SKILLEMALL.ai

BC decision-gate-verifier

Independent third-party verification that an AI agent's action matched what it committed to beforehand - the part a self-authored audit log cannot prove. PAYING TAKES ONE SIGNATURE: x402 native, so your agent signs an authorization and retries - it never sends a transaction, never needs ETH, no account, no API key, no wallet approval. You need USDC on Base and nothing else. Use when you must show someone who won't take your word that an agent stayed inside its policy: donations, payouts, autonomous spending, irreversible releases. Returns PASS, REFUSE or IN_DOUBT with an oracle-signed receipt anchored on Base that anyone can independently re-derive; a mismatch is a fraud proof. Paid the same either way, so there is no incentive to rubber-stamp. PRICE: $0.05 USDC per check, no subscription. Verified live on Base mainnet: settle + anchor in 3.5s with the buyer's ETH balance unchanged. Check a real receipt: soulscore.xyz/proof. TRIGGERS: verify agent action, prove agent compliance, third-party audit, did my agent follow policy, conformance check, signed receipt, x402, pay per call, agentic payment, check before sending, prove no money moved.

ClawHub Agent Skills author: vaahl-dev v0.4.1 MIT-0 3 files body ≈ 1 506 tokens Open the sourceclawhub.ai analyzed 2 d ago

Independent third-party verification that an AI agent's action matched what it committed to beforehand - the part a self-authored audit log cannot prove.

As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
77/100
safety, quality, tests
Safety 60%
98
Quality 40%
46
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Secrets in code secret-high-entropy-token client.py:51
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    DEFAULT_REGISTRY_ADDRESS = "0x2C…ce9"
    quoted
  • low Secrets in code secret-high-entropy-token client.py:52
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    DEFAULT_USDC_ADDRESS = "0x83…913"  # Base mainnet USDC
    quoted

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1156 chars, limit 1024
  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Independent third-party verification that an AI agent's action mat… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 5 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 5 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1506 tokens
  • 100Progress reporting. Reports progress

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)
  • +3Description length 1156: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 5 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 46.

External checks

ClawHub: suspicious
This skill is a coherent paid verifier, but it asks agents to handle wallet private keys and sign live USDC payment authorizations with broad triggers and limited built-in spending safeguards.
LLM: suspicious (high) · 14 Aug 2026