rill-model

Detailed instructions and examples for developing model resources in Rill

1.41x

Quality

—

Does it follow best practices?

Impact

96%

1.41x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

This is a thorough, highly actionable reference for Rill model YAML with excellent concrete examples, but it is held back by a heavy inline JSON schema dump, some example redundancy, and the absence of any progressive file split or explicit development workflow with validation feedback loops.

Suggestions

Move the large JSON schema block into a separate reference file (e.g., references/model_schema.json) and link to it from a concise 'Reference documentation' section, reducing inline token load and improving progressive disclosure.

Consolidate near-duplicate examples (e.g., the several S3-to-DuckDB partition variants) or cross-reference one canonical example, keeping only entries that illustrate a distinct concept.

Add a short 'Developing a model' workflow with explicit checkpoints (e.g., pick category → write SQL → choose materialization → configure dev partition → validate with a test/assert before promoting), since models are expensive and benefit from a validation feedback loop.

Dimension	Reasoning	Score
Conciseness	The instructional prose is reasonably lean and domain-specific (it does not explain basic concepts Claude already knows), but the ~630-line inline JSON schema dump and some near-duplicate examples are token-heavy and could be tightened or split out, matching 'mostly efficient but includes some unnecessary content / could be tightened' rather than the fully lean level 3.	2 / 3
Actionability	The body is packed with concrete, copy-paste-ready YAML/SQL examples covering many real source-to-target combinations plus specific property references and dialect notes, fitting the 'fully executable code/commands; specific examples; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The skill is structured as a reference/configuration guide with good decision guidance (materialization, dev partitions, model categories) rather than a sequenced multi-step workflow, and it lacks an explicit validate→fix→retry development feedback loop for the expensive/batch model operations it describes, which caps it at 2 per the feedback-loop guidance.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headings, but the skill is a monolithic single file (no references/, scripts/, or assets/ bundle files) and embeds a large inline JSON schema that reads as reference material which should be split out, matching 'some structure but content that should be separate is inline' rather than the appropriately-split level 3.	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 accurate and clearly scoped to Rill model resources, giving it strong distinctiveness, but it is generic on actions and entirely lacks a 'Use when...' trigger clause, which limits specificity, trigger-term quality, and completeness to the mid level.

Suggestions

Add an explicit 'Use when...' trigger clause naming concrete situations (e.g., 'Use when creating or editing Rill model YAML, defining ETL/transformations, partitions, or incremental ingestion').

Enumerate concrete actions instead of the generic 'developing model resources' (e.g., 'Define SQL-based ETL models, configure materialization, set up partitioned and incremental ingestion, schedule refreshes').

Include natural user-facing terms like 'Rill model', 'Rill YAML', 'ETL', 'incremental', and 'partitions' so the description matches how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	The description names the domain ("model resources in Rill") and a general activity ("developing" via "instructions and examples"), but it does not enumerate multiple concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It clearly states what the skill does ("Detailed instructions and examples for developing model resources in Rill") but provides no "Use when..." or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Terms like "model", "Rill", and "developing" are somewhat natural, but the description omits common variations a user might actually say (e.g., ETL, SQL, partitions, incremental, transformations), so it lands at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The Rill-specific model niche is clearly scoped and unlikely to trigger for non-Rill work, fitting the 'clear niche with distinct triggers; unlikely to conflict' anchor; it is above level 2 because the domain binding makes overlap with other skills minimal.	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 (1387 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 7 missing, 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: rilldata/agent-skills
Commit: 892996d

Reviewed: about 8 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.