Skip to content
Get packs

Investor Panel (Virtual Investor Vote)

Simulates a panel of famous investor personas scoring a stock by their own methods

Source Download skill
Repository
wbh604/UZI-Skill
Stars
7,490
Licence
MIT
Files
11 files

What it does

Once installed, when a user asks what famous investors would think of a stock, the agent role-plays dozens of investor personas (value, growth, macro, technical, Chinese value and speculative trader styles, quant) and gives each a bullish/neutral/bearish signal, score, verdict and short quote-style comment, then tallies a consensus. It works from pre-collected stock data files (dimensions.json and raw_data.json) that the user must supply, and the output is a role-play opinion, not a financial analysis.

Great for

  • Investors curious how different investing philosophies would view a stock, as a discussion prompt
  • Developers studying multi-persona prompt design or structured JSON output from an agent
  • Students comparing value, growth and momentum frameworks side by side

Skip it if

  • Making real buy or sell decisions: the personas are generated by the model, not the real investors, and the scores are not validated predictions
  • Anyone expecting the skill to fetch live market data by itself: the files only describe reading cached inputs, and the included SKILL.md references scripts and a quotes knowledge base that are not part of the listed files, so it may fail or hallucinate
  • Attributing quotes to real people: comments are model-generated in investors' styles and may misrepresent them

Try asking

  • “Run an investor panel vote on this stock using its dimensions.json and raw_data.json”
  • “What would Buffett and Munger think of this company? Give me a panel verdict”
  • “Show the consensus distribution across all value and growth investors for this ticker”
Step-by-step guide: how to use Investor Panel (Virtual Investor Vote)Install, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 11 original files, the MIT licence and an attribution note.

    investor-panel.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip investor-panel.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip investor-panel.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Provide complete input JSON files first; without them the panel cannot run as described
  • Treat the consensus percentage as a roleplay summary, not an investment signal, and verify any quoted language against real sources
  • Ask for the reasoning behind a specific investor's verdict to see which criteria were used

What's inside

  • assets/investor-cards.json
  • references/group-a-classic-value.md
  • references/group-b-growth.md
  • references/group-c-macro-hedge.md
  • references/group-d-technical.md
  • references/group-e-china-value.md
  • references/group-f-china-youzi.md
  • references/group-g-quant.md
  • references/group-i-serenity.md
  • references/serenity-voice.md
  • SKILL.md

Redistributed unmodified from wbh604/UZI-Skill under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.