rill-metrics-view

Detailed instructions and examples for developing metrics view resources in Rill

Quality

57%

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

61%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 body is highly actionable with comprehensive, copy-paste-ready YAML examples and dialect-specific guidance, but it is weighed down by a large inline JSON schema that should live in a separate reference file and by the absence of any authoring workflow with validation checkpoints.

Suggestions

Move the full JSON schema (lines 459-772) into a separate reference file (e.g., references/schema.md) and link to it from a short 'Reference documentation' section, leaving only a compact key-properties summary inline.

Add a short authoring workflow with a validation checkpoint, e.g. 'rill start' / reconcile -> review validation errors -> fix -> re-reconcile, since metrics views only validate on reconcile.

Create bundle files for the dialect-specific notes and security-policy examples to reduce inline bulk and improve navigation.

Dimension	Reasoning	Score
Conciseness	The prose is mostly efficient and avoids explaining basic concepts Claude already knows, but the ~300-line inline JSON schema dump (lines 459-772) is heavy reference material that does not earn its token cost in SKILL.md; this pulls it down from the 'efficient; minor instances' anchor at 4 to 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	Provides numerous concrete, copy-paste-ready YAML examples across all common cases (dimensions, measures, security, rollups, annotations, dialect-specific SQL) with a fully annotated end-to-end example; matches the 'fully executable; copy-paste ready code; specific examples cover the common cases' anchor.	5 / 5
Workflow Clarity	Content is organized into clear conceptual sections but there is no sequenced authoring workflow with validation checkpoints (e.g., no 'validate the metrics view -> fix -> retry' loop), fitting the 'sequence present but checkpoints missing or implicit' anchor; it is not lower because the sectioning does convey order, and not higher because no explicit checkpoints exist.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent) and the full JSON schema reference is inlined directly in SKILL.md, which is exactly 'content that clearly belongs in separate files is inlined'; section headers provide some structure, keeping it above 1 but firmly at the 'minimal structure; content that should be separate is inline' anchor rather than 3.	2 / 5
	Total	13 / 20 Passed

Description

53%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 clearly identifies the domain and product but is generic about concrete actions and entirely omits a 'Use when...' trigger clause, which caps completeness at 3. It is reasonably distinct because of its Rill-specific scope.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when creating or editing metrics view / semantic-layer resources in Rill') so the when-condition is concrete.

Replace the generic 'instructions and examples for developing' with specific concrete actions such as 'define dimensions, measures, security policies, and rollups for Rill metrics views'.

Include natural synonyms users actually say (e.g., 'dashboards', 'semantic layer', 'Rill metrics') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('metrics view resources in Rill') and two actions ('instructions and examples' / 'developing') but the actions are generic and not a comprehensive list; fits the 'names domain and 1-2 concrete actions, but not comprehensive' anchor and falls short of the several-specific-actions anchor at 4.	3 / 5
Completeness	Clearly states what the skill does ('instructions and examples for developing metrics view resources') but has no 'Use when...' or equivalent trigger clause; per the guideline a missing explicit trigger clause caps completeness at 3, which is the 'clear what but when missing or only weakly implied' anchor.	3 / 5
Trigger Term Quality	Includes the natural product term 'metrics view' and 'Rill', but misses common variations/synonyms a user might say ('dashboards', 'semantic layer', 'Rill metrics'); matches the 'some relevant keywords but missing common variations or synonyms' anchor rather than the fuller coverage at 4.	3 / 5
Distinctiveness Conflict Risk	Tightly scoped to 'metrics view resources in Rill', a specific product feature, giving it a clear niche with minimal overlap risk; not a 5 only because the description lacks distinct trigger phrases that would fully separate it from neighboring Rill/dashboard skills.	4 / 5
	Total	13 / 20 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 (772 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: 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.