Ready to supercharge your AI agents?

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

Get Started Free →

LLMQuant Commodities | DecimalAI

financeby llmquant

LLMQuant Commodities

llmquant/llmquant-commodities

Source llmquant/skills ↗License MIT

Router skill for LLMQuant commodities workflows.

SkillScore100Maintained

Automatic

Finance & Accounting pack

Last verified 9/26/2026

What it changes

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

Without skill43%

With skill100%

Checks it passed that the model alone missed

The response states that contract dates must be reported.
The response declines to output memory-based spot prices.
The response refrains from fabricating warehouse inventory figures.

and 13 more in the full report

13 fixed10 passed either way0 still failing0 broke

Pass-rate lift: +57 pp
Tokens: -11%
Agent turns: 0%
Response time: -23%

Model gemini-3.6-flashMeasured 9/26/2026v123 of 23 cases passed with skill · 22 comparable

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-commodities/SKILL.md https://app.decimal.ai/s/llmquant-llmquant-commodities/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add llmquant-llmquant-commodities, 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-commodities/ and pins it in .decimal/skills.lock

decimalai skills add llmquant-llmquant-commodities

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

A quant analyst wants to quantify the annualized roll yield across the NYMEX RBOB Gasoline futures curve to determine the cost of carry for a long position. Which workflow file governs this procedure?

What was checked, without and with the skill
Checked	Without skill	With skill
The response identifies `workflows/futures-curve-monitor.md` as the governing workflow.	Missed	Passed

case-19 · 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 Commodities

This category routes commodity research and futures-curve workflows. It defines the LLMQuant Data inputs required even when some commodity endpoints are future product surface.

Routing Rules

Identify the commodity, contract codes, region, horizon, and output target.
Select the closest workflow below.
Open only that workflow and relevant local resources.
Use LLMQuant Data for spot, futures, inventory, macro, FX, and rate inputs.
Report contract dates, observation dates, source coverage, and missing inputs.

Workflow Index

User intent	Workflow
Build a commodity market brief across price, curve, inventory, macro, and equities.	`workflows/commodity-market-lens.md`
Analyze futures term structure, roll yield, contango/backwardation, and curve shifts.	`workflows/futures-curve-monitor.md`

LLMQuant Data Contract

Prefer LLMQuant Data when available. The workflows may need these data capabilities:

Retrieve commodity spot or front-month prices, recent changes, volume, and observation timestamp.
Retrieve futures curves by contract month, including curve shape, roll yield, volume, and open interest.
Retrieve inventory, production, demand, import/export, weather, and commodity event context.
Retrieve macro indicators, rates, FX, inflation, growth, and related equity or ETF price proxies.

Fallback:

If commodity data is not available, list the exact inputs needed and continue only with available macro, market, or user-provided evidence.
Do not infer spot prices, inventories, or curve shape from memory.

Track record

Benchmark

22 / 22

test cases passed, vs 10 / 22 without

Adoption

Users: 1
Times used: 1

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-commodities/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 Commodities

Routing Rules

Workflow Index

LLMQuant Data Contract

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills