Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -28% | 0% |
Expose graph-based retrieval as a tool capability without breaking the existing RepoBrain execution chain.
query_graph(query, max_hops=2, workspace='.').repobrain/graph/.json{ "summary": "...", "triples": [["subject", "predicate", "object"]], "evidence": [{"retrieval_id": "...", "tool_name": "..."}], "nodes": [...], "edges": [...] }
Other measured skills in the registry, with their headline benchmark lift.