New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Investor Lenses

by HKUDS in HKUDS/Vibe-Trading

Named investor reasoning frameworks packaged as reusable analytical lenses — 12 lenses (deep value, quality franchise, inversion, scuttlebutt growth, GARP, cycle positioning, debt cycle, forensic…

MITAuto-check passedBusiness, Finance & HR

Install Investor Lenses

skills CLI
$ npx skills add HKUDS/Vibe-Trading --skill investor-lenses -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HKUDS/Vibe-Trading investor-lenses --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent/src/skills/investor-lenses .claude/skills/investor-lenses && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
investor-lenses
GitHub stars
35k
Token cost
~2.4k tokens
SKILL.md length
1,211 words
Files
13 (incl. references)
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

Named investor reasoning frameworks packaged as reusable analytical lenses — 12 lenses (deep value, quality franchise, inversion, scuttlebutt growth, GARP, cycle positioning, debt cycle, forensic…

  • Works in 5 steps: Freeze the evidence. Write down what is… → Choose by the situation, never by the… → Walk the priority signals in order. Each… → …
  • Business, Finance & HR work in your project
  • SKILL.md covers What a lens is, What a lens is NOT, The five-step run and Lens index, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Investor Lenses is an agent skill from HKUDS/Vibe-Trading. Named investor reasoning frameworks packaged as reusable analytical lenses — 12 lenses (deep value, quality franchise, inversion, scuttlebutt growth, GARP, cycle positioning, debt cycle, forensic short, cost drag, right-business, weak-system contrarian, three questions) that stack on top of evidence already gathered, each with ordered priority signals, hard disqualifiers, and documented failure modes.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `references/bogle-cost-drag.md`, `references/buffett-quality-franchise.md` and `references/chanos-forensic-short.md`).

It sits in Business, Finance & HR. The repository describes itself as: "Vibe-Trading: Your Personal Trading Agent". The licence is MIT.

When your agent uses it

  • Business, Finance & HR work in your project

Example prompts

  • “/investor-lenses”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Freeze the evidence. Write down what is known before choosing the lens —
  2. Choose by the situation, never by the answer you want. Use the selection
  3. Walk the priority signals in order. Each lens orders its signals for a
  4. Hit a hard disqualifier → stop and report the veto. Disqualifiers are not
  5. Run the misuse check, then emit under the output contract. Every lens file

What it can do on your machine

Read from SKILL.md and the folder at commit 8e43007. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Investor Lenses loads about 2.4k tokens when it runs, and up to ~22k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 1,211 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~22k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/Vibe-Trading at commit 8e43007, republished under its MIT licence (© HKUDS). 1,211 words, ~2,432 tokens.

Download SKILL.mdSave it as .claude/skills/investor-lenses/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
investor-lenses
description
Named investor reasoning frameworks packaged as reusable analytical lenses — 12 lenses (deep value, quality franchise, inversion, scuttlebutt growth, GARP, cycle positioning, debt cycle, forensic short, cost drag, right-business, weak-system contrarian, three questions) that stack on top of evidence already gathered, each with ordered priority signals, hard disqualifiers, and documented failure modes.
category
analysis

Investor Lenses

What a lens is

A lens is a reasoning procedure: a fixed, ordered set of questions plus explicit veto rules, distilled from one investor's publicly published methodology. It is applied after the evidence exists — it does not gather data and does not care where the data came from.

The value of a lens is that it is opinionated and therefore falsifiable. A lens tells you, before you look at the answer, which signals it ranks first and which facts make it walk away. Two lenses disagreeing on the same evidence is the product, not a bug: the disagreement localizes exactly which assumption the decision rests on.

What a lens is NOT

  • Not investment advice. Every lens output is an analytical exercise.
  • Not the named person's opinion. Each lens is a reconstruction, in our own words, of a methodology that investor has described publicly. It is not written by them, not endorsed by them, and may diverge from what they would say today.
  • Not a universal truth test. A lens verdict is conditional on the lens. "Fails the Graham lens" and "bad investment" are different statements.
  • Not a ranking of masters. No lens is more correct than another; each has a domain where it is sharp and a domain where it is reliably wrong.

The five-step run

  1. Freeze the evidence. Write down what is known before choosing the lens — financials, prices, disclosures, timelines. A lens applied to evidence collected after the lens was chosen is circular.
  2. Choose by the situation, never by the answer you want. Use the selection table below. If you are picking the lens because you already know its verdict, stop.
  3. Walk the priority signals in order. Each lens orders its signals for a reason. Do not jump to the signal you have the best data on.
  4. Hit a hard disqualifier → stop and report the veto. Disqualifiers are not weighted against positives. They end the run under that lens.
  5. Run the misuse check, then emit under the output contract. Every lens file lists the regimes where it fails. State explicitly whether the current case sits in one of them.

Lens index

LensStyleSharpest onBlindest onFile
Statistical deep value (Graham)Value / balance sheetCheap, boring, asset-heavy, wide-basketAsset-light compounders; single namesgraham-deep-value
Quality franchise (Buffett)Quality / durabilityDurable consumer & toll-road economicsFast-changing tech; deep cyclicalsbuffett-quality-franchise
Inversion (Munger)Risk / pre-mortemFinding the way this diesSizing an opportunity; timingmunger-inversion
Scuttlebutt growth (Fisher)Growth / qualitativeProduct & channel truth vs. reported numbersAnything you cannot reach people aboutfisher-scuttlebutt
GARP by category (Lynch)Growth at a priceMid-cap earnings compounding; retail-visible businessesFinancials; commodity cyclicalslynch-garp
Cycle positioning (Marks)Contrarian / risk-firstWhere we are in the greed–fear cycleSingle-company fundamentalsmarks-cycle-position
Debt cycle & uncorrelated bets (Dalio)Macro / allocationRates, currency, liquidity regime; portfolio shapeStock pickingdalio-debt-cycle
Forensic short (Chanos)Short / accountingAccounting distortion, value traps, structural declineLongs; anything you must be right about soonchanos-forensic-short
Cost drag & mean reversion (Bogle)Allocation / costWhether the activity itself is worth its costIndividual security selectionbogle-cost-drag
Right business, right people (Duan Yongping / 段永平)Quality / concentrationFounder-led A-share, HK and US-listed China namesDiversified baskets; turnaroundsduan-right-business
Weak-system contrarian (Feng Liu / 冯柳)Contrarian / positioningA-share names beaten down by known bad newsMomentum regimes; names with unresolved fraud riskfengliu-weak-system
Three questions (Qiu Guolu / 邱国鹭)Value / industry structureA-share and HK industry structure and pricing powerEarly-stage, structure-not-yet-formed industriesqiuguolu-three-questions

Choosing a lens

SituationStart withThen stack
"Is this cheap enough?" on an asset-heavy or out-of-favour nameGrahamMunger, Qiu Guolu
"Is this a great business?" on a stable franchiseBuffettDuan Yongping, Munger
"The story is wonderful, is it real?"FisherChanos, Munger
"It's grown 5 years, is the multiple sane?"LynchBuffett, Qiu Guolu
"Is the market euphoric or despairing right now?"MarksDalio
"What does the rates / currency / liquidity regime do to this?"DalioMarks
"The accounting smells"ChanosMunger, Fisher
"Should we be picking at all, or just allocating?"BogleMarks
A-share name down 50% on known bad newsFeng LiuChanos, Qiu Guolu
A-share / HK industry with consolidating competitive structureQiu GuoluBuffett, Duan Yongping
Founder-controlled company, governance is the swing factorDuan YongpingMunger, Chanos
Show full SKILL.md (500 more words)Show less

Stacking protocol

Stacking is where lenses earn most of their value, but only under discipline.

  • Two or three lenses. Never more. Beyond three the output degenerates into a survey and the disagreements stop being legible.
  • Choose lenses that can actually disagree. Buffett + Duan Yongping mostly agree by construction; that stack is decoration. Buffett + Chanos, or Feng Liu + Munger, produce real tension.
  • Run each lens independently before comparing. Do not let lens 2 read lens 1's verdict. Cross-contaminated lenses collapse into one lens.
  • Classify every disagreement into exactly one root cause:
    • Horizon — same facts, different holding period (10-year certainty vs. next two quarters).
    • Caliber — the two lenses are measuring different quantities (owner earnings vs. reported net income; EV vs. market cap).
    • Risk preference — same expected value, different tolerance for the left tail.
    • Information — one lens needs a fact nobody has. Say which fact.
  • Never average the verdicts. A 2-to-1 split among lenses is not evidence of anything; lenses are not voters and they are not independent samples. Report the split and its root cause instead.
  • Report the losing lens's strongest point verbatim. If it cannot be stated fairly, the stack was not run honestly.

Anti-patterns

  • Lens shopping — running lenses until one agrees with the pre-existing conclusion, then reporting only that one. If a lens is run, it is reported.
  • Lens as authority — "Buffett would buy this" is a claim about a person and is unsupportable. "Under a quality-franchise lens, this passes the moat test and fails the price test" is a claim about a procedure and is checkable.
  • Biography instead of procedure — quoting temperament, anecdotes or life story in place of walking the signal list.
  • Silent disqualifier — noticing a hard veto and continuing to score anyway because the rest of the picture is attractive.
  • Lens applied out of market — a US-designed lens dropped onto an A-share name without adjusting for what the disclosure regime actually reveals. Each lens file carries a market-fit note; read it.
  • Retrofitting the evidence — going back to collect exactly the data the chosen lens rewards, after choosing the lens.

Output contract (binding on every lens)

Any output produced under this skill must contain, in this order:

  1. Lens name and one-line statement of what it optimizes for.
  2. Verdict, explicitly framework-conditional — phrased "under this framework, …", never as a flat assertion about the security.
  3. The ordered signal walk — each priority signal, the evidence found, and whether it passed. Missing evidence is written as missing, never inferred.
  4. Disqualifier check — every hard veto listed and marked triggered / not triggered / unknown.
  5. Misuse check — whether the current case sits in a regime where this lens is documented to fail.
  6. Falsifiers — the two or three observations that would flip the verdict, each concrete enough that someone could go check it.
  7. Confidence with its limiting factor — "medium, limited by the absence of segment-level disclosure", not a bare number.
  8. The standing disclaimer: this is an analytical framework, not investment advice, and the verdict is conditional on the framework used.

© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (references) in agent/src/skills/investor-lenses of HKUDS/Vibe-Trading.

  • SKILL.md
  • references/bogle-cost-drag.md
  • references/buffett-quality-franchise.md
  • references/chanos-forensic-short.md
  • references/dalio-debt-cycle.md
  • references/duan-right-business.md
  • references/fengliu-weak-system.md
  • references/fisher-scuttlebutt.md
  • references/graham-deep-value.md
  • references/lynch-garp.md
  • references/marks-cycle-position.md
  • references/munger-inversion.md
  • references/qiuguolu-three-questions.md

Open the folder on GitHubat commit 8e43007

Compare with similar skills

Investor Lenses next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Investor Lenses compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Investor Lenses this skillHKUDS/Vibe-Trading35k—~2.4kAutomated safety check: PassMIT
Market Research Reportsforyourhealth111-pixel/Vibe-Skills3.6k—~2.5kAutomated safety check: NotesMIT
Analytics Strategyrampstackco/claude-skills945—~2.4kAutomated safety check: PassMIT
GitHub Project Contributor Finder API Skillbrowser-act/skills6.1k1 repos~1.9kAutomated safety check: PassMIT
Sk Pitchmohamedameen-io/StartupKit163—~15kAutomated safety check: PassMIT
Founder Videopexoai/pexo-skills804—~1.4kAutomated safety check: PassMIT

Similar skills

  • Market Research Reports

    foryourhealth111-pixel/Vibe-Skills

    Produces long consulting-style market research and industry reports covering market sizing, competitive landscape, market entry and investment theses.

    3.6k GitHub stars~2.5k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check: notes

  • Analytics Strategy

    rampstackco/claude-skills

    Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy.

    945 GitHub stars~2.4k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed

  • GitHub Project Contributor Finder API Skill

    browser-act/skills

    This skill helps users extract GitHub repository project details and contributor contact information using keywords, stars, and update dates.

    6.1k GitHub starsUsed in 1 repo~1.9k tokens
    Business, Finance & HRAuto-check passed

  • Sk Pitch

    mohamedameen-io/StartupKit

    Phase 10: Build investor-ready pitch scripts in multiple formats (10-min, 5-min, 2-min, 1-min elevator, investor email).

    163 GitHub stars~15k tokensUpdated 5 mo ago
    Business, Finance & HRAuto-check passed

  • Founder Video

    pexoai/pexo-skills

    Make a founder video with Pexo — built for solo founders and small teams.

    804 GitHub stars~1.4k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed

  • Find Next Crypto Idea

    sendaifun/solana-new

    Interview users sharply to discover, rank, or validate what they should build in crypto.

    179 GitHub stars~2.5k tokensUpdated 9 days ago
    Business, Finance & HRAuto-check passed

More from HKUDS/Vibe-Trading

All 89 skills in this repo

  • Eastmoney Market Data

    HKUDS/Vibe-Trading

    Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.

    35k GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

  • OKX Market Data

    HKUDS/Vibe-Trading

    Retrieves public OKX cryptocurrency market data such as spot prices, candlesticks, funding rates and open interest through the OKX V5 REST API, with no authentication.

    35k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • SEC EDGAR Filings Fetcher

    HKUDS/Vibe-Trading

    Fetches U.S. SEC EDGAR data: resolves tickers to CIK numbers, lists recent 10-K, 10-Q and 8-K filings with document URLs, and pulls XBRL financial series.

    35k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • A-Share ST Risk Screener

    HKUDS/Vibe-Trading

    Predicts whether a mainland China A-share company risks an ST or *ST warning after its next annual report, using financial thresholds and Sina penalty records.

    35k GitHub stars~4.9k tokensUpdated yesterday
    Auto-check passed

  • Supply-Chain Bottleneck Hunter

    HKUDS/Vibe-Trading

    Breaks a structural trend such as AI infrastructure into its physical supply chain and ranks lesser-known listed companies sitting on each bottleneck.

    35k GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed

  • Eight-Part Company Deep Dive

    HKUDS/Vibe-Trading

    Plans and drafts an eight-part, roughly 120k-word investigative series on one company, built around a strict fact-check pass rather than fast drafting.

    35k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Investor Lenses

What does Investor Lenses do?

Named investor reasoning frameworks packaged as reusable analytical lenses — 12 lenses (deep value, quality franchise, inversion, scuttlebutt growth, GARP, cycle positioning, debt cycle, forensic…. Investor Lenses is an agent skill from HKUDS/Vibe-Trading. Named investor reasoning frameworks packaged as reusable analytical lenses — 12 lenses (deep value, quality franchise, inversion, scuttlebutt growth, GARP, cycle positioning, debt cycle, forensic short, cost drag, right-business, weak-system contrarian, three questions) that stack on top of evidence already gathered, each with ordered priority signals, hard disqualifiers, and documented failure modes.

When should I use Investor Lenses?

Investor Lenses fits situations like: business, Finance & HR work in your project.

How do I install Investor Lenses in Claude Code?

Run `npx skills add HKUDS/Vibe-Trading --skill investor-lenses -a claude-code`. Or copy the skill folder (agent/src/skills/investor-lenses in HKUDS/Vibe-Trading) into .claude/skills/investor-lenses in your project. Claude Code loads it when a task matches its description.

How do I install Investor Lenses in Codex?

Run `npx skills add HKUDS/Vibe-Trading --skill investor-lenses -a codex`. Or copy the skill folder (agent/src/skills/investor-lenses in HKUDS/Vibe-Trading) into .agents/skills/investor-lenses in your project. Codex loads it when a task matches its description.

Can I use Investor Lenses in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/Vibe-Trading --skill investor-lenses -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/investor-lenses, .gemini/skills/investor-lenses, .github/skills/investor-lenses and .opencode/skills/investor-lenses in your project.

What does Investor Lenses need to run?

SKILL.md names no scripts, command-line tools or credentials: Investor Lenses is instructions for the agent only.

Does Investor Lenses access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Investor Lenses safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Investor Lenses use?

Investor Lenses is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Investor Lenses use?

About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 19k tokens, read only when the agent opens those files.

What are the alternatives to Investor Lenses?

Skills that share tags, products or a category with Investor Lenses: Market Research Reports (foryourhealth111-pixel/Vibe-Skills, 3.6k stars), Analytics Strategy (rampstackco/claude-skills, 945 stars), GitHub Project Contributor Finder API Skill (browser-act/skills, 6.1k stars) and Sk Pitch (mohamedameen-io/StartupKit, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Investor Lenses?

HKUDS (a GitHub organization) maintains it in HKUDS/Vibe-Trading, which has 35,163 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 10, 2026.

Source: HKUDS/Vibe-Trading on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.