AC minara
Crypto trading & wallet, and AI market analysis via Minara CLI. Swap, perps, transfer, deposit (credit card/crypto), withdraw, AI chat, market discovery, x402 payment, autopilot, limit orders, premium. EVM + Solana + Hyperliquid. Use when: (1) crypto tokens/tickers (ETH, BTC, SOL, USDC, $TICKER, contract addresses), (2) chain names (Ethereum, Solana, Base, Arbitrum, Hyperliquid), (3) trading actions (swap, buy, sell, long, short, perps, leverage, limit order, autopilot), (4) wallet actions (balance, portfolio, deposit, withdraw, transfer, send, pay, credit card), (5) market data (trending, price, analysis, fear & greed, BTC metrics, Polymarket, DeFi), (6) stock tickers in crypto context (AAPL, TSLA), (7) Minara/x402/MoonPay explicitly, (8) subscription/premium/credits.
As a process C 63/100 · Has gaps — weak spots: result and completion, running it twice, progress reporting
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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Secrets in code
secret-high-entropy-tokenreferences/examples.md:32High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)minara swap -s buy -t DezX…263 -a 100
fixture -
low Secrets in code
secret-high-entropy-tokenSKILL.md:182High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- USDT (Ethereum): `0xdA…ec7`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:183High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- USDC (Ethereum): `0xA0…B48`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:184High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- WETH (Ethereum): `0xC0…Cc2`
quoted
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5404 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 11 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5404 tokens
- 100Steps. 85 steps
- 100Failures and branches. 16 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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 779: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 85 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (17 of 17)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.