SKILLEMALL.ai
GitHub ↗ RU Sign in

DC rozo-checkout

Use when an agent needs to pay OpenRouter (or any Coinbase invoice) with the crypto it already holds: USDT/USDC on Solana, BNB Chain, Ethereum or Polygon, USDC on Base or Stellar, or BTC over Lightning, with no Coinbase account. A bridge creates a one-time deposit order for that coin, then a funder wallet settles the Coinbase invoice. Triggers on a payments.coinbase.com/payment-links/pl_* (or payment-sessions/paymentSession_*) URL, on "rozo-checkout" / "pay this link with bitcoin", or when a user asks to top up OpenRouter credits with crypto and has no link yet (OpenRouter's crypto credits API returns 410 Gone). Also pays a Bitrefill invoice created with "USDC on Base": triggers on "pay bitrefill", "bitrefill invoice", or an invoice id plus a Base USDC address and amount from Bitrefill. Supports Coinbase payment links and Bitrefill invoices only (not Stripe). Also pays any x402 API (HTTP 402, PAYMENT-REQUIRED) from a prepaid Rozo balance: triggers on "x402", "402 Payment Required", "pay this x402 endpoint"; the payment leg is USDC on Base only (Solana payment leg is coming later).

ClawHub Agent Skills author: Shawn Muggle v0.1.19 MIT-0 22 files · 5 scripts body ≈ 8 860 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

Use when an agent needs to pay OpenRouter (or any Coinbase invoice) with the crypto it already holds: USDT/USDC on Solana, BNB Chain, Ethereum or Polygon…

As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost

IntegrationStripeFinanceCommercetype 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
D
69/100
safety, quality, tests
Safety 60%
83
Quality 40%
48
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Execution cost w 6
40
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 17

✓ No critical or high findings

Medium and low: 17
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.es.md:153
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "receiverAddress": "9WzD…WWM",
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.es.md:156
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "payTo": "9WzD…WWM"
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.es.md:303
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "txHash": "3Bxs…h5c"
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.ja.md:135
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "receiverAddress": "9WzD…WWM",
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.ja.md:138
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "payTo": "9WzD…WWM"
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.ja.md:279
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "txHash": "3Bxs…h5c"
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.md:146
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "receiverAddress": "9WzD…WWM",
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.md:149
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "payTo": "9WzD…WWM"
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.md:295
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "txHash": "3Bxs…h5c"
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.zh.md:124
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "receiverAddress": "9WzD…WWM",
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.zh.md:127
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "payTo": "9WzD…WWM"
    quoted
  • low Secrets in code secret-high-entropy-token docs/QUICKSTART.zh.md:254
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "txHash": "3Bxs…h5c"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/dist/blacklist.json:22
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x8F…c2a",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/dist/blacklist.json:29
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0xa9…7dB",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/dist/blacklist.json:36
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x57…897",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/dist/blacklist.json:43
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "AEEt…HiH",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/dist/blacklist.json:50
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "TBce…cGu",
    quoted

Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1098 chars, limit 1024
  • warning body-long SKILL.md body ≈ 8860 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 622): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 61/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 8860 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 24 steps
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 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)
  • +3Description length 1097: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -411 reference files, but SKILL.md never points to them: the model will not open them
  • +2Single-language instructions
  • +5Description quotes 7 example trigger phrases
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 24 items
  • +4Has examples (13 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 48.

External checks

ClawHub: clean
This skill is a disclosed crypto-payment helper with real financial-transfer risk, but its sensitive behavior is purpose-aligned, documented, and guarded by confirmation and send controls.
LLM: benign (high) · VirusTotal: · 10 Oct 2026