rill-model

Detailed instructions and examples for developing model resources in Rill

1.32x

Quality

43%

Does it follow best practices?

Impact

94%

1.32x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/rill-model/SKILL.md

Quality

Discovery

22%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is too vague and lacks the specificity needed for Claude to reliably select it from a pool of skills. It fails to enumerate concrete actions, omits a 'Use when...' clause, and relies on generic phrasing that doesn't convey what 'model resources in Rill' actually involves.

Suggestions

List specific concrete actions the skill covers, e.g., 'Define metrics, dimensions, and measures in Rill model YAML files, configure data sources, and set up dashboard models.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about creating or editing Rill models, defining metrics/dimensions, or configuring Rill YAML resources.'

Include common file types or terminology users would mention, such as '.yaml', 'Rill Developer', 'OLAP', 'metrics layer', or 'dashboard definitions' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'detailed instructions and examples' without listing any concrete actions. It does not specify what 'model resources' entails or what specific tasks the skill performs.	1 / 3
Completeness	The description weakly addresses 'what' (developing model resources) but provides no 'when' clause or explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	It includes 'model resources' and 'Rill' as domain-specific terms, but lacks natural keywords a user might say such as 'metrics', 'dimensions', 'YAML', 'data modeling', or 'dashboards'. The term 'Rill' is helpful but 'model resources' is somewhat jargon-heavy.	2 / 3
Distinctiveness Conflict Risk	'Rill' provides some distinctiveness as a specific tool, but 'model resources' is vague enough that it could overlap with other data modeling or resource development skills. Without more specifics, the niche is unclear.	2 / 3
	Total	6 / 12 Passed

Implementation

64%

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

This is a highly actionable and comprehensive skill with excellent executable examples covering many real-world scenarios for Rill model development. Its main weaknesses are verbosity (the document is very long with some unnecessary conceptual explanations and a full inline JSON schema) and lack of explicit validation/verification workflows for what the skill itself acknowledges are 'expensive resources that can take a long time to run.' The content would benefit from splitting into multiple files with a concise overview pointing to detailed references.

Suggestions

Extract the full JSON schema reference into a separate REFERENCE.md file and link to it from the main skill to reduce token usage

Add explicit validation steps for model development workflows, e.g., 'After creating a model, verify it by checking: 1) model status in Rill UI, 2) row counts match expectations, 3) schema is correct'

Trim the introduction and model categories sections - remove explanatory content Claude already knows (e.g., what ETL is, what a DAG is) and focus on Rill-specific distinctions

Split dialect-specific notes and the extensive examples section into separate files (e.g., DUCKDB_NOTES.md, CLICKHOUSE_NOTES.md, EXAMPLES.md) with clear links from the main skill

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but includes some unnecessary explanatory content that Claude would already know (e.g., explaining what models are conceptually, what ETL means in context). The introduction and model categories sections could be significantly tightened. However, the examples section and dialect-specific notes are dense with useful, non-obvious information. The full JSON schema at the end adds significant length but serves as a reference.	2 / 3
Actionability	The skill excels at actionability with numerous complete, copy-paste-ready YAML and SQL examples covering a wide range of scenarios (S3 to DuckDB, BigQuery to DuckDB, ClickHouse with indexes/TTL, incremental models, dev partitions, etc.). Every concept is backed by executable code with realistic configurations and clear file path comments indicating where files should be placed.	3 / 3
Workflow Clarity	While the skill covers many model types and configurations clearly, it lacks explicit validation checkpoints and feedback loops. For example, there's no guidance on how to verify a model was created correctly, how to debug failed partitions, or what to check after editing a model. The performance considerations mention caution but don't provide a clear workflow for safely developing expensive models. The dev partitions section provides good development practices but without explicit validation steps.	2 / 3
Progressive Disclosure	The content is a monolithic document with no references to external files for detailed topics. The full JSON schema at the end (~200+ lines) could be in a separate REFERENCE.md file. Dialect-specific notes, the extensive examples section, and the schema could all be split into separate files with clear navigation from the main skill. The document is well-organized with clear headers, but everything is inline in one large file.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1380 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: rilldata/agent-skills
Commit: 65ccd1f

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.