rill-model

Detailed instructions and examples for developing model resources in Rill

1.66x

Quality

56%

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

71%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 content is highly actionable with comprehensive executable examples and solid organization, but it carries significant inlined bulk (the full schema reference) that would benefit from progressive disclosure into separate files.

Suggestions

Move the full JSON schema reference block into a separate referenced file (e.g. reference/schema.md) and keep only a brief pointer plus key properties inline in SKILL.md.

Consider splitting the extensive Examples catalog into a dedicated examples file, leaving a representative subset inline.

Trim the synthetic-data-generation guidance or relocate it to a reference, since it is secondary to the core model-authoring workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient technical prose with concrete examples, but the ~630-line inlined JSON schema reference and some explanatory padding (e.g. the synthetic-data section) could be trimmed or moved out of the main flow.	3 / 5
Actionability	It provides numerous copy-paste-ready YAML and SQL examples with real property names covering the common cases (S3/GCS/BigQuery to DuckDB, ClickHouse, partitions, incremental merge, dev limits).	5 / 5
Workflow Clarity	Content is well-sequenced from concepts to properties to dialect notes to examples, with explicit best-practice and exception guidance; because this is a reference skill rather than a destructive/batch workflow, the absence of validation checkpoints is a minor gap rather than a disqualifier.	4 / 5
Progressive Disclosure	Section headers provide reasonable structure, but with no bundle files present the full JSON schema reference and large example catalog are inlined in SKILL.md rather than split into clearly signaled one-level-deep reference files.	3 / 5
	Total	15 / 20 Passed

Description

41%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 identifies a clear, narrow domain but uses generic language and omits any explicit usage triggers. Adding concrete capabilities and a "Use when..." clause would substantially improve it.

Suggestions

Replace the generic verb "developing" with concrete actions, e.g. "Create, partition, and incrementally load model resources in Rill."

Add an explicit trigger clause such as "Use when building or editing Rill models, partitions, incremental ingestion, or refresh schedules."

Include natural synonyms users might say (e.g. "Rill model YAML", "Rill SQL model") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("model resources in Rill") but relies on the generic action "developing" with "instructions and examples," offering no concrete capabilities like partitioning, incremental loading, or materialization.	2 / 5
Completeness	It states a clear "what" (developing model resources in Rill) but provides no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	It surfaces only the narrow keywords "model resources" and "Rill"; it lacks the natural variations or synonyms a user would actually say when needing this skill.	2 / 5
Distinctiveness Conflict Risk	"model resources in Rill" is a distinct niche unlikely to fire for unrelated skills, with only minor overlap risk against other Rill-specific skills.	4 / 5
	Total	11 / 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 (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: 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.