wiki
Wiki is a knowledge base manager that helps you build interconnected markdown articles from ingested sources. Initialize topic-scoped wikis, compile raw documents incrementally, query with Codex, and maintain structured indexes—all while keeping your sources immutable and synthesis honest.
Wiki initializes and manages LLM-compiled knowledge bases with ingestion, compilation, and topic-scoped querying for Codex.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-15
Wiki initializes and manages LLM-compiled knowledge bases with ingestion, compilation, and topic-scoped querying for Codex. Wiki is a knowledge base manager that helps you build interconnected markdown articles from ingested sources. Initialize topic-scoped wikis, compile raw documents incrementally, query with Codex, and maintain structured indexes—all while keeping your sources immutable and synthesis honest.
Use it when
- Wiki supports bulk ingestion of source collections into your knowledge base.
- Wiki includes audit, lint, and verify capabilities to check content quality, provenance, and semantic drift across your knowledge base.
Verify before relying
Read SKILL.md below before installing (19 files). Open directory: indexed for reading, not audited.
Install
nvk/llm-wiki/wiki · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I set up a knowledge base wiki?
Wiki is a knowledge base manager that helps you initialize topic-scoped wikis to build interconnected markdown articles from ingested sources. Start by creating a local .wiki folder, define your topic scope, and configure ingestion rules. Wiki will then compile raw documents incrementally while maintaining structured indexes and keeping your sources immutable.
How do I ingest documents into wiki?
Wiki supports bulk ingestion of source collections into your knowledge base. You can import documents, configure metadata for each source, and wiki will organize them with structured tracking. The ingestion process is designed to be incremental, allowing you to add sources over time while wiki maintains provenance and keeps synthesis honest.
What linting and audit tools does wiki provide?
Wiki includes audit, lint, and verify capabilities to check content quality, provenance, and semantic drift across your knowledge base. Run quality scans to detect issues, review source attribution, and ensure your compiled articles remain accurate and well-sourced. These tools help maintain integrity as your wiki grows.
Can I archive and restore wiki state across sessions?
Wiki supports capturing, archiving, and restoring your knowledge base state across research workflows and sessions. You can snapshot your current wiki configuration, articles, and indexes, then rehydrate from that archive later. This enables long-term research projects and session continuity without losing your accumulated knowledge.
How do I query my wiki for information?
Wiki lets you query your compiled knowledge base using Codex integration. Once you've ingested sources and compiled articles, you can search and retrieve information from your interconnected markdown articles. The query system works within your topic-scoped wiki to surface relevant content from your indexed sources.
What can wiki help me plan and track?
Wiki supports research planning, output generation, and inventory tracking within your topic-scoped knowledge base. You can organize wiki topics and articles with cross-linking and navigation, conduct dataset tracking, and manage research workflows. Wiki helps you structure complex research projects while maintaining clear provenance and source attribution.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
LLM Wiki Manager
You manage an LLM-compiled knowledge base. Source documents are ingested into raw/, then incrementally compiled into a wiki of interconnected markdown articles. Codex is both the compiler
(truncated - see the full file via the links below)
File tree — 15 files
plugins/llm-wiki/skills/wiki/SKILL.md
plugins/llm-wiki/skills/wiki/agents/openai.yaml
plugins/llm-wiki/skills/wiki/references/archive.md
plugins/llm-wiki/skills/wiki/references/audit.md
plugins/llm-wiki/skills/wiki/references/command-prelude.md
plugins/llm-wiki/skills/wiki/references/compilation.md
plugins/llm-wiki/skills/wiki/references/datasets.md
plugins/llm-wiki/skills/wiki/references/feedback.md
plugins/llm-wiki/skills/wiki/references/hub-resolution.md
plugins/llm-wiki/skills/wiki/references/indexing.md
plugins/llm-wiki/skills/wiki/references/ingestion.md
plugins/llm-wiki/skills/wiki/references/inventory.md
plugins/llm-wiki/skills/wiki/references/librarian.md
plugins/llm-wiki/skills/wiki/references/linting.md
plugins/llm-wiki/skills/wiki/references/projects.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Initialize and manage an LLM-compiled knowledge base with ingestion, compilation, and querying”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Wiki Manager organizes AI-generated knowledge bases as interconnected markdown articles compiled from ingested sources. It handles hub resolution, topic sub-wikis, incremental compilation, and semantic queries without external tools—all through Claude Code.
LLM Wiki lets you build and maintain a self-contained personal knowledge base as plain markdown, organized into immutable source material and compiled articles you own. Sources land in a `raw/` directory, you compile them into `wiki/` articles, and the system keeps everything local—readable on GitHub and openable as an Obsidian vault. Query your knowledge, ingest new sources, lint for health, audit claims against their sources, or critique reasoning, all without external servers or embeddings.
wiki-query is a read-only protocol for fast, index-first lookups across llm-wiki knowledge bases. It prioritizes exact file citations and respects evidence boundaries, refusing to fill gaps from model memory. Use it for inventory checks and factual questions where provenance matters.
Karpathy LLM Wiki organizes your knowledge into two layers: immutable source files and compiled wiki articles that grow together. Sources feed into raw directories, then compile into topic-organized wiki pages with automatic fact-checking against originals. The wiki becomes a persistent, compounding artifact you query and maintain over time.
llm-wiki helps you create and maintain a compounding knowledge base as interlinked markdown files, inspired by Andrej Karpathy's pattern. Unlike traditional retrieval systems that rediscover information per query, this skill compiles knowledge once and keeps it current with built-in cross-references and contradiction detection. The agent handles summarization, filing, and maintenance while you curate sources and direct analysis.
Okf Refactor transforms unstructured knowledge from notes, wikis, databases, or catalog exports into conformant OKF v0.1 bundles. It structures content as one-concept-per-file markdown documents with YAML frontmatter, generates navigable indexes, and wires cross-linked knowledge graphs while preserving all source metadata.
More skills llm-wiki (MIT)