Trade Validation

10-dimension weighted scoring framework for prediction market trade evaluation. Enforces disciplined position sizing, circuit breakers, and mandatory counter-arguments. Use when: evaluating prediction market trades, scoring opportunities, deciding position sizes, comparing Polymarket/Kalshi opportunities, running pre-trade checklists. Don't use when: general crypto analysis, DeFi yield farming, non-prediction-market investments, stock/equity analysis, sports betting (different framework needed). Negative examples: - "Should I buy ETH?" → No. This is for prediction markets with binary/discrete outcomes. - "What's the best DeFi yield?" → No. Wrong domain entirely. - "Score this sports bet" → No. Sports betting has different dimensions (injuries, matchups). Edge cases: - Crypto prediction markets (e.g., "Will BTC hit $X?") → YES, use this if on Polymarket/Kalshi. - Multi-outcome markets → Score each outcome separately. - Markets with <$25 liquidity → Auto-fail on Liquidity dimension.

This skill is an opinionated, self-contained scoring and discipline framework — not an automated trading connector. Before installing or using it, confirm: (1) your agent's network access and browsing behavior — the rubric expects consulting external sources; (2) your agent's filesystem permissions — the skill suggests logging to projects/polymarket/trade-journal/ and will create or write files if allowed; (3) you have NOT given this skill any exchange or wallet credentials (it requests none); (4) you understand the financial limits it enforces (dollar thresholds, veto rules) and whether those match your bankroll and risk tolerance; and (5) you accept that outputs are advisory and not professional financial advice. If you want to allow the agent to execute trades automatically, treat that as a separate decision and restrict credentials and permissions accordingly.

Type: OpenClaw Skill Name: trade-validation Version: 1.0.0 The skill bundle provides a detailed framework for prediction market trade evaluation and instructs the AI agent to apply this framework, including logging trade results to a local journal. All instructions in SKILL.md and content in references/scoring-rubric.md are directly aligned with the stated purpose. There is no evidence of prompt injection attempting to subvert the agent's behavior, exfiltrate data, execute malicious commands, or establish persistence. The file writing instruction for the trade journal is a legitimate function of the skill, not an indicator of malicious intent.