CtrlK
BlogDocsLog inGet started
Tessl Logo

rill-development

Overview of how to develop a Rill project

59

1.55x
Quality

52%

Does it follow best practices?

Impact

84%

1.55x

Average score across 2 eval scenarios

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

66%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 a well-structured, mostly actionable overview of Rill development with a clear sequenced workflow and strong deferred-detail structure. Its main weaknesses are length/conceptual padding and references to detail files that are described generically rather than concretely named.

Suggestions

Trim conceptual restating (e.g. re-explaining DAG, OLAP role) that a competent data-engineering agent can infer, to improve conciseness.

Name the referenced resource-specific instruction files explicitly (e.g. link to rill-metrics-view) so progressive disclosure is concrete and one-level-deep.

Add explicit per-stage validation gating (verify parse/reconcile before proceeding) to push workflow clarity toward 5.

DimensionReasoningScore

Conciseness

The body is mostly efficient domain-specific guidance (resource types, DAG, pitfalls) but ~280 lines with some explanatory padding a competent agent could infer; it fits 'Mostly efficient but includes some unnecessary explanation or could be tightened' rather than 4 due to length and conceptual restating.

3 / 5

Actionability

It gives concrete, executable guidance: named tools (project_status, query_sql with LIMIT), specific CLI commands (rill validate), YAML properties (olap_connector:, managed: true), and a numbered workflow; minor gaps (no full code/config examples) keep it just below 5.

4 / 5

Workflow Clarity

The 'Recommended workflow' is a clearly sequenced 8-step pipeline with an explicit iterate-until-fixed validation checkpoint ('Check for errors and keep iterating until they are fixed'); it misses a 5 because validation steps are partly implicit and lack formal verify-then-proceed gating per stage.

4 / 5

Progressive Disclosure

It is a well-organized overview that repeatedly defers detail to 'separate resource-specific instruction files' and 'resource-specific instructions', and references docs.rilldata.com; it stays at 4 rather than 5 because those references are described generically rather than named as concrete one-level-deep files, and no bundle files exist to verify.

4 / 5

Total

15

/

20

Passed

Description

38%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 names the Rill platform niche clearly but is too vague to be a strong trigger: it states no concrete actions and omits any 'use when' guidance. It is distinguishable from other skills but weak on completeness and trigger terms.

Suggestions

Add concrete actions, e.g. 'Build, model, and deploy dashboards in a Rill BI project'.

Append an explicit 'Use when...' clause with natural triggers like 'Rill', 'Rill BI dashboard', or 'develop a Rill project'.

Include synonyms or product-specific terms users would actually say to improve trigger term quality.

DimensionReasoningScore

Specificity

'Overview of how to develop a Rill project' names the domain but gives no concrete actions, matching 'Names the domain but actions are minimal or generic'; it does not reach 3 because no specific verbs (build, deploy, model) are stated.

2 / 5

Completeness

It provides a vague 'what' ('Overview of how to develop a Rill project') and no 'when' guidance, matching 'Has a vague what and no when'; per guidelines a missing Use-when clause caps completeness at 3, and this is below that midpoint.

2 / 5

Trigger Term Quality

It mentions 'Rill project' but offers no natural trigger phrases a user would say (e.g. 'build a dashboard', 'Rill BI'), aligning with 'One or two generic keywords'; below 3 because common variations and synonyms are absent.

2 / 5

Distinctiveness Conflict Risk

'Rill project' names a specific platform with a clear niche and minimal conflict risk against unrelated skills; it stops short of 5 because no concrete distinct triggers are given.

4 / 5

Total

10

/

20

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.