CtrlK
BlogDocsLog inGet started
Tessl Logo

rill-development

Overview of how to develop a Rill project

56

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/rill-development/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is a well-organized, actionable guide with a strong validated workflow for Rill development, but it is a single monolithic file whose references to per-resource instruction files and sibling skills point to bundle files that do not exist.

Suggestions

Provide the referenced resource-specific instruction files (e.g. model, metrics-view, connector guides) or remove the dangling "see ... instructions" references so navigation is one level deep and resolvable.

Split the per-resource-type details into separate reference files and keep SKILL.md a concise overview pointing to them, reducing the monolithic length.

Tighten the introductory "Introduction to Rill" and OLAP sections, which lean on conceptual explanation, to improve token efficiency.

DimensionReasoningScore

Conciseness

The ~280-line body is mostly Rill-specific knowledge Claude would not already know, so most tokens earn their place, but it is a long monolithic document with sections that could be tightened or split out.

2 / 3

Actionability

It provides concrete executable guidance — specific tools (project_status, query_sql, list_tables), CLI commands (rill validate), exact YAML properties (olap_connector:, managed: true, mode: read), and a real project file listing — meeting the actionable standard for an instruction-only skill.

3 / 3

Workflow Clarity

The 8-step Recommended workflow is clearly sequenced with an explicit feedback loop — step 8 checks for parse/reconcile errors at each stage and iterates until fixed — plus validation via wait_until_idle and rill validate.

3 / 3

Progressive Disclosure

The body is well-sectioned but monolithic, and it repeatedly references separate resource-specific instruction files and skills (e.g. "instructions for model development", the rill-metrics-view skill) that are not present in the bundle, leaving navigation dangling.

2 / 3

Total

10

/

12

Passed

Description

47%

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 a specific niche (Rill BI development) but is vague about concrete capabilities and entirely lacks trigger guidance for when to invoke the skill. It is distinguishable but under-specified for discovery.

Suggestions

List concrete actions the skill performs, e.g. "Configure connectors, build models, define metrics views, and create dashboards in a Rill project."

Add an explicit trigger clause such as "Use when developing, editing, or debugging a Rill BI project, or when the user mentions Rill, metrics views, or Rill dashboards."

Expand trigger keyword coverage with natural variations users would say ("Rill project", "Rill dashboard", "Rill model", "rill.yaml").

DimensionReasoningScore

Specificity

The phrase "Overview of how to develop a Rill project" names a domain but lists no concrete actions — "Overview" is abstract with no verbs describing what the skill does, matching the vague/no-actions anchor.

1 / 3

Completeness

It states a rough "what" (overview of Rill development) but provides no "when"/trigger guidance; per the missing-Use-when guideline completeness is capped at 2, and the weak what prevents a 3.

2 / 3

Trigger Term Quality

"Rill" and "develop" are relevant natural terms a user might say, but coverage is thin with no "Use when" trigger or common variations, fitting the some-relevant-keywords-but-missing anchor.

2 / 3

Distinctiveness Conflict Risk

Naming the specific "Rill" platform gives a clear niche with distinct triggers unlikely to conflict with other skills, matching the clear-niche anchor.

3 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rilldata/agent-skills
Reviewed

Table of Contents

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.