BC foundry-solidity
Build and test Solidity contracts with Foundry. Use when developing Ethereum contracts, writing Forge tests, deploying with scripts, or debugging with Cast/Anvil. Triggers on forge, cast, anvil, foundry.toml, *.t.sol, or *.s.sol.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 21
✓ No critical or high findings
Medium and low: 21
-
low Secrets in code
secret-high-entropy-tokenreferences/anvil-advanced.md:18High-entropy token-like string (may be an id, hash or a credential)--from 0xd8…045 \
-
low Secrets in code
secret-high-entropy-tokenreferences/anvil-advanced.md:35High-entropy token-like string (may be an id, hash or a credential)address whale = 0x47…503;
-
low Secrets in code
secret-high-entropy-tokenreferences/anvil-advanced.md:266High-entropy token-like string (may be an id, hash or a credential)address whale = 0x47…503;
-
low Secrets in code
secret-high-entropy-tokenreferences/anvil-advanced.md:296High-entropy token-like string (may be an id, hash or a credential)address router = 0x7a…88D;
-
low Secrets in code
secret-high-entropy-tokenreferences/anvil-advanced.md:297High-entropy token-like string (may be an id, hash or a credential)address weth = 0xC0…Cc2;
-
low Secrets in code
secret-high-entropy-tokenreferences/cast-advanced.md:231High-entropy token-like string (may be an id, hash or a credential)cast lookup-address 0xd8…045
-
low Secrets in code
secret-high-entropy-tokenreferences/cast-advanced.md:256High-entropy token-like string (may be an id, hash or a credential)cast call 0xcA…A11 \
-
low Secrets in code
secret-high-entropy-tokenreferences/chisel.md:68High-entropy token-like string (may be an id, hash or a credential)➜ IERC20 usdc = IERC20(0xA0…B48)
-
low Secrets in code
secret-high-entropy-tokenreferences/chisel.md:70High-entropy token-like string (may be an id, hash or a credential)➜ usdc.balanceOf(0x47…503)
-
low Secrets in code
secret-high-entropy-tokenreferences/configuration.md:93High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)sender = "0x18…f38"
quoted -
low Exfiltration
net-credential-usereferences/configuration.md:225Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)custom = { key = "${CUSTOM_API_KEY}", url = "https://api.custom-explorer.com/api" }quoted -
low Secrets in code
secret-high-entropy-tokenreferences/deployment.md:223High-entropy token-like string (may be an id, hash or a credential)address constant CREA…ORY = 0x4e…56C;
-
low Secrets in code
secret-high-entropy-tokenreferences/forge-std-api.md:561High-entropy token-like string (may be an id, hash or a credential)address constant VM_ADDRESS = 0x71…12D;
-
low Secrets in code
secret-high-entropy-tokenreferences/forge-std-api.md:562High-entropy token-like string (may be an id, hash or a credential)address constant CONSOLE = 0x00…f67;
-
low Secrets in code
secret-high-entropy-tokenreferences/forge-std-api.md:563High-entropy token-like string (may be an id, hash or a credential)address constant CREA…ORY = 0x4e…56C;
-
low Secrets in code
secret-high-entropy-tokenreferences/forge-std-api.md:564High-entropy token-like string (may be an id, hash or a credential)address constant DEFAULT_SENDER = 0x18…f38;
-
low Secrets in code
secret-high-entropy-tokenreferences/forge-std-api.md:565High-entropy token-like string (may be an id, hash or a credential)address constant DEFAULT_TEST_CONTRACT = 0x56…72f;
-
low Secrets in code
secret-high-entropy-tokenreferences/security.md:375High-entropy token-like string (may be an id, hash or a credential)IERC20 usdc = IERC20(0xA0…B48);
-
low Secrets in code
secret-high-entropy-tokenreferences/security.md:376High-entropy token-like string (may be an id, hash or a credential)address whale = 0x47…503;
-
low Secrets in code
secret-high-entropy-tokenreferences/testing.md:342High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)address constant USDC = 0xA0…B48;
fixture -
low Secrets in code
secret-high-entropy-tokenreferences/testing.md:343High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)address constant WHALE = 0x47…503;
fixture
Files scanned: 18. 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 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1833 tokens
- 100Progress reporting. Reports progress
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 229: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (15 of 15)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.