CtrlK
BlogDocsLog inGet started
Tessl Logo

rill-explore

Detailed instructions and examples for developing explore dashboard resources in Rill

67

1.08x
Quality

61%

Does it follow best practices?

Impact

100%

1.08x

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-explore/SKILL.md
SKILL.md
Quality
Evals
Security

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 complete YAML examples and clear section structure, but it carries a heavy inline JSON schema dump and lacks validation/verify steps in its workflow. Splitting the schema into a reference file and adding a verification step would materially improve it.

Suggestions

Move the raw JSON schema into a separate reference file (e.g. references/explore-schema.yaml) and link to it, keeping the body as an overview.

Add an explicit validation/verification step to the development workflow, such as how to confirm the explore resource resolves or displays correctly after editing.

Consolidate the annotated and minimal examples to reduce repetition, or clearly label the minimal one as the recommended starting point to tighten token use.

DimensionReasoningScore

Conciseness

The body avoids concept-explaining fluff and stays mostly lean, but pastes a large raw JSON schema inline and repeats similar YAML across the annotated and minimal examples, which could be tightened or externalized.

2 / 3

Actionability

Provides multiple complete, copy-paste-ready YAML examples (inline explore, full annotated example, minimal example) with per-property explanations, giving concrete executable guidance for authoring explore dashboards.

3 / 3

Workflow Clarity

The 'Development approach' section offers a numbered sequence (reference metrics view, select dimensions/measures, configure defaults) plus inline-vs-separate guidance, but there are no validation checkpoints or verify steps, leaving the sequence checkpoint-free.

2 / 3

Progressive Disclosure

Sections are clearly organized, but the full raw JSON schema is dumped inline in the body rather than split into a separate reference file, and no bundle files (references/scripts/assets) exist to house such reference material.

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 clearly identifies a specific, distinctive niche (Rill explore dashboards) but relies on a single broad verb and omits any explicit 'Use when...' trigger guidance. It answers what the skill does but not when Claude should reach for it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating or configuring Rill explore dashboards or when the user mentions Rill dashboards/metrics views.'

Replace the broad 'developing' with several concrete actions such as 'create, configure, and customize explore dashboards'.

Include common user-facing variations like 'Rill dashboard' or 'metrics dashboard' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the concrete domain ('explore dashboard resources in Rill') and a broad action ('developing') plus content type ('instructions and examples'), but does not list multiple specific actions like 'create, configure, or customize' explore dashboards.

2 / 3

Completeness

Answers 'what' (instructions and examples for developing explore dashboards) but provides no 'when' / 'Use when...' trigger guidance, which per the rubric caps completeness at 2.

2 / 3

Trigger Term Quality

Includes relevant natural terms ('explore dashboard', 'Rill') but misses common variations a user might say ('Rill dashboard', 'metrics dashboard'); 'developing' and 'instructions and examples' are not natural user utterances.

2 / 3

Distinctiveness Conflict Risk

Tied to the named product Rill and the specific 'explore dashboard' resource type, giving it a clear niche unlikely to conflict with other generic skills.

3 / 3

Total

9

/

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.