LLM Wikify — AI skill for Claude Code
How to install LLM Wikify
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open wjgoarxiv/llm-wikify and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What LLM Wikify does
.
Alternatives in AI
- WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
- Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
- Firecrawl MCP Server — 🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM c 6.1k ★
README

llm-wikify
Turn the current working directory into a small, compounding LLM wiki — without building a giant universal vault.
Install · Novice Quickstart · When to Use · Features · Workflow · Repo Layout · 한국어
[!NOTE] `llm-wikify` is inspired by Karpathy’s `llm-wiki` pattern, but optimized for **task-driven work**. Instead of forcing the model to constantly reason over one ever-growing mega-wiki, this skill treats the **current working directory as a mini wiki boundary**. New sources dropped into `raw/` get integrated into a small, local markdown knowledge base that stays useful for the project at hand.
Install (npx)
Install the skill **and** its `init / ingest / query / save / lint` commands into your AI agents — **Claude Code, Codex, and OpenCode** — with one command:
npx llm-wikify
A bilingual (KO/EN) interactive installer detects which agents you have, shows **exactly which files it will write and where**, then installs only self-contained, namespaced files.
[!IMPORTANT] **Your `CLAUDE.md` / `AGENTS.md` are never touched.** The installer writes only namespaced files — `~/.claude/skills/wikify/`, `~/.agents/skills/wikify/` + `~/.codex/prompts/`, and `~/.config/opencode/{agents,commands}/`. This is verified by an automated test: your instruction files are byte-f
Related Skills
Wikify Repo
Compile any codebase into a grounded, lint-clean markdown wiki your AI agent can actually trust — SCIP symbol
Inference Serving
ai-research-skills vLLM, SGLang, TensorRT-LLM, llama.cpp
Deepreasoning
A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthr
Manifest
Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage. Includes Cl
Surface
Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is cbh su
Open Knowledge
Beautiful, AI-native markdown IDE and LLM wiki
Related Agents
Gaia Agent Builder
GAIA agent creation specialist. Use PROACTIVELY when CREATING a new GAIA agent — inheriting from the base Agen
LLM AI Hunter
LLM and Agentic AI vulnerability specialist. Covers OWASP LLM Top 10 v2025 (LLM01-LLM10) and OWASP Agentic AI
Style Distiller
三阶段 13 模板 LLM 提取,写风格主卡、场景卡、分析稿与版本快照