Detailed instructions and examples for developing model resources in Rill
57
36%
Does it follow best practices?
Impact
96%
1.41xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/rill-model/SKILL.mdClickHouse model column schema and indexes
order_by present
100%
100%
LowCardinality for country
100%
100%
LowCardinality for device_type
100%
100%
LowCardinality for campaign_id
0%
100%
S3 env var templating
20%
100%
TTL configured
80%
100%
bloom_filter index
0%
100%
set index
0%
100%
No explicit MergeTree
0%
100%
Partition-based incremental
60%
100%
Correct partition URI in SQL
16%
100%
No trailing semicolon
100%
100%
Incremental model with dev partition limits
Partition-based not state-based
100%
100%
Dev partition on source model
100%
100%
Dev limit is time range
40%
100%
No dev partition on derived model
100%
100%
partition: directory with wildcard URI
100%
100%
Correct partition template variable
100%
100%
Cron refresh on source
100%
100%
materialize: true on source
0%
100%
materialize: false on derived
0%
100%
No trailing semicolons
100%
100%
ref usage in derived model
100%
100%
Synthetic data model for prototyping
Timestamp column present
100%
100%
Row count ~10,000
0%
100%
6-12 months of historical data
0%
100%
Timestamps spread realistically
100%
100%
Multiple dimension columns
100%
100%
Realistic category distributions
100%
100%
Numeric measure column
100%
100%
Correct materialization
100%
0%
No trailing semicolon
100%
100%
type: model declared
100%
100%
e7c833e
Table of Contents
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.