BB ai-bounty-claim
Use when claiming the AI bounty on the tDVV mainnet sidechain. First explain the difference between Portkey AA/CA and EOA, recommend AA/CA because the current campaign rewards 2 AIBOUNTY for AA/CA and 1 AIBOUNTY for EOA, then route to account onboarding, Portkey AA/CA claim through CA ManagerForwardCall, EOA claim, or diagnostics-only stop handling.
As a process B 65/100 · Nearly there — weak spots: result and completion, consistency
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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Risky intent
intent-wallet-secretsskill-card.md:22Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetRisk: Wallet secrets could be exposed if a user pastes a seed phrase or private key into chat. <br>
Files scanned: 12. 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 65/100
- 0Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (ai-bounty-claim) differs from the folder (ai-bounty-skill)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 108 steps
- 100Failures and branches. 15 branches, has a failure section
- 100Execution cost. Instruction body is 3273 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 351: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 108 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.