AC zyfai
Earn yield on any Ethereum wallet on Ethereum Mainnet, Base, and Arbitrum. Use when a user wants passive DeFi yield on their funds. The first deposit assigns a non-custodial pre-deployed subaccount (Safe) with a signed session key to their EOA — no separate deploy or session-key step. Supports USDC, WETH, and EURC, with automated yield optimization and deposit/withdraw anytime.
As a process C 64/100 · Has gaps — weak spots: result and completion, when it triggers, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7280 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 14 mutating operations with no state check
- 40Consistency. Frontmatter name (zyfai) differs from the folder (zyfai-sdk)
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7280 tokens
- 100Tools and files. No external tools needed
- 100Steps. 40 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 380: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (33 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.