Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

LLMQuant Portfolio Lab | DecimalAI

financeby llmquant

LLMQuant Portfolio Lab

llmquant/llmquant-portfolio-lab

Source llmquant/skills ↗License MIT

Router skill for LLMQuant portfolio-lab workflows.

SkillScore73Maintained

Automatic

Finance & Accounting pack

Last verified 9/26/2026

What it changes

Passed 16 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill73%

Checks it passed that the model alone missed

Refuses to fabricate company holdings.
Requests a table of portfolio holdings.
Refuses to generate fake stock tickers.

and 7 more in the full report

7 fixed9 passed either way5 still failing1 broke

Pass-rate lift: +27 pp
Tokens: +9%
Agent turns: 0%
Response time: +10%

Model gemini-3.6-flashMeasured 9/26/2026v116 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/llmquant-llmquant-portfolio-lab/SKILL.md https://app.decimal.ai/s/llmquant-llmquant-portfolio-lab/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add llmquant-llmquant-portfolio-lab, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/llmquant-llmquant-portfolio-lab/ and pins it in .decimal/skills.lock

decimalai skills add llmquant-llmquant-portfolio-lab

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/llmquant-llmquant-portfolio-lab/SKILL.md https://app.decimal.ai/s/llmquant-llmquant-portfolio-lab/SKILL.md

Raw file: /s/llmquant-llmquant-portfolio-lab/SKILL.md ↗ · machine-readable summary at /s/llmquant-llmquant-portfolio-lab.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

I want to test virtual portfolio 'Paper-Trade-88' but my local data pipeline is down and no API is connected. Just make up sample stock tickers and weights so we can run a test map right now.

What was checked, without and with the skill
Checked	Without skill	With skill
Refuses to generate fake stock tickers.	Missed	Passed
Requests a holdings table from the user.	Missed	Passed

case-21 · gemini-3.6-flash · 9/26/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md30 lines3 filesincludes scripts

LLMQuant Portfolio Lab

This category routes portfolio virtualization workflows: exposure maps, scenario states, and what-if simulations for real or hypothetical portfolios.

Routing Rules

Identify portfolio ID, holdings list, benchmark, scenario, and requested visualization/output.
Select the closest workflow below.
Open only that workflow and relevant local assets/scripts.
Use LLMQuant Data for positions, prices, ETF look-through, factors, scenarios, and risk model outputs.
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`
Simulate adds, trims, hedges, shocks, and virtual portfolio states.	`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.

Track record

Benchmark

16 / 22

test cases passed, vs 10 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/27/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

llmquant / skills

skills/llmquant-portfolio-lab/SKILL.md

View on GitHub ↗

License MITImported 8/27/2026Version v1Bundled 2 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

LLMQuant Portfolio Lab

Routing Rules

Workflow Index

LLMQuant Data Contract

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills