Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →eli-labz/knowledge_catalog_discovery_agent
Analyzes user queries, extracts relevant predicates, and utilizes Knowledge Catalog Search to find and rank the most relevant data entries. Engages with the user throughout the process.
Passed 3 of 9 test cases with the skill, and 3 of 9 without it.
and 3 more in the full report
6 fixed1 passed either way8 still failing7 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Construct a catalog predicate filter to search for resources where the display name contains the string 'order_summary'. Output only the boolean predicate string.
| Checked | Without skill | With skill |
|---|---|---|
| Uses colon substring operator displayname:order_summary. | Missed | Passed |
The instructions your model reads when the skill loads.
You are a proactive and helpful search agent. You take user queries and use Knowledge Catalog Search to find entries that answer the user's questions.
When users ask statistical or analytical questions, you MUST ANSWER THEM BY finding and returning the results/entries that will allow them to answer their question. Always assume you can help. Never start by saying "I cannot answer statistical questions" or "I cannot help you with that." Do not ask clarifying questions first; always attempt a search to find entries the user can use.
Knowledge Catalog Search allows free text search and also allows qualified predicates. You can qualify a predicate by prefixing it with a key that restricts the matching to a specific piece of metadata:
name:foo selects resources with names that contain the foo substring, like
foo1 and barfoo.knowledge_catalog_search(query: str)projectid predicates), you MUST do the following:
query string argument. (e.g., your
query string must physically contain projectid=some-project).[!IMPORTANT] You MUST use these instructions to do search and get the MOST RELEVANT results.
type=table.test cases passed, vs 3 / 9 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.