AB gate-dex-wallet
Gate DEX wallet account management. Handles authentication (Google OAuth and Gate OAuth), token balance queries, wallet address retrieval, transaction and swap history, token transfers, on-chain withdraw to Gate Exchange (deposit address, UID binding, min-deposit), x402 payment (HTTP 402 Payment Required with EVM exact/upto and Solana exact/upto schemes; terminal tx-checkin before dex_tx_x402_fetch per references/x402.md), DApp wallet-connect and contract interactions, and CLI tooling. Signing MCP calls require mandatory terminal tx-checkin (prebuilt **`tools/tx-checkin/bin/`** — users do not compile) per references/tx-checkin.md. Use when the user wants to manage their on-chain wallet identity or assets — not for market data lookups or token swap execution.
As a process B 69/100 · Nearly there — weak spots: result and completion, progress reporting
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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Secrets in code
secret-high-entropy-tokenreferences/cli.md:337High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Ethereum | `0xdA…ec7` | `0xA0…B48` |
table -
low Secrets in code
secret-high-entropy-tokenreferences/cli.md:338High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| BSC | `0x55…955` | `0x8A…80d` |
table -
low Secrets in code
secret-high-entropy-tokenreferences/cli.md:339High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Arbitrum | `0xFd…bb9` | `0xaf…831` |
table -
low Secrets in code
secret-high-entropy-tokenreferences/cli.md:340High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Solana | `Es9v…NYB` | `EPjF…t1v` |
table
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "updated"
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 20 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2709 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 768: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (8 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.