rill-model

Detailed instructions and examples for developing model resources in Rill

1.66x

Quality

53%

Does it follow best practices?

Impact

93%

1.66x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/rill-model/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 content is highly actionable with extensive executable examples and well-organized dialect-specific guidance, but it is verbose for a single SKILL.md and lacks validation/verification checkpoints for risky model edits. Splitting the JSON schema and reference examples into bundle files would improve progressive disclosure.

Suggestions

Move the verbatim JSON schema (the '## Reference documentation' section) into a references/ file (e.g. SCHEMA.md) and link to it, keeping only an overview in SKILL.md to reduce token load.

Add an explicit validation/verification checkpoint for risky model operations, e.g. 'After editing a model, trigger a refresh and confirm the output table materializes; for incremental models, verify partition state to avoid duplicate processing.'

Trim introductory content Claude already knows (the dbt comparison, generic synthetic-data advice) and consolidate the long worked examples into a references/ examples file referenced one level deep.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured with executable YAML/SQL snippets, but it is very long (~1400 lines) and includes some content Claude already knows (e.g. explaining what a model is, dbt comparison, and generic 'realistic data distributions' guidance) plus a full verbatim JSON schema dump, so it could be tightened — matching the score-2 anchor 'Mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	It provides numerous complete, copy-paste-ready YAML and SQL examples covering concrete scenarios (S3-to-DuckDB, ClickHouse with TTL/indexes, incremental merge, dev partitions) plus specific property references and dialect notes, matching the score-3 anchor 'Fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	The skill is reference-style rather than a multi-step workflow, and while sections are logically organized it lacks explicit validation/checkpoint steps for risky operations (e.g. validating models after edits, verifying incremental state), so per the destructive/batch-operations guidance and the score-2 anchor it should be capped at 2.	2 / 3
Progressive Disclosure	There are no bundle files in references/scripts/assets, yet the body inlines a large JSON schema and many long examples that could live in separate files; organization is decent with clear sections but content that should be separated is inline, matching the score-2 anchor 'Some structure but could be better organized ... content that should be separate is inline'.	2 / 3
	Total	9 / 12 Passed

Description

42%

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 correctly identifies its niche (Rill model resources) and uses appropriate third-person voice, but it lacks natural trigger terms and any explicit 'Use when...' guidance for when Claude should invoke it. Adding concrete capabilities and usage triggers would lift the weaker dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when creating, editing, or debugging Rill model resources (.yaml/.sql model files), or when the user mentions Rill models, ETL/transformations, or materialization.'

List concrete capabilities (e.g. 'materialization, incremental loading, partitioning, refresh schedules, and connector staging') instead of the single generic action 'developing model resources'.

Include natural user-facing terms such as 'Rill model', 'model YAML', 'SQL model', 'incremental model', and 'partitioned model' to improve trigger-term matching.

Dimension	Reasoning	Score
Specificity	The phrase 'developing model resources in Rill' names the domain (Rill models) and an action (developing) but offers only a single broad action with no concrete enumerated capabilities (e.g. materialization, incremental loading, partitioning), matching the score-2 anchor 'Names domain and some actions, but not comprehensive'.	2 / 3
Completeness	It states what the skill covers ('detailed instructions and examples for developing model resources') but provides no explicit 'Use when...' trigger, so 'when' is only implied, matching the score-2 anchor 'Has what, but when is missing or only implied'.	2 / 3
Trigger Term Quality	It uses the technical phrase 'model resources in Rill' with no natural, user-facing keywords (e.g. 'Rill model', 'ETL', 'SQL', 'incremental', 'partition', 'dataset'), so a user would be unlikely to say this verbatim; this matches the score-1 anchor 'technical jargon or overly generic'.	1 / 3
Distinctiveness Conflict Risk	It is scoped to a clear niche — model resources specifically in Rill — with a distinct product name making it unlikely to trigger for unrelated skills, matching the score-3 anchor 'Clear niche with distinct triggers'.	3 / 3
	Total	8 / 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 (1412 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
Path: skills/rill-model/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.