SKILLEMALL.ai
GitHub ↗ RU Sign in

BC polymarket-auto-trader

Autonomous Polymarket prediction market trading agent. Scans markets, evaluates probabilities with LLM, sizes positions with Kelly criterion, and executes trades via CLOB API. Use when user wants to trade on Polymarket, set up automated prediction market trading, or build a trading bot. Supports cron-based autonomous operation, P&L tracking, and budget management.

modbender/skill-library-mcp Agent Skills author: modbender MIT 7 files · 1 script body ≈ 1 116 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Autonomous Polymarket prediction market trading agent.

As a process C 54/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice

IntegrationAI and agentsInfrastructureSoftware 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
84/100
safety, quality, tests
Safety 60%
79
Quality 40%
91
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Running it twice w 4
30
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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

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 · 17

    ✓ No critical or high findings

    Medium and low: 17
    • medium Risky intent intent-wallet-secrets references/polymarket-api.md:12
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      1. Derive API key from wallet private key:
    • low Secrets in code secret-high-entropy-token references/contract-addresses.md:5
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | USDC.e (PoS Bridged) | `0x27…174` |
      table
    • low Secrets in code secret-high-entropy-token references/contract-addresses.md:6
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | USDC (Native) | `0x3c…359` |
      table
    • low Secrets in code secret-high-entropy-token references/contract-addresses.md:7
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | CTF (Conditional Tokens) | `0x4D…045` |
      table
    • low Secrets in code secret-high-entropy-token references/contract-addresses.md:8
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | CTF Exchange | `0x4b…82E` |
      table
    • low Secrets in code secret-high-entropy-token references/contract-addresses.md:9
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | Neg Risk Exchange | `0xC5…80a` |
      table
    • low Secrets in code secret-high-entropy-token scripts/approve_contracts.py:14
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      USDC_E = "0x27…174"
      quoted
    • low Secrets in code secret-high-entropy-token scripts/approve_contracts.py:15
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      CTF = "0x4D…045"
      quoted
    • low Secrets in code secret-high-entropy-token scripts/approve_contracts.py:16
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      CTF_EXCHANGE = "0x4b…82E"
      quoted
    • low Secrets in code secret-high-entropy-token scripts/approve_contracts.py:17
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      NEG_RISK_EXCHANGE = "0xC5…80a"
      quoted
    • low Secrets in code secret-high-entropy-token scripts/approve_contracts.py:18
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      NEG_RISK_ADAPTER = "0xd9…296"
      quoted
    • low Secrets in code secret-high-entropy-token scripts/pnl_tracker.py:23
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      USDC_E = "0x27…174"
      quoted
    • low Secrets in code secret-high-entropy-token scripts/run_trade.py:25
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      USDC_E = "0x27…174"
      quoted
    • low Dangerous commands cmd-cron-mention scripts/setup_vps.sh:33
      Mentions editing / listing crontab (string literal in code, not executed)
      echo "   crontab -e"
      code literal
    • low Dangerous commands cmd-cron-mention SKILL.md:64
      Mentions editing / listing crontab
      crontab -e
    • low Secrets in code secret-high-entropy-token SKILL.md:101
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      - **Token:** USDC.e (`0x27…174`), not native USDC
      detector
    • low Secrets in code secret-high-entropy-token SKILL.md:102
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **Neg-risk markets** (elections, sports leagues) require USDC.e approval for Neg Risk Adapter (`0xd9…296`)
      quoted

    Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 54/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 3 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 33 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1116 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)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 366: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 33 items
    • +4Has examples (8 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +3All 4 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.