affaan-m avatar

Prediction Market Risk Review

A pre-flight checklist for any prediction market workflow before it touches real auth, portfolio data, or trade execution. It walks through five gates: advice boundary (strip recommendations, keep it informational), venue rules (geography, rate limits, regulatory ambiguity), data quality (liquidity, spreads, timestamps), security (no private keys in logs, read-only by default), and privacy (redact PII, minimize exposure). The output is a structured pass/warn/fail report with blocked actions and required mitigations. Honest take: this is defensive scaffolding. If you're building agents that could place real trades or handle financial data, you want this kind of guardrail baked in early, not bolted on after an incident.

skills.sh installs
801
GitHub stars
229.1K
last updated
Jul 14, 2026

Install

$ npx -y skills add affaan-m/everything-claude-code --skill prediction-market-risk-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Prediction Market Risk Review

Use this skill before a prediction-market workflow touches user financial context, venue authentication, portfolio data, automation, or execution-capable tools.

Review Gates

Advice Boundary

  • Confirm the output is informational.
  • Remove buy/sell/hold/size recommendations.
  • Keep manual user decision points explicit.

Venue And Regulatory Boundary

  • Identify venue terms, geography restrictions, account limits, and API rules.
  • Flag betting, derivatives, securities, or commodities ambiguity for legal review when relevant.
  • Do not bypass venue restrictions or rate limits.

Data Quality

  • Check market liquidity, spread, resolution rules, stale prices, and source timestamps.
  • Separate public venue data from Itô gated data.
  • Do not mix public and private sources without labels.

Security

  • Do not request or store private keys, seed phrases, or passwords.
  • Keep ITO_API_KEY and venue API keys out of logs and docs.
  • Use read-only scopes by default.
  • Require circuit breakers, spend limits, dry runs, and human approval before any private implementation adds execution.

Privacy

Sponsors

Details

Repository
github.com/affaan-m/everything-claude-code
Categories
Git & Pull Requests, Code Review & Quality
First seen
Jul 14, 2026

More from affaan-m/everything-claude-code

All 256
1majiayu000 avatargithub-trendingmajiayu000/claude-arsenalgithub trending788skills.sh installs
2bobmatnyc avatargithub-actionsbobmatnyc/claude-mpm-skillsGitHub Actions CI/CD workflows for automating build, test, and deployment771skills.sh installs
3dalestudy avatargithub-actionsdalestudy/skillsGitHub Actions 워크플로우 생성, 보안 및 버전 관리 스킬. 다음 상황에서 사용: (1) 새 워크플로우 파일(.yml) 작성 시, (2) 기존 워크플로우 수정 시, (3) 액션 버전 검토 또는 업데이트 시, (4) CI/CD 보안 감사 시, (5) 'actions/', 'us743skills.sh installs
4collaborative-deep-research avatarliterature-reviewcollaborative-deep-research/agent-papers-cliConduct a systematic literature review on an academic topic. Use when the user asks for a literature review, survey, or systematic overview of a research area.741skills.sh installs
5parcadei avatargithub-searchparcadei/continuous-claude-v3Search GitHub code, repositories, issues, and PRs via MCP740skills.sh installs
6hugorcd avatarreview-logging-patternshugorcd/evlogReview code for logging patterns and suggest evlog adoption. Optionally use @evlog/cli (`evlog init` to wire evlog, `evlog agents` to write the conventions into728skills.sh installs