SKILLEMALL.ai
GitHub ↗ RU Sign in

BC rozo-intents

Cross-chain crypto payments and bridging via Rozo. Send USDC/USDT across Ethereum, Arbitrum, Base, BNB Chain (BSC), Polygon, Solana, and Stellar (Base and Stellar are USDC-only; Solana receives USDC only but can pay in USDT). On Stellar the trustline checker can also verify EURC trustlines; EURC is trustline-verification only, never a payment token here. Use when the user asks to pay, send, transfer, or bridge crypto/USDC/USDT, check a wallet or USDC/USDT balance, check a crypto payment's status, or shares a crypto payment QR code screenshot, a wallet address (0x, base58, G/C stellar), or a transaction hash. Auto-detects wallet type and auto-selects token (USDC preferred). Every payment shows full details and waits for an explicit yes/no by default. Small-amount auto-execute is opt-in: it runs only if the user raises the confirmation thresholds in version.json (shipped 0 = off). Do NOT use for general blockchain questions, non-payment tasks, or ordinary fiat payments, bank transfers, or bank-account balance questions.

ClawHub Agent Skills author: Shawn Muggle v1.0.9 MIT-0 17 files body ≈ 1 286 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

AnalyzerInfrastructureSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
92
Quality 40%
61
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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 · 8

✓ No critical or high findings

Medium and low: 8
  • low Secrets in code secret-high-entropy-token references/supported-chains.md:22
    High-entropy token-like string (may be an id, hash or a credential)
    | Solana | 900 | EPjF…t1v | 6 |
  • low Secrets in code secret-high-entropy-token references/supported-chains.md:33
    High-entropy token-like string (may be an id, hash or a credential)
    | Solana | 900 | Es9v…NYB | 6 |
  • low Secrets in code secret-high-entropy-token references/supported-chains.md:46
    High-entropy token-like string (may be an id, hash or a credential)
    | Solana | 900 | EPjF…t1v | 6 |
  • low Secrets in code secret-high-entropy-token scripts/dist/chains.js:18
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    900: { address: "EPjF…t1v", decimals: 6 },
    quoted
  • low Secrets in code secret-high-entropy-token scripts/dist/chains.js:26
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    900: { address: "Es9v…NYB", decimals: 6 },
    quoted
  • low Secrets in code secret-high-entropy-token scripts/dist/chains.js:36
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    900: { address: "EPjF…t1v", decimals: 6 },
    quoted
  • low Secrets in code secret-high-entropy-token scripts/dist/parse-qr.js:35
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "EPjF…t1v": "USDC",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/dist/parse-qr.js:36
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Es9v…NYB": "USDT",
    quoted

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1034 chars, limit 1024

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 16 mutating operations with no state check
  • 40Consistency. Frontmatter name (rozo-intents) differs from the folder (rozo-intents-skills)
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 100Steps. 10 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 6 branches, has a failure section
  • 100Execution cost. Instruction body is 1286 tokens

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
  • +3Description length 1033: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 10 items
  • +4Reference files are cited in the instructions (3 of 3)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.

External checks

ClawHub: suspicious
This skill is openly for crypto payments, but it includes an opt-in mode that can move funds without a fresh per-payment confirmation.
LLM: suspicious (high) · 11 Aug 2026