SKILLEMALL.ai
GitHub ↗ RU Sign in

AB Vincent - Polymarket for agents

Polymarket prediction market trading for agents. Use this skill when users want to create a Polymarket wallet, browse markets, place bets, manage positions, or withdraw funds. Triggers on "polymarket", "prediction market", "place bet", "browse markets", "trade prediction", "polymarket wallet", "betting", "market odds".

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 4 895 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Polymarket prediction market trading for agents.

As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, consistency

ProcedureTelegramAI 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
A
91/100
safety, quality, tests
Safety 60%
95
Quality 40%
86
Run on models
none yet
Process rating
B
66/100
Nearly there
Inputs and preconditions w 11
0
Consistency w 8
40
Failures and branches w 10
50
the three weakest of ten parameters · all ten

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • low Secrets in code secret-high-entropy-token SKILL.md:96
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      2. Send USDC.e (bridged USDC, contract `0x27…174`) on Polygon to that address
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:99
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      **Do not send native USDC** (`0x3c…359`). Polymarket only accepts bridged USDC.e.
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:109
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      --token-in 0x83…913 --amount 10 \
      detector
    • low Secrets in code secret-high-entropy-token SKILL.md:110
      High-entropy token-like string (may be an id, hash or a credential)
      --token-out 0x27…174 --slippage 100
    • low Secrets in code secret-high-entropy-token SKILL.md:115
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      --token-in 0x83…913 --amount 10 \
      detector

    Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
    • note frontmatter-key unknown frontmatter key "homepage"
    • note frontmatter-key unknown frontmatter key "source"

    Process rating: all ten parameters 66/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 40Consistency. Frontmatter name (Vincent - Polymarket for agents) differs from the folder (vincentpolymarket)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 70Execution cost. Instruction body is 4895 tokens
    • 85Steps. 62 steps, 2 vague phrases
    • 100Tools and files. Tools declared in frontmatter
    • 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 The response is described with custom markup (3 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)
    • +2Single-language instructions
    • +5Description quotes 8 example trigger phrases
    • +3Description length 320: enough signal without eating the budget
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 62 items
    • +3Output format is stated explicitly
    • +4Has examples (23 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.