Download for MacApple silicon, macOS 14+
Skill

rwa-analysis

@allium-labs Updated 2026-10-23

Methodology playbook for analyzing tokenized real-world assets (RWA) on Allium — tokenized treasuries, money market funds, tokenized equities/pre-IPO stocks, commodities, and private credit. Use whenever a question touches RWA supply, AUM, market cap, holders, mint/burn activity, or classification — even if the user just says "tokenized treasuries," "BUIDL," "tokenized stocks," "money market fund AUM growth," or names a specific RWA product/issuer. Covers the aggregation mistakes, classification pitfalls, and data-quality exclusions that come up repeatedly in real RWA questions before you write the SQL.

Install

With your agent

Install OMGSkills skill "allium-labs/allium-claude-plugin:skills/rwa-analysis" 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/rwa-analysis ~/.claude/skills/rwa-analysis

From README

RWA Analysis RWA questions look like simple aggregations ("what's the AUM of X," "how many holders does Y have") but the naive query is usually wrong in a specific, recurring way. Read this before writing SQL for an RWA question — it's cheaper than debugging a 30x-inflated number after the fact. Aggregation: snapshot, don't sum AUM, market cap, and supply are stock quantities (a balance at a point in time), not flow quantities. Summing a daily-snapshot table across a date range compounds the same balance over and over. Take the latest row per grouping key (QUALIFY ROWNUMBER() OVER (PARTITION BY ... ORDER BY date DESC) = 1, or MAX(date) per group), never SUM(marketcapusd) / SUM(supply) across days. This mistake is easy to miss because the wrong number is still plausible-looking — one real case reported "$220B" AUM that was actually $7.2B, a 30x inflation from summing 30 days of the same snapshot.