SKILLEMALL.ai
GitHub ↗ RU Sign in

BF sports-betting

Place and claim decentralized sports bets on-chain via Pinwin and Azuro: real-time odds, high liquidity, no custody. Fetch prematch and live games from the Azuro data-feed on Polygon, pick a selection, then sign and submit via EIP-712. Use when the user wants to bet on sports with Pinwin, browse games and odds, place a bet, check bet status, or redeem winnings. Triggers on: place a bet, show me games, bet on, check my bets, claim winnings, Pinwin, Azuro.

ClawHub Agent Skills author: skinnynoizze v1.3.1 MIT-0 10 files body ≈ 6 521 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 41/100 · Will not run — References files that are not bundled: references/subgraph.md

ProcedureInfrastructuretype 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
81/100
safety, quality, tests
Safety 60%
89
Quality 40%
70
Run on models
none yet
Process rating
F
41/100
Will not run
References files that are not bundled: references/subgraph.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
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 · 11

✓ No critical or high findings

Medium and low: 11
  • low Secrets in code secret-high-entropy-token scripts/claim-bets.js:24
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    const CLAIM_CONTRACT    = '0x0F…1b8'
    detector
  • low Secrets in code secret-high-entropy-token scripts/place-bet.js:19
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const USDT           = '0xc2…e8F'
    quoted
  • low Secrets in code secret-high-entropy-token scripts/place-bet.js:20
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const RELAYER        = '0x8d…a9d'
    quoted
  • low Secrets in code secret-high-entropy-token scripts/place-bet.js:21
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const CLIENT_CORE    = '0xF9…AC7'  // Azuro ClientCore for betting
    quoted
  • low Risky intent intent-wallet-secrets SKILL.md:4
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
    compatibility: "Requires Node, viem and @azuro-org/dictionaries. Required env: BETTOR_PRIVATE_KEY (wallet private key; high-sensitivity). Optional env: POLYGON_RPC_URL."
    detector
  • low Secrets in code secret-high-entropy-token SKILL.md:48
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **betToken (USDT)** | `0xc2…e8F` (6 decimals) |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:49
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **relayer** | `0x8d…a9d` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:50
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **clientCore** (bet payload verification) | `0xF9…AC7` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:51
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **claimContract** (LP claim, redeem won/canceled bets) | `0x0F…1b8` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:116
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const USDT = '0xc2…e8F'
    quoted
  • low Dangerous commands cmd-autorun-instruction SKILL.md:578
    Instructs the agent to auto-run a script on every session (security demo / example)
    | Payload stake = 0 after `/agent/bet` | **Always run `place-bet.js --dry-run` first to see request body.** Likely causes: (1) `outcomeId` not valid for that `conditionId` — always take both from the
    demo

Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6521 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/subgraph.md
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 41/100

Will not run. References files that are not bundled: references/subgraph.md
  • 0Tools and files. 1 referenced file(s) missing: references/subgraph.md
  • 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. 7 mutating operations with no state check
  • 60Steps. 41 steps, 4 vague phrases
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 6521 tokens
  • 100Failures and branches. 18 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +1No license
  • +2Single-language instructions
  • +3Description length 458: enough signal without eating the budget
  • +4Structure: 21 headings
  • +3Step-by-step instructions: 41 items
  • +4Has examples (23 code blocks)
  • +3All 4 scripts are documented

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

External checks

ClawHub: suspicious
This is a real sports-betting wallet skill, but it needs review because it handles irreversible transactions and its transaction safeguards are not as tight as the instructions imply.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026