AB metacomp_visionx_kyt
Check Web3 wallet or transaction security using MetaComp VisionX. Trigger when user mentions wallet address (0x..., Bitcoin, Tron), transaction hash, or asks about Web3 security, risk, scam, or suspicious activity. When triggered, read the full SKILL.md file at the skill location before calling any tool or writing any response.
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
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
-
low Risky intent
intent-offensive-securitySKILL.md:190Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Malware**: Linked to ransomware or malware payment wallets.
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (metacomp_visionx_kyt) differs from the folder (metacomp-visionx-kyt)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 54 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 3904 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
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)
- -268 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 329: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 54 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.