No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by vanillaflava · Claude Skill · ★ 67
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is llm-wiki-skills safe to install? View the security audit →
Featured in: Personal Knowledge Skills
llm-wiki-skills Six agent skills for building and maintaining a personal knowledge wiki using Markdown files, wikilinks, and filesystem access. Developed on Claude with GUI install support; works on Claude Code, Gemini CLI, Codex CLI, and GitHub Copilot. What this is A set of agent skills for incrementally building and maintaining a structured, interlinked knowledge base on your local filesystem. You add sources; the agent reads, synthesises, and files them into wiki pages. You ask questions; the agent reads the wiki and answers with ci
| Stars | 67 |
| Forks | 9 |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 57.4725689996086/100 |
| Last Updated | 2026-07-11 |
| Created | 2026-04-13 |
| Platforms | claude-code |
| Est. Tokens | ~23k |
These tools work well together with llm-wiki-skills for enhanced workflows:
Looking for a llm-wiki-skills alternative? If you're comparing llm-wiki-skills with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-main
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
Modular Context | Karpathy LLM Knowledge Base + Gmail & G-Cal — multi-account MCP server for Claude Code, encr
A fast, open-source markdown editor. Graph view, plugin API, themes, Git/WebDAV sync, AI MCP — built on Tauri
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Agent SKILL for Obsidian.md plugin development
Explore other popular claude skill tools:
llm-wiki-skills is Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with every conversation. Works with Obsidian, Logseq, etc. or just folders on your lo. It is categorized as a Claude Skill with 67 GitHub stars.
You can find installation instructions and usage details in the llm-wiki-skills GitHub repository at github.com/vanillaflava/llm-wiki-skills. The project has 67 stars and 9 forks, indicating an active community.
llm-wiki-skills is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to llm-wiki-skills on Agent Skills Hub include llm-wiki-plugin, skill-conductor, modular-context-obsidian-plugin. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: