md) and link to it from a short 'Reference documentation' section to improve both conciseness and progressive disclosure.

Consider extracting dialect-specific notes (DuckDB/ClickHouse/Druid) into a references/dialects.md file with a clear pointer from the main body.

Trim the prose around the schema block, which currently adds little beyond what the schema itself states.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tight YAML examples, but it embeds a ~300-line raw JSON schema verbatim under 'Reference documentation', which is padded reference material that inflates token usage; matches 'mostly efficient but includes some unnecessary explanation or could be tightened'; not a 3 due to the schema dump, not a 1 because the prose itself is lean.	2 / 3
Actionability	Throughout the body, concrete copy-paste-ready YAML examples with real property names (e.g., `model: events`, `expression: SUM(order_total) / NULLIF(COUNT(*), 0)`, `cache: { enabled: true, key_ttl: 5m }`) provide fully executable guidance, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	For a reference/config-authoring skill, sections are well-sequenced (source -> timeseries -> dimensions -> measures -> security -> advanced) with a complete annotated full example; the single action of authoring a metrics view YAML is unambiguous, so per the simple-skill note workflow clarity can score 3 without multi-step validation checkpoints.	3 / 3
Progressive Disclosure	No bundle files (references/scripts/assets) exist and the entire content lives inline in one file, including the large JSON schema and dialect notes that could be split into separate reference files; matches 'some structure but content that should be separate is inline'; not a 3 because there is no one-level-deep external reference split, not a 1 because sections are reasonably organized.	2 / 3
	Total	10 / 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 a product-specific niche but lacks an explicit 'Use when' trigger and stops short of listing concrete capabilities. Adding trigger terms and a use-when clause would raise completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g., 'Use when building or editing metrics views (semantic layer) in a Rill project, or when the user asks about Rill dashboards, measures, or dimensions.'

Enumerate concrete actions to boost specificity, e.g., 'Define dimensions, measures, security policies, and timeseries for Rill metrics view resources.'

Include natural user-facing variations like 'metrics layer', 'semantic layer', or 'Rill dashboard' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Detailed instructions and examples for developing metrics view resources in Rill" names the domain and artifact type but does not enumerate multiple concrete actions (e.g., defining dimensions, measures, security), matching the 'names domain and some actions, not comprehensive' anchor; not a 3 because no list of specific actions, not a 1 because the target resource is concrete.	2 / 3
Completeness	The description answers 'what' (instructions/examples for developing metrics views) but contains no explicit 'when to use' trigger guidance, so per the rubric a missing 'Use when...' clause caps completeness at 2; not a 3 because 'when' is entirely absent, not a 1 because 'what' is clearly stated.	2 / 3
Trigger Term Quality	The phrase "metrics view resources in Rill" provides the relevant product term but offers no common natural variations a user might say (e.g., 'metrics layer', 'semantic layer', 'dashboards'), landing on 'some relevant keywords but missing common variations'; not a 3 due to thin coverage, not a 1 because the term is natural rather than jargon.	2 / 3
Distinctiveness Conflict Risk	"metrics view resources in Rill" carves out a clear, product-specific niche with distinct triggers that would not fire for unrelated skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.	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 (734 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 5 suspicious	Warning

	Total	14 / 16 Passed

Repository: rilldata/agent-skills
Commit: 892996d

Reviewed: about 10 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.