rill-rillyaml

Detailed instructions and examples for developing the rill.yaml file

Quality

45%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/rill-rillyaml/SKILL.md

Quality

Content

50%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 body is well-structured and actionable with strong copy-paste YAML examples and a thorough property schema, but it is held back by an inlined ~270-line JSON schema (with leftover admonition markup) that should live in a separate reference file, hurting both conciseness and progressive disclosure.

Suggestions

Move the full JSON schema into a references/ file (e.g. references/rill-yaml.schema.json) and replace the inline block with a one-line pointer plus a few key property highlights.

Strip the leftover Docusaurus admonition syntax (':::info', ':::note', ':::tip') from any retained schema or prose; it is noise in a SKILL.md.

De-duplicate the 'Core Concepts' prose against the schema so each property is documented in one place, trimming token volume.

Dimension	Reasoning	Score
Conciseness	The body inlines a ~270-line raw JSON schema with leftover Docusaurus admonitions (':::info'/':::tip') and duplicates much of the prose 'Core Concepts' section, making it noticeably verbose despite the prose itself being Rill-specific.	2 / 5
Actionability	It provides copy-paste-ready minimal and fully annotated complete YAML examples plus a property-level JSON schema with defaults and examples, covering common cases with only minor gaps (many rill.* env vars are documented but not demonstrated).	4 / 5
Workflow Clarity	This is reference documentation rather than a multi-step process; the minimal -> complete -> schema progression gives an implicit path with no validation checkpoints, but no explicit sequenced workflow is present (none is required since editing a config file is not destructive).	3 / 5
Progressive Disclosure	Section headers are clear, but the large JSON schema that clearly belongs in a separate reference file is inlined directly in SKILL.md, and no references/ bundle files exist to offload it, matching 'content that should be separate is inline'.	3 / 5
	Total	12 / 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, specific domain (rill.yaml) but relies on a generic action verb and omits any explicit 'Use when...' trigger guidance, weakening trigger-term quality and completeness. It is reasonably distinctive but not comprehensive.

Suggestions

Replace the generic 'developing' with concrete actions, e.g. 'Configure project-wide settings, OLAP/AI connectors, mock users, and environment defaults in rill.yaml'.

Add an explicit trigger clause: 'Use when the user asks to set up, configure, or edit a Rill project's rill.yaml file'.

Drop the meta phrasing 'Detailed instructions and examples for' to tighten the description and surface more natural trigger terms.

Dimension	Reasoning	Score
Specificity	The description names the domain ('rill.yaml file') but the only action verb is the generic 'developing', and 'instructions and examples' describes the content format rather than concrete capabilities, matching the 'Names the domain but actions are minimal or generic' anchor.	2 / 5
Completeness	A clear 'what' is present (instructions and examples for developing rill.yaml) but there is no 'when'/'Use when...' trigger guidance, which per the rubric caps completeness at 3; matches 'Has a clear what but when is missing or only weakly implied'.	3 / 5
Trigger Term Quality	It includes one real keyword ('rill.yaml') but 'developing' is not the verb users naturally say (they would say configure/set up/edit), and no synonyms or natural trigger phrases are present, fitting 'one or two generic keywords; missing the natural phrases users say'.	2 / 5
Distinctiveness Conflict Risk	The 'rill.yaml' niche is specific and largely distinct, with only minor overlap risk against other Rill config skills (e.g. models.yaml), matching 'Mostly distinct; minor overlap risk with closely related skills'.	4 / 5
	Total	11 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 6 missing, 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: rilldata/agent-skills
Path: skills/rill-rillyaml/SKILL.md
Commit: 3ad909d

Reviewed: 3 days 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.