Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →wondelai/ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models.
Passed 23 of 24 test cases with the skill, and 19 of 24 without it.
and 4 more in the full report
4 fixed19 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Can you run a diagnostic assessment on our IoT telemetry platform? We use Cassandra for high-throughput write ingestion along with Kafka and Flink for streaming analytics. However, our replication lag tolerance is ungrounded, network timeouts rely on vendor defaults, and our node failovers remain untested in production. Please analyze our design, present our current numerical score out of 10, identify which diagnostic rows failed, and provide a roadmap of improvements needed to reach 10/10.
| Checked | Without skill | With skill |
|---|---|---|
| Structures the diagnostic around the seven Quick Diagnostic rows from the framework | Missed | Passed |
| Calculates the score by awarding approximately 1.4 points per passed diagnostic row | Missed | Passed |
| Identifies untuned timeouts, ungrounded replication lag tolerance, and untested failovers as failing diagnostic rows | Passed | Passed |
The instructions your model reads when the skill loads.
A principled approach to building reliable, scalable, and maintainable data systems. Apply these principles when choosing databases, designing schemas, architecting distributed systems, or reasoning about consistency and fault tolerance.
Data outlives code. Applications are rewritten and frameworks come and go, but data persists for decades -- prioritize the long-term correctness, durability, and evolvability of the data layer. Most applications are data-intensive, not compute-intensive: the hard problems are data volume, complexity, and rate of change, and explicit consistency/availability/latency trade-offs separate robust systems from fragile ones.
Goal: 10/10. Score a data architecture by the seven Quick Diagnostic rows below: award ~1.4 points per row answered "yes" with evidence (deliberate, documented trade-off), 0 where the answer is "no" or unknown.
Report the current score, which diagnostic rows failed, and the improvements needed to reach 10/10.
Seven domains for reasoning about data-intensive systems:
Core concept: The data model shapes how you think about the problem. Relational, document, and graph models each impose different constraints and enable different query patterns.
Why it works: Choosing the wrong data model forces application code to compensate for representational mismatch, adding accidental complexity that compounds over time.
Key insights:
Code applications:
| Context | Pattern | Example |
|---|---|---|
| User profiles with nested data | Document model for self-contained aggregates | Profile, addresses, and preferences in one MongoDB document |
| Social network connections | Graph model for relationship traversal | Neo4j Cypher: MATCH (a)-[:FOLLOWS*2]->(b) for friend-of-friend |
test cases passed, vs 19 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.