llm-wiki

94 / 100 · Low risk

Fine to try. Some of what it can do is expected: a research skill usually looks things up on the internet.

By infranodus/skills (GitHub) · research · 127 stars · scanned at commit 99c800e

Guide users through setting up a personal LLM-maintained wiki — a persistent, compounding knowledge base where the LLM incrementally builds and maintains interlinked markdown pages from raw sources. Use this skill when the user wants to: set up a personal knowledge base, create a research wiki, organize notes with LLM help, build a "second brain", set up an Obsidian + LLM workflow, create a persistent knowledge graph from documents, plan research priorities and next steps, or mentions "LLM wiki…

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README.

Found in 1 place.

skill-llm-wiki/SKILL.md, line 444mkdir -p todos

Connects to the internet

This is disclosed by the author in the skill's SKILL.md or README. Expected for a research skill.

Found in 8 places.

skill-llm-wiki/references/acquire-and-process.md, line 384. If it's a YouTube or web URL, fetch + transcribe (InfraNodus `analyze_text` with url arg, yt-dlp + Whisper, Obsidian Web Clipper, or `WebFetch`)
skill-llm-wiki/references/acquire-and-process.md, line 45- Offer to fetch a relevant web article via `WebSearch` / `WebFetch` based on the wiki's topic
skill-llm-wiki/references/acquire-and-process.md, line 60- **D) Search for new sources** — given a gap or topic from Phase 10 priorities, the LLM uses `WebSearch` / InfraNodus `analyze_google_search_results` to propos

Show 5 more

skill-llm-wiki/references/acquire-and-process.md, line 71- Web URL → article markdown (Obsidian Web Clipper, InfraNodus fetch, `WebFetch`)
skill-llm-wiki/references/acquire-and-process.md, line 85| Web articles, blog posts | URL | Obsidian Web Clipper, InfraNodus fetch, `WebFetch` | `raw/articles/`
skill-llm-wiki/scripts/upload_wiki_ontology.py, line 56import urllib.request
skill-llm-wiki/scripts/upload_wiki_ontology.py, line 149req = urllib.request.Request(self.base_url + path, data=data,
skill-llm-wiki/scripts/upload_wiki_ontology.py, line 151return urllib.request.urlopen(req, timeout=HTTP_TIMEOUT)

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'llm-wiki' ] || [ -L ~/.agents/skills/'llm-wiki' ]; then echo 'A skill folder named llm-wiki already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/infranodus/skills' "$d" && git -C "$d" checkout --quiet '99c800ecb8b49f789cc04ca7bd1ddece783167ee' -- 'skill-llm-wiki' && mkdir -p ~/.agents/skills && cp -R "$d"/'skill-llm-wiki' ~/.agents/skills/'llm-wiki' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'llm-wiki' ~/.claude/skills/'llm-wiki' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for infranodus/skills shows the score of its lowest-scoring skill.

SkillTrust badge for infranodus/skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/infranodus/skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/infranodus/skills/)

Score history

Date	Version	Score
2026-11-13	`99c800e`	94
2026-11-07	`882aed2`	94