Ready to supercharge your AI agents?

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

Get Started Free →

LLMQuant Risk | DecimalAI

financeby llmquant

LLMQuant Risk

llmquant/llmquant-risk

Source llmquant/skills ↗License MIT

Router skill for LLMQuant risk workflows.

SkillScore36Maintained

Automatic

Finance & Accounting pack

Last verified 9/19/2026

What it changes

Passed 8 of 22 test cases with the skill, and 6 of 22 without it.

Without skill27%

With skill36%

Checks it passed that the model alone missed

Must include a stale evidence notice.
Must report the data coverage window.
Must audit outdated economic evidence.

and 4 more in the full report

4 fixed4 passed either way12 still failing2 broke

Pass-rate lift: +9 pp
Tokens: +5%
Agent turns: 0%
Response time: +2%

Model gemini-3.6-flashMeasured 9/19/2026v18 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-risk/SKILL.md https://app.decimal.ai/s/llmquant-llmquant-risk/SKILL.md

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

decimalai skills add llmquant-llmquant-risk

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

Review my macro research entries regarding rate cuts to flag outdated economic evidence and stale profiles. Report timestamps, coverage windows, and data gaps.

What was checked, without and with the skill
Checked	Without skill	With skill
Must audit outdated economic evidence.	Missed	Passed
Must report the data coverage window.	Missed	Passed
Must include an explicit analysis timestamp.	Missed	Passed

case-17 · gemini-3.6-flash · 9/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md31 lines3 filesincludes scripts

LLMQuant Risk

This category routes risk regime, hedging, panic scoring, and research-quality workflows.

Routing Rules

Identify the asset, portfolio, risk horizon, drawdown tolerance, and required decision.
Select the closest workflow below.
Open only the selected workflow.
Use LLMQuant Data for prices, volatility, options, macro, portfolio positions, alerts, profiles, and watchlists.
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`
Translate VIX into an options-risk regime.	`workflows/vix-status.md`
Design protective puts, collars, and put-spread hedges.	`workflows/hedge-advisor.md`
Audit stale profiles, thesis drift, orphan themes, and outdated evidence.	`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.

Track record

Benchmark

8 / 22

test cases passed, vs 6 / 22 without

Adoption

Users: 1
Times used: 12

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-risk/SKILL.md

View on GitHub ↗

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

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 Risk

Routing Rules

Workflow Index

LLMQuant Data Contract

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills