rill-development

Overview of how to develop a Rill project

1.19x

Quality

53%

Does it follow best practices?

Impact

99%

1.19x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

70%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 a strong, domain-specific developer guide with a genuinely well-engineered workflow (explicit validation loops, tool guidance, an extensive pitfalls checklist). Its main weaknesses are repeated content that could be deduplicated, the absence of any concrete resource-file example, and references to instruction files that are not clearly signaled or present in the bundle.

Suggestions

State the duplicate-explore rule once (e.g. in the pitfalls section) and reference it from the other two locations to remove the triple repetition and tighten conciseness.

Include one short, representative example resource file (e.g. a minimal model YAML or metrics view with an inline explore block) to push actionability toward copy-paste ready.

Turn the vague deferrals ('see the metrics view instructions') into explicit, verifiable references with paths, and move the per-resource-type detail into separate reference files so SKILL.md stays an overview.

Dimension	Reasoning	Score
Conciseness	The body is overwhelmingly domain-specific knowledge Claude cannot be assumed to know (Rill's resource types, DAG semantics, default OLAP connector behavior), but it could be tightened: the duplicate-explore warning is repeated three times (Explores section, workflow step 7, Common pitfalls) and the 'expensive resources' caution recurs across sections. This fits anchor 3, 'Mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	Concrete, executable guidance throughout for an instruction-only skill: exact properties ('olap_connector:', 'managed: true', 'mode: read', 'timeseries:'), named tools ('project_status', 'query_sql', 'wait_until_idle', 'rill validate'), and specific limits ('up to 10 dimensions and up to 5 measures'). This matches anchor 4 ('Mostly executable guidance... minor gaps'); it stops short of anchor 5 because there is no copy-paste-ready example of a resource file (e.g. a sample model or metrics view YAML).	4 / 5
Workflow Clarity	The 'Recommended workflow' provides a clearly sequenced 8-step pipeline with an explicit validation and iterate-until-fixed loop, a blocking 'wait_until_idle' checkpoint for reconciliation, an 'rill validate' fallback when MCP tools are unavailable, and a detailed pitfalls checklist. This matches anchor 5 (clear sequence with explicit validation steps, feedback loops for error recovery, and a checklist).	5 / 5
Progressive Disclosure	Section organization is reasonable, but the body repeatedly defers to 'the metrics view instructions', 'instructions for model development', and skills like 'rill-metrics-view' without any paths or links, and no bundle files exist to back these references. Much of the ~300 lines of per-resource-type detail could also live in separate files. This fits anchor 3 ('references present but not clearly signaled; content that should be separate is inline').	3 / 5
	Total	15 / 20 Passed

Description

36%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 the domain clearly via 'Rill' but says almost nothing else: the action is generic, there is no 'Use when...' trigger guidance, and none of the platform's concrete capabilities (models, metrics views, dashboards, connectors) are named. It would benefit most from naming concrete actions and an explicit trigger clause.

Suggestions

Add an explicit trigger clause, e.g. 'Use when developing, editing, or debugging a project on the Rill business intelligence platform.'

Name the concrete capabilities instead of the generic 'develop', e.g. 'Create and manage Rill resources: connectors, models, metrics views, explore and canvas dashboards.'

Include the natural terms users would say, such as 'dashboard', 'metrics view', 'model', 'connector', and 'Rill Cloud', to improve trigger-term coverage and distinguish it from resource-specific Rill skills.

Dimension	Reasoning	Score
Specificity	"Overview of how to develop a Rill project" names the domain (Rill) but offers only the generic action "develop"; no concrete actions such as creating models, metrics views, or dashboards are listed, matching the anchor 'Names the domain but actions are minimal or generic'. It falls short of anchor 3, which requires at least 1-2 concrete named actions.	2 / 5
Completeness	The 'what' is vague ('Overview of how to develop a Rill project') and there is no 'when' / 'Use when...' trigger clause at all, exactly matching anchor 2 ('Has a vague what and no when'). It cannot reach anchor 3 because even the 'what' lacks concrete actions.	2 / 5
Trigger Term Quality	"Rill" is a strong, natural keyword, but the description misses the common phrases users would actually say when needing this skill (dashboard, metrics view, model, connector, BI), fitting the anchor 'Some relevant keywords but missing common variations or synonyms'. It is above anchor 2 because 'Rill' is specific rather than generic.	3 / 5
Distinctiveness Conflict Risk	'Rill' gives the skill a clear niche versus non-Rill skills, but the generic scope would cause it to trigger for nearly any Rill task, overlapping with the resource-specific skills the body itself references (e.g. rill-metrics-view). This fits anchor 3 ('Somewhat specific but could still overlap with similar skills') better than anchor 4, which assumes only minor overlap risk.	3 / 5
	Total	10 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rilldata/agent-skills
Path: skills/rill-development/SKILL.md
Commit: 1307e7f

Reviewed: 7 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.