LLM Wiki Setup (Investment Research Second Brain)
Co-creates a pure-markdown investment research wiki in Karpathy's LLM Wiki style by interviewing you to distill your own analysis framework into CLAUDE.md.
Data & AnalyticsIntermediate★ 1,323⑂ 212AI score 8/10Last updated: Aug 8, 2026
What it does
- Scaffolds an investment-research wiki built on plain markdown +
[[wikilinks]]+ grep, deliberately no RAG, vector DB or embeddings. scripts/init_vault.pygenerates the three-tier directory layout, a linter, a git pre-commit hook, and empty index/log files.- The heart of it is an interview: it walks the 8 dimensions in
references/interview.mdone at a time and writes your answers, in your own wording, into the rules layer ofCLAUDE.md— instead of handing you a generic schema. - Ingests sell-side reports, earnings-call transcripts and meeting notes through a 5-checkpoint human-in-the-loop SOP, and builds post-earnings prediction→fulfillment review pages.
Who it's for
- Individual investors and analysts tracking companies, industries, macro and analysts over time
- Markdown/Obsidian vault users whose notes lack structure and maintenance discipline
- Anyone who wants their personal investing criteria written down so the AI works by those criteria
Examples
- "Build me an investment research wiki from scratch" → scaffolds the vault, then interviews you across 8 dimensions to author your own CLAUDE.md
- "Ingest this broker report into my wiki" → splits it into company/industry/analyst pages and wires up the wikilinks per the ingest SOP
- "Earnings just dropped — review whether last quarter's thesis played out" → produces a prediction-vs-outcome review page
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/daymade/claude-code-skills/HEAD/llm-wiki-setup/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the llm-wiki-setup folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/llm-wiki-setup/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/daymade/claude-code-skills.git && mkdir -p ~/.claude/skills && cp -r claude-code-skills/llm-wiki-setup ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and clone the repo:
git clone https://github.com/daymade/claude-code-skills.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill in:
cp -r claude-code-skills/llm-wiki-setup ~/.claude/skills/ - Make sure Python 3 and
uvare installed (needed by the lint script). If not:pip install uv. - Restart Claude Code and ask: "Set up an investment research LLM Wiki for me".
- When asked for a target directory, provide one, then answer the interview questions in your own words. Do not copy the files in
examples/— the skill explicitly forbids it. - Once the vault exists, run
git initinside it andgit config core.hooksPath .githooksto enable the lint hook.
View source on GitHub ↗License: MIT