Ready to supercharge your AI agents?

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

Get Started Free →

LLMQuant ETFs | DecimalAI

financeby llmquant

LLMQuant ETFs

llmquant/llmquant-etfs

Source llmquant/skills ↗License MIT

Router skill for LLMQuant ETFs workflows.

SkillScore87Maintained

Automatic

Finance & Accounting pack

Last verified 9/26/2026

What it changes

Passed 20 of 23 test cases with the skill, and 10 of 23 without it.

Without skill43%

With skill87%

Checks it passed that the model alone missed

States that stale flags must be reported.
Refuses to estimate ETF holdings from memory.
Refuses to approximate ETF holdings from memory.

and 9 more in the full report

10 fixed10 passed either way3 still failing0 broke

Pass-rate lift: +43 pp
Tokens: -28%
Agent turns: 0%
Response time: -44%

Model gemini-3.6-flashMeasured 9/26/2026v120 of 23 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-etfs/SKILL.md https://app.decimal.ai/s/llmquant-llmquant-etfs/SKILL.md

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

decimalai skills add llmquant-llmquant-etfs

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

I want to compare portfolio overlap between XLK and VGT. Which workflow document should be opened to execute this analysis?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies workflows/etf-overlap-report.md as the workflow to open.	Missed	Passed

case-04 · 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 ETFs

This category routes ETF analysis tasks to holdings and exposure workflows.

Routing Rules

Identify the ETF tickers, comparison universe, as-of date, and required output.
Select the closest workflow below.
Open only the selected workflow and required local resources.
Use LLMQuant Data for holdings, fund metadata, prices, and coverage notices.
Report holdings as_of_date, source, stale flags, unsupported tickers, and missing fields.

Workflow Index

User intent	Workflow
Compare ETF holdings, overlap, concentration, and exposure.	`workflows/etf-overlap-report.md`

LLMQuant Data Contract

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

Look up ETF identity, issuer, category, expense ratio, market price, NAV, and coverage status.
Retrieve ETF holdings with weights, identifiers, sectors, countries, source, and holdings as-of date.
Compare ETF holdings overlap, top-name concentration, and exposure breakdowns.
Retrieve price history, fund-flow history, and sector exposure history when available.

Fallback:

If holdings coverage is unsupported, report the unsupported ticker and the ETF identifiers needed.
If LLMQuant Data or a compatible data MCP is unavailable, ask the user for issuer holdings files or holdings tables.
Do not approximate holdings from memory.

Track record

Benchmark

20 / 23

test cases passed, vs 10 / 23 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-etfs/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 ETFs

Routing Rules

Workflow Index

LLMQuant Data Contract

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills