llmquant-portfolio-lab — Claude Code skill: exposure maps and what-if
A router skill for portfolio work: exposure maps, scenario states and virtual portfolio comparisons for real or hypothetical holdings.
npx skills add LLMQuant/skills --skill llmquant-portfolio-lab -a claude-codeWhat llmquant-portfolio-lab does
The skill pulls apart a request into portfolio ID, holdings list, benchmark, scenario and the output you want. Then it picks one of two workflows and opens only that one plus the local assets and scripts it needs. The first workflow maps exposure by holdings, sectors, factors, geography, ETF look-through and concentration. The second runs simulations: adds, trims, hedges, shocks and virtual portfolio states.
Data comes from LLMQuant Data — positions, prices, factor exposures, risk model outputs, scenarios. If the portfolio APIs are not reachable, the skill asks for a holdings table or builds a structured input template. It will not make up weights, holdings, factor exposures or scenario returns; the instructions say so outright.
Reports carry as-of dates, model dates, the benchmark, missing holdings and unsupported asset types. That matters in practice: a date mismatch or a gap in the holdings list shows up before the numbers reach a deck. Worth installing if you already have LLMQuant Data access or a holdings table ready to hand.
What it helps with
- map portfolio exposure by sector and factor
- work out ETF look-through and find overlapping names
- simulate an add or trim in a virtual portfolio
- compare current and pro forma portfolio states
- spot holdings missing from the source data
Example prompts for the agent
- map the exposure of my portfolio by sector and factor
- what happens if I add 5% to this ETF and trim the tech sleeve
- compare the current portfolio with the virtual one after the hedge
How to install llmquant-portfolio-lab
1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-portfolio-lab -a claude-code2Manually: put the files in place
~/.claude/skills/llmquant-portfolio-lab/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llmquant-portfolio-lab/
1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-portfolio-lab -a codex2Manually: put the files in place
.agents/skills/llmquant-portfolio-lab/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-portfolio-lab -a cursor2Manually: put the files in place
.cursor/skills/llmquant-portfolio-lab/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install LLMQuant/skills llmquant-portfolio-lab2Manually: put the files in place
.github/skills/llmquant-portfolio-lab/SKILL.md1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-portfolio-lab -a gemini-cli2Platform CLI
gemini skills install https://github.com/LLMQuant/skills --path skills/llmquant-portfolio-labManually: put the files in place
.devin/skills/llmquant-portfolio-lab/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-portfolio-lab -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-portfolio-lab
How do I install llmquant-portfolio-lab in Claude?
Run npx skills add LLMQuant/skills --skill llmquant-portfolio-lab -a claude-code. The skill lands in ~/.claude/skills/llmquant-portfolio-lab/SKILL.md.
What does llmquant-portfolio-lab do?
It routes portfolio requests to one of two workflows: an exposure map or a what-if simulator. Calculations run through LLMQuant Data, and it asks for a holdings table when the APIs are unavailable.
What data does the skill need?
Holdings, weights, a benchmark and an as-of date at minimum. Factor breakdowns and scenarios need risk model outputs and simulation results from LLMQuant Data.
Source text
SKILL.md · MIT
--- name: llmquant-portfolio-lab description: Router skill for LLMQuant portfolio-lab workflows. Use when the user needs portfolio exposure maps, what-if simulations, scenario states, or virtual portfolio comparisons. input_data_source: LLMQuant Data category: portfolio-lab --- # LLMQuant Portfolio Lab This category routes portfolio virtualization workflows: exposure maps, scenario states, and what-if simulations for real or hypothetical portfolios. ## Routing Rules 1. Identify portfolio ID, holdings list, benchmark, scenario, and requested visualization/output. 2. Select the closest workflow below. 3. Open only that workflow and relevant local assets/scripts. 4. Use LLMQuant Data for positions, prices, ETF look-through, factors, scenarios, and risk model outputs. 5. Report as-of dates, model dates, benchmark, missing holdings, and unsupported asset types. ## Workflow Index | User intent | Workflow | |---|---| | Map portfolio exposure by holdings, sectors, factors, geography, ETF look-through, and concentration. | [`workflows/portfolio-exposure-map.md`](workflows/portfolio-exposure-map.md) | | Simulate adds, trims, hedges, shocks, and virtual portfolio states. | [`workflows/portfolio-what-if-simulator.md`](workflows/portfolio-what-if-simulator.md) | ## LLMQuant Data Contract Prefer LLMQuant Data when available. The workflows may need these data capabilities: - Retrieve portfolio holdings, weights, cost basis, asset types, benchmarks, and as-of dates. - Retrieve factor exposures, sector/geography exposures, ETF look-through holdings, risk model outputs, and scenario simulation results. - Retrieve prices, correlations, drawdowns, volatility, option Greeks, and hedge context when relevant. - Compare current, pro forma, and hypothetical portfolio states. Fallback: - If portfolio APIs are unavailable, ask for a holdings table or build a structured portfolio input template. - Do not invent weights, holdings, factor exposures, or scenario returns.
© LLMQuant · MIT · LLMQuant/skills
