SKILLEMALL.ai
GitHub ↗ RU Sign in

BB ospex-one

Bet on sports with one word (or maybe, a few words). Say a team name, city, or abbreviation. 'Edmonton', 'Duke', 'Celtics', 'Lakers'. NBA, NHL, NCAAB.

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 5 files body ≈ 4 899 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Bet on sports with one word (or maybe, a few words).

As a process B 70/100 · Nearly there — weak spots: result and completion, running it twice

IntegrationData and analyticsAI and agentstype 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
83/100
safety, quality, tests
Safety 60%
81
Quality 40%
87
Run on models
none yet
Process rating
B
70/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

    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 · 15

    ✓ No critical or high findings

    Medium and low: 15
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: bash
      allowed-tools: bash exec
    • low Secrets in code secret-high-entropy-token PROMPT.md:256
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - USDC: `0x3c…359` (6 decimals)
      quoted
    • low Secrets in code secret-high-entropy-token PROMPT.md:257
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - PositionModule: `0xF7…B1A`
      quoted
    • low Secrets in code secret-high-entropy-token references/api-reference.md:63
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      Platform fees are **currently disabled**. The `feeTxHash` field on instant-match quote requests can be omitted. When fees are re-enabled, a 0.20 USDC payment to the fee wallet (`0xda…A18
      quoted
    • low Secrets in code secret-high-entropy-token references/api-reference.md:1022
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "core": "0x80…2aD",
      quoted
    • low Secrets in code secret-high-entropy-token references/api-reference.md:1023
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "usdc": "0x3c…359"
      quoted
    • low Secrets in code secret-high-entropy-token references/contract-interface-reference.md:15
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | USDC | `0x3c…359` (6 decimals) |
      table
    • low Secrets in code secret-high-entropy-token references/contract-interface-reference.md:16
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | PositionModule | `0xF7…B1A` |
      table
    • low Secrets in code secret-high-entropy-token references/contract-interface-reference.md:17
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | Moneyline Scorer | `0x82…045` |
      table
    • low Secrets in code secret-high-entropy-token references/contract-interface-reference.md:18
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | Spread Scorer | `0x43…4af` |
      table
    • low Secrets in code secret-high-entropy-token references/contract-interface-reference.md:19
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | Total Scorer | `0xD7…eCf` |
      table
    • low Risky intent intent-wallet-secrets SKILL.md:7
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      compatibility: "Requires Node and ethers.js v6. Required env: OSPEX_WALLET_PRIVATE_KEY (wallet private key; high-sensitivity — do not log or expose), OSPEX_WALLET_ADDRESS, OSPEX_RPC_URL (Polygon RPC).
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:112
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      1. **Contract address:** The contract address used in the script equals the PositionModule address from the On-Chain Reference section (`0xF7…B1A`). Never derive a co
      detector
    • low Secrets in code secret-high-entropy-token SKILL.md:287
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | USDC | `0x3c…359` (6 decimals) |
      table
    • low Secrets in code secret-high-entropy-token SKILL.md:288
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | PositionModule | `0xF7…B1A` |
      table

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 70/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 8 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Execution cost. Instruction body is 4899 tokens
    • 85Steps. 33 steps, 1 vague phrases
    • 100Tools and files. Tools declared in frontmatter
    • 100Failures and branches. 8 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Progress reporting. Reports progress
    • 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 150: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 33 items
    • +4Has examples (10 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.