Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →goldsky-io/goldsky-datasets
Discover available blockchain datasets for Turbo pipelines.
Passed 24 of 24 test cases with the skill, and 5 of 24 without it.
and 29 more in the full report
20 fixed5 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.
I tried configuring polygon.raw_logs in my dataset source config, but the deployment failed. What is the correct chain prefix for Polygon mainnet?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies matic as the chain prefix for Polygon mainnet | Missed | Passed |
The instructions your model reads when the skill loads.
Explore and discover available blockchain datasets for Turbo pipelines.
Invoke this skill when the user:
/goldsky-datasetsIMPORTANT - Avoid
goldsky dataset list: This command is slow (30-60+ seconds) and often times out. Use the reference tables below instead. Only run the command if you need to verify a specific dataset exists or find an exact version.
When this skill is invoked:
Do NOT run goldsky dataset list upfront. Instead:
goldsky turbo validate on a test YAML to verify a dataset exists (fast, ~3 seconds)goldsky dataset list | grep "specific_name" if you need version infoBased on what they're building, recommend directly from the reference:
| User Need | Dataset | Version |
|---|---|---|
| Token transfers (ERC-20) | <chain>.erc20_transfers | 1.0.0 (eth), 1.2.0 (base) |
| NFT transfers (ERC-721) | <chain>.erc721_transfers | 1.0.0 |
| All transactions | <chain>.raw_transactions | 1.0.0 |
| Event logs | <chain>.logs or <chain>.raw_logs | 1.0.0 |
test cases passed, vs 5 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.