validate(signal, portfolio_state) → risk gate result
Direct query: "What's my current drawdown?"
Direct query: "Is it safe to open a new BTC position?"
Data Sources
Portfolio state from portfolio_management
config/fund_policy.py — fund-level risk limits
Runtime PnL from execution engine
Query Interface
/risk_guard?ticker=BTC/USDT&side=long&size=0.5
Returns: approved/blocked + per-gate flags.
Dependencies
fund_policy for limits
Portfolio state estimator
1---2name: risk-guard3description: Skill: Risk Guard4---5# Skill: Risk Guard67## Capabilities8- `validate(signal, portfolio_state)` → risk gate result9- Direct query: "What's my current drawdown?"10- Direct query: "Is it safe to open a new BTC position?"1112## Data Sources13- Portfolio state from `portfolio_management`14- `config/fund_policy.py` — fund-level risk limits15- Runtime PnL from execution engine1617## Query Interface18```19/risk_guard?ticker=BTC/USDT&side=long&size=0.520```21Returns: approved/blocked + per-gate flags.2223## Dependencies24- `fund_policy` for limits25- Portfolio state estimator
Run npx skillmds@latest add olaxbt/risk-guard in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Skill: Risk Guard It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
olaxbt (@olaxbt) published this skill. Their other Agent Skills are listed on their SkillMD profile.
olaxbt