Loading...
Loading...
Found 7 Skills
Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced? Use before trusting any 'how we'll know it worked' — an A/B, a holdout, a score, a validation — and whenever a result feels too clean or self-confirming. Walks an 8-pattern leakage taxonomy and returns only the patterns that fire, each with an independence fix. Read-only.
Guides multi-chain wallet and entity clustering using public bridge traces, wrapped-asset flows, temporal and behavioral heuristics, unified graphs with chain-prefixed addresses, and confidence scoring. Use when the user asks for cross-chain clustering, bridge hop analysis, multichain scam or phishing infrastructure mapping, laundering-pattern education from observable flows, or Arkham/Nansen-style entity graphs—without claiming ground-truth identity from heuristics alone.
Background knowledge for droid-control workflows -- not invoked directly. Capture ground-truth byte sequences from real terminal emulators.
After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
Shatter compromised calibration and rebuild from ground truth.
After solving a non-trivial problem, detect generalizable learnings and propose skill updates so future interactions benefit automatically. Always active — applies to every interaction.
Testing framework for evaluating Databricks skills. Use when building test cases for skills, running skill evaluations, comparing skill versions, or creating ground truth datasets with the Generate-Review-Promote (GRP) pipeline. Triggers include "test skill", "evaluate skill", "skill regression", "ground truth", "GRP pipeline", "skill quality", and "skill metrics".