llmquant-investor-lenses — Claude Code skill: how to install
llmquant-investor-lenses routes stock and asset evaluations through investor frameworks like Buffett, Graham, or Taleb using LLMQuant Data fundamentals.
MIT 500 installs ★ 248 updated 2026-05-30
npx skills add LLMQuant/skills --skill llmquant-investor-lenses -a claude-codeWhat llmquant-investor-lenses does
The skill acts as an analytical router for investment research. When you query a ticker, the agent checks the asset, investment horizon, and desired lens, then loads the relevant markdown workflow. It covers approaches from Warren Buffett's moat criteria to Nassim Taleb's antifragile barbell checks and Michael Burry's filing-focused downside analysis.
All external numbers must come directly from LLMQuant Data. The workflow inspects corporate filings, 13F ownership records, prices, and macro indicators, keeping retrieved facts strictly separate from persona speculation.
Missing inputs change how the analysis proceeds. If LLMQuant Data lacks a specific valuation metric, the agent explicitly names the gap instead of guessing. Without access to LLMQuant Data, the workflow operates entirely on manually supplied figures.
What it helps with
- evaluate a company using Warren Buffett's economic moat and margin of safety
- run quantitative value screening based on Benjamin Graham's rules
- assess tail risk and convexity using Nassim Taleb's antifragile framework
- verify asset metrics against SEC filings and 13F ownership records
Example prompts for the agent
- Evaluate MSFT using the Warren Buffett workflow with LLMQuant Data metrics.
- Check TSLA downside risk using Michael Burry's filing-first lens.
- Apply Aswath Damodaran's story-and-numbers valuation to NVDA.
How to install llmquant-investor-lenses
1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-investor-lenses -a claude-code2Manually: put the files in place
~/.claude/skills/llmquant-investor-lenses/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llmquant-investor-lenses/
1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-investor-lenses -a codex2Manually: put the files in place
.agents/skills/llmquant-investor-lenses/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-investor-lenses -a cursor2Manually: put the files in place
.cursor/skills/llmquant-investor-lenses/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install LLMQuant/skills skills/llmquant-investor-lenses2Manually: put the files in place
.github/skills/llmquant-investor-lenses/SKILL.md1Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-investor-lenses -a gemini-cli2Platform CLI
gemini skills install https://github.com/LLMQuant/skills --path skills/llmquant-investor-lensesManually: put the files in place
.devin/skills/llmquant-investor-lenses/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add LLMQuant/skills --skill llmquant-investor-lenses -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-investor-lenses
How do I install llmquant-investor-lenses in Claude Code?
Run npx skills add LLMQuant/skills --skill llmquant-investor-lenses -a claude-code. The file will be placed in ~/.claude/skills/llmquant-investor-lenses/SKILL.md.
What does llmquant-investor-lenses do?
It routes your investment research prompt to a matching investor framework, such as Buffett, Graham, or Taleb, grounding the reasoning in LLMQuant Data.
How does the skill handle missing data points?
The skill strictly forbids generating fictional metrics or investor quotes. It flags the missing input and proceeds using only retrieved facts or user-supplied details.
Source text
SKILL.md · MIT
--- name: llmquant-investor-lenses description: Router skill for LLMQuant investor-lens workflows. Use when the user wants an investor-style reasoning overlay grounded in LLMQuant Data evidence. input_data_source: LLMQuant Data category: investor-lenses --- # LLMQuant Investor Lenses This category routes investor-style reasoning overlays. The named workflows are analytical lenses, not claims of endorsement or replication. All external evidence must come from LLMQuant Data. ## Routing Rules 1. Identify the requested investor lens, ticker/asset, horizon, and decision type. 2. Select the closest workflow below. 3. Open only that workflow and any local resources explicitly referenced by that workflow. 4. Use LLMQuant Data for filings, prices, fundamentals, ownership, macro, and valuation evidence. 5. Separate evidence from interpretation and avoid unsupported persona claims. ## Workflow Index | User intent | Workflow | |---|---| | Long-term owner lens: moat, circle of competence, and margin of safety. | [`workflows/warren-buffett.md`](workflows/warren-buffett.md) | | Quantitative value and margin-of-safety discipline. | [`workflows/ben-graham.md`](workflows/ben-graham.md) | | Multi-model quality investor with inversion discipline. | [`workflows/charlie-munger.md`](workflows/charlie-munger.md) | | Dhandho, cloning, and low-risk doubles. | [`workflows/mohnish-pabrai.md`](workflows/mohnish-pabrai.md) | | Emerging-market compounder and ROE-first selection. | [`workflows/rakesh-jhunjhunwala.md`](workflows/rakesh-jhunjhunwala.md) | | GARP, ten-baggers, and simple explainable businesses. | [`workflows/peter-lynch.md`](workflows/peter-lynch.md) | | Qualitative growth and scuttlebutt-style research. | [`workflows/phil-fisher.md`](workflows/phil-fisher.md) | | Disruptive innovation, Wright's Law, and exponential TAM. | [`workflows/cathie-wood.md`](workflows/cathie-wood.md) | | Macro liquidity regime and asymmetric sizing. | [`workflows/stanley-druckenmiller.md`](workflows/stanley-druckenmiller.md) | | Concentrated activist value and catalyst unlocks. | [`workflows/bill-ackman.md`](workflows/bill-ackman.md) | | Contrarian deep value and filing-first downside work. | [`workflows/michael-burry.md`](workflows/michael-burry.md) | | Tail-risk, barbell, convexity, and antifragile thinking. | [`workflows/nassim-taleb.md`](workflows/nassim-taleb.md) | | Story-plus-numbers valuation discipline. | [`workflows/aswath-damodaran.md`](workflows/aswath-damodaran.md) | | Mechanical Buffett-style business, moat, management, and valuation scorecard. | [`workflows/warren-buffett-scorecard.md`](workflows/warren-buffett-scorecard.md) | | Seller-only quality-business options framework. | [`workflows/duan-yongping-seller.md`](workflows/duan-yongping-seller.md) | | Cycle-position offense/defense signal. | [`workflows/howard-marks-cycle.md`](workflows/howard-marks-cycle.md) | | Rare panic-buy gate for liquid quality exposure. | [`workflows/david-tepper-panic-signal.md`](workflows/david-tepper-panic-signal.md) | ## LLMQuant Data Contract Prefer LLMQuant Data when available. The workflows may need these data capabilities: - Retrieve filings, fundamentals, valuation inputs, market prices, 13F ownership, macro indicators, options context, credit context, and sentiment evidence. - Support investor-lens analysis with dated evidence rather than persona-style assertions. - Preserve the distinction between retrieved facts, user-provided assumptions, and the selected investor framework. Fallback: - If a lens needs unavailable data, name the missing input and continue only with retrieved or user-provided evidence. - Do not invent quotes, holdings, valuation inputs, or biographical claims.
© LLMQuant · MIT · LLMQuant/skills