AC ava
Lend real USDC on Base from your coding agent, inside limits the human sets. Ava handles session, mandate, two-phase preview, execution, and returns a receipt with chain proof. The agent never holds a key. Works from Claude Code, Cursor, Codex, and OpenClaw over HTTP MCP (https://www.getava.xyz/mcp). Fastest connect for Claude Code, Cursor, or Codex: npx @getava-xyz/connect. Live money is ava_lend_execute on Base (Morpho); copilot tools are testnet only. Use when: (1) the human wants their agent to allocate capital under bounds they set, (2) they ask for DeFi yield from a coding session, (3) they want a recomputable track record of agent executions. Triggers: Ava, agentic finance, MCP trading, mandate, agent wallet, OpenClaw DeFi, Claude trade, Cursor finance tools.
Lend real USDC on Base from your coding agent, inside limits the human sets.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 14 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1385 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- -2localhost URLs: will not work for another user
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 776: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.