data-matching
Match an analytical question to the right Allium table, metric, dashboard, or realtime endpoint. Required when selecting a new data source for a query or analysis: define the intended meaning, compare schema candidates, test coverage, and record the fit and caveats before treating a source as correct. Run this before `allium-investigation` or any other analysis.
Install
With your agent
Install OMGSkills skill "allium-labs/allium-claude-plugin:skills/data-matching" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/allium-labs/allium-claude-plugin /tmp/allium-claude-plugin && ln -s /tmp/allium-claude-plugin/skills/data-matching ~/.claude/skills/data-matchingFrom README
Data Matching The schema KB finds candidates. This skill decides whether a candidate actually matches the user's question. A semantically similar table is not automatically the right metric. Fetch this skill when introducing a new data source. Do not repeat it when making a narrow refinement to a previously inspected saved query unless the metric, source, scope, or interpretation changes.
More from this repo
allium-investigation
Investigate an onchain entity, protocol, market, or wallet question with Allium.
bridge-analysis
Methodology playbook for analyzing cross-chain bridge and messaging-protocol data on Allium — CCTP, LayerZero,...
dashboard-design
Used to build and update Allium Explorer dashboards with set_dashboard.