BC smart-accounts-kit
Web3 development using MetaMask Smart Accounts Kit. Use when the user wants to build dApps with ERC-4337 smart accounts, send user operations, batch transactions, configure signers (EOA, passkey, multisig), implement gas abstraction with paymasters, create delegations, or request advanced permissions (ERC-7715). Supports Viem integration, multiple signer types (Dynamic, Web3Auth, Wagmi), gasless transactions, and the Delegation Framework.
Web3 development using MetaMask Smart Accounts Kit.
As a process C 60/100 · 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.
For the model run — optional
- 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 · 14
✓ No critical or high findings
Medium and low: 14
-
low Secrets in code
secret-high-entropy-tokenreferences/advanced-permissions.md:110High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)tokenAddress: '0x1c…238',
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/advanced-permissions.md:142High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)tokenAddress: "0x1c…238",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/advanced-permissions.md:302High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)tokenAddress: '0x1c…238',
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/delegations.md:110High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)tokenAddress: '0xb4…7da',
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/delegations.md:149High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)tokenAddress: '0xc1…E92',
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/delegations.md:166High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)tokenAddress: '0x3f…319',
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/delegations.md:249High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)targets: ['0x1c…238'], // USDC
detector -
low Secrets in code
secret-high-entropy-tokenreferences/delegations.md:267High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)contractAddress: '0x1c…238',
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/smart-accounts.md:297High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)sender: '0xE9…E1f',
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:94High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)tokenAddress: '0x1c…238',
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:340High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| EntryPoint | `0x00…032` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:341High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| SimpleFactory | `0x69…77c` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:342High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| DelegationManager | `0xdb…dB3` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:343High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| MultiSigDeleGatorImpl | `0x56…3A7` |
table
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6578 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 27 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6578 tokens
- 100Steps. 94 steps
- 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 17 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 442: enough signal without eating the budget
- +4Structure: 61 headings
- +3Step-by-step instructions: 94 items
- +4Has examples (20 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.