Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Daily DeFi read — regime verdict (RISK-ON / NEUTRAL / RISK-OFF) reproducible from named inputs, top TVL movers with one-line causal reasoning, and a sustainable-vs-incentive yield split so the operator can tell real product-market fit from emissions-pumped APY. Public APIs only. Triggers: "DeFi read", "DeFi regime today", "yield decomposition", "is this APY real or emissions", "DeFi movers with why".
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 155% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -10% | 0% |
The decision layer above DefiLlama. One read per day on the regime, the biggest movers with causal reasoning, and which yields are actually sustainable vs being paid for in inflation.
One of RISK-ON / NEUTRAL / RISK-OFF. Computed from five inputs, each named in the output:
Verdict is reproducible from these values — operator can disagree but not on the math.
Top 5 TVL gainers and top 5 losers. Per row: protocol + chain, 24h delta, one-line "why" (incentive launch, exploit, depeg, narrative, liquidation cascade) or "no obvious driver" if unclear.
Top protocols by TVL on each major chain, with the sustainable share (real / (real + incentives)). Yields under 20% sustainable share are flagged incentive-dependent — they evaporate when emissions end.
DefiLlama (api.llama.fi), GeckoTerminal, perp aggregators for funding rates.
Other measured skills in the registry, with their headline benchmark lift.