llmquant-risk — Claude Code skill: risk workflows and setup
Routes risk requests to panic scoring, VIX regimes, hedge design, and research health checks when those workflows are needed.
npx skills add LLMQuant/skills --skill llmquant-risk -a claude-codeWhat llmquant-risk does
The skill first identifies the asset or portfolio, risk horizon, drawdown tolerance, and decision the user needs. It then routes the request to one workflow: a per-ticker panic score, a VIX-based options regime, protective puts, collars or put spreads, or a research health check for stale profiles, thesis drift, orphan themes, and old evidence.
Its workflow files are workflows/fear-score.md, workflows/vix-status.md, workflows/hedge-advisor.md, and workflows/research-health-check.md. The skill uses LLMQuant Data for prices, volatility, options, macro indicators, portfolio positions, alerts, profiles, and watchlists. Reports should include timestamps, data windows, stale-data notices, assumptions, and missing inputs. When portfolio or options data cannot be used, it produces a data-limited risk note.
What it helps with
- score panic for an individual ticker
- translate VIX into an options-risk regime
- design a protective options hedge
- audit stale research profiles and evidence
Example prompts for the agent
- Calculate a panic score for NVDA and show the data window.
- Translate the current VIX into an options-risk regime and explain the result.
- Design a protective put or collar for my portfolio and report the hedge cost.
How to install llmquant-risk
1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-risk -a claude-code2Manually: put the files in place
~/.claude/skills/llmquant-risk/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llmquant-risk/
1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-risk -a codex2Manually: put the files in place
.agents/skills/llmquant-risk/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-risk -a cursor2Manually: put the files in place
.cursor/skills/llmquant-risk/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install LLMQuant/skills llmquant-risk2Manually: put the files in place
.github/skills/llmquant-risk/SKILL.md1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-risk -a gemini-cli2Platform CLI
gemini skills install https://github.com/LLMQuant/skills --path skills/llmquant-riskManually: put the files in place
.devin/skills/llmquant-risk/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-risk -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about llmquant-risk
How do I install llmquant-risk in Claude Code?
Run npx skills add LLMQuant/skills --skill llmquant-risk -a claude-code, then check ~/.claude/skills/llmquant-risk/SKILL.md.
What does llmquant-risk do?
It routes a request to a workflow for ticker panic scoring, VIX regime analysis, options hedging, or research health checks.
What data does the skill use?
Its workflows can use LLMQuant Data for prices, volatility, options, macro risk indicators, portfolio positions, alerts, and research records. If portfolio or options data is unavailable, the result is a data-limited risk note.
Source text
SKILL.md · MIT
--- name: llmquant-risk description: Router skill for LLMQuant risk workflows. Use when the user needs fear scoring, VIX regime, hedge design, or research health checks. input_data_source: LLMQuant Data category: risk --- # LLMQuant Risk This category routes risk regime, hedging, panic scoring, and research-quality workflows. ## Routing Rules 1. Identify the asset, portfolio, risk horizon, drawdown tolerance, and required decision. 2. Select the closest workflow below. 3. Open only the selected workflow. 4. Use LLMQuant Data for prices, volatility, options, macro, portfolio positions, alerts, profiles, and watchlists. 5. Report timestamps, data windows, stale notices, assumptions, and missing inputs. ## Workflow Index | User intent | Workflow | |---|---| | Build a per-ticker panic score. | [`workflows/fear-score.md`](workflows/fear-score.md) | | Translate VIX into an options-risk regime. | [`workflows/vix-status.md`](workflows/vix-status.md) | | Design protective puts, collars, and put-spread hedges. | [`workflows/hedge-advisor.md`](workflows/hedge-advisor.md) | | Audit stale profiles, thesis drift, orphan themes, and outdated evidence. | [`workflows/research-health-check.md`](workflows/research-health-check.md) | ## LLMQuant Data Contract Prefer LLMQuant Data when available. The workflows may need these data capabilities: - Retrieve price history, volatility, drawdowns, correlations, market regime, VIX context, and macro risk indicators. - Retrieve option chains, implied volatility history, Greeks, hedge candidates, and liquidity context. - Retrieve portfolio positions, watchlists, alerts, research profiles, thesis records, and stale evidence. - Measure hedge cost, risk reduction, concentration, and unresolved data gaps. Fallback: - If portfolio or option data is unavailable, name the missing input and produce a data-limited risk note.
© LLMQuant · MIT · LLMQuant/skills