Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →study8677/graph-retrieval
Exposes graph-based retrieval as a tool capability via `query_graph`. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.
Passed 20 of 22 test cases with the skill, and 7 of 22 without it.
and 18 more in the full report
14 fixed6 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
Write a tool invocation statement or Python function call for performing graph retrieval on the query 'order processing flow' using default parameters.
| Checked | Without skill | With skill |
|---|---|---|
| The tool call uses the function name query_graph. | Missed | Passed |
| The max_hops parameter defaults to 2. | Missed | Passed |
The instructions your model reads when the skill loads.
Expose graph-based retrieval as a tool capability without breaking the existing RepoBrain execution chain.
query_graph(query, max_hops=2, workspace='.').repobrain/graph/.{
"summary": "...",
"triples": [["subject", "predicate", "object"]],
"evidence": [{"retrieval_id": "...", "tool_name": "..."}],
"nodes": [...],
"edges": [...]
}
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.