AC solclaw
Non-custodial USDC payments on Solana by agent name. Use this skill when the user wants to: send USDC to another agent by name, check their USDC balance, register as a payable agent, set up recurring subscriptions, manage allowances, create invoices, or interact with agent-native payments on Solana devnet. Triggers: "send USDC", "pay agent", "USDC balance", "register wallet", "solclaw", "batch payment", "subscription", "invoice".
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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
-
medium Broad scope
meta-agent-memory-dumpheartbeat.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensheartbeat.md
-
low Dangerous commands
cmd-cron-mentionheartbeat.md:112Mentions editing / listing crontabcrontab -e
-
low Secrets in code
secret-high-entropy-tokenskill.md:206High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Program ID | `J4qi…Z5H` |
table -
low Secrets in code
secret-high-entropy-tokenskill.md:207High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| USDC Mint | `4zMM…cDU` |
table
Files scanned: 3. 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 57/100
- 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1592 tokens
- 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
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +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
- +5Description quotes 8 example trigger phrases
- +3Description length 433: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.