Wiki (wiki-3)
LLM-compiled knowledge base manager for Codex. Use it to initialize, ingest, import source collections, collect catalogs, track inventory…
- Type
- Skill
- Repository
- nvk/llm-wiki
- GitHub stars
- 1.4k
- License
- MIT
- Repo last updated
- Sep 15, 2026
- Source file
- README.md
What Wiki (wiki-3) is
Wiki (wiki-3) is a skill published in the nvk/llm-wiki repository on GitHub, which has about 1.4k stars. The repository describes itself as: “LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.”
A skill is a folder with a SKILL.md file: frontmatter with a name and a description, followed by instructions Claude follows. Claude loads a skill automatically when a task matches its description, and you can also run it directly with a slash and its name.
Skills work in Claude Code and in Claude Cowork, which makes Wiki a portable way to give Claude the same method everywhere.
How to install Wiki (wiki-3)
Claude Code
- Download the wiki-3 folder from the repository.
- Save it as ~/.claude/skills/<skill-name>/SKILL.md for all projects, or .claude/skills/<skill-name>/SKILL.md for one project.
- Claude loads it automatically when a task matches; you can also run it with / and its name.
Claude Cowork
- Zip the skill folder so SKILL.md sits at the top level of the folder.
- Open Customize → Skills, click +, then upload the ZIP.
- Start a task that matches the description, or call it by name with /.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from README.md, shared under the repository's MIT license. Read the full file on GitHub.
██╗ ██╗ ███╗ ███╗ ██╗ ██╗██╗██╗ ██╗██╗
██║ ██║ ████╗ ████║ ██║ ██║██║██║ ██╔╝██║
██║ ██║ ██╔████╔██║ ██║ █╗ ██║██║█████╔╝ ██║
██║ ██║ ██║╚██╔╝██║ ██║███╗██║██║██╔═██╗ ██║
███████╗███████╗██║ ╚═╝ ██║ ╚███╔███╔╝██║██║ ██╗██║
╚══════╝╚══════╝╚═╝ ╚═╝ ╚══╝╚══╝ ╚═╝╚═╝ ╚═╝╚═╝llm-wiki.net · @LLMWIKI on X · github.com/nvk/llm-wiki
LLM-compiled knowledge bases for any AI agent. Capture rough Ideas, research and shape them, then explicitly promote approved briefs into delivery Projects. Also includes parallel research, collector catalogs, session memory, source ingestion, compilation, audits, querying, and artifact generation. Ships for Claude Code, OpenAI Codex, OpenCode, and portable agents. Obsidian-compatible.
Install · Quick Start · Sessions · Commands · How It Works · Research Modes · Thesis Research · Query Depths · Linking · Obsidian · Architecture · Nono Sandbox · Upgrade · Changelog · Credits
Changelog
v0.25.0 — Portable multi-runtime reliability. Adds configurable llm-wiki lint --fail-on critical|warning|suggestion exit gates, portable Claude/Codex/OpenCode packaging without rsync, safer Windows session-state and path handling, HOME-aware hub discovery, and isolated Codex installs that respect the selected CODEX_HOME.
v0.24.0 — Project Knowledge Checkpoints Export. Exports comprehensive, cross-topic project handoffs under docs/knowledge/ / with dry-run-first create and refresh, read-only verification and bounded import, exact source and section coverage, explicit omissions, semantic privacy minimization, deterministic sealing, attested overrides, and a thin-output guard. Checkpoint writes never authorize commit, publication, or import.
v0.23.0 — Personal specialist framework. Adds optional user-owned, instruction-only SKILL.md review methods under the user's local wiki hub, explicit per-topic allowlists, deterministic validation and management, and research selection with version/hash provenance. The public release contains the framework only; personal specialist packages and wiki-derived candidate reports are not bundled or published.
v0.22.0 — Declarative private-adapter routing. Registered adapters may declare provider-neutral intent and exact-URL routes plus an adapter-owned workflow guide. The public plugin discovers the route before ingestion but no longer embeds any provider's authentication, browser, recovery, or editing workflow.
v0.21.3 — Adapter-boundary transition. Consolidates the v0.21 line and keeps the session-hook compatibility fix. Provider-specific workflow material from that line is superseded in current source by manifest-driven routing and lives only in the corresponding private adapter.
v0.20.0 — Governed remote writes. Extends private adapters with exact remote-resource allowlists, declared read/write effects, explicit approval bound to an exact plan hash, expected revisions, stable idempotency keys, private verified receipts, and content-free terminal reporting.
Install
Claude Code (native plugin):
claude plugin install wiki@llm-wikiOpenAI Codex (marketplace plugin):
Install from GitHub:
codex plugin marketplace add nvk/llm-wiki
codex plugin add wiki@llm-wiki
# Start a new Codex thread, then use @wiki or type $ to select wiki-queryInstall from a local checkout with the managed bootstrap helper:
./scripts/bootstrap-codex-plugin.sh --scope user --verifyOr register the local checkout manually:
codex plugin marketplace add /absolute/path/to/llm-wiki
codex plugin add wiki@llm-wikiCanonical explicit invocation:
$wiki-query "What does the wiki say about hardware wallet threat models?"
@wiki research "hardware wallet threat models"
@wiki collect "bitcoin memes" --wiki memes-bitcoin
@wiki ingest https://example.com/article
@wiki audit --project coldcard-threat-model
@wiki session status
@wiki feedback list --unpromoted
@wiki session disable # optional opt-out
@wiki ll "codex plugin install gotchas"Upgrade:
codex plugin marketplace upgrade llm-wiki
codex plugin add wiki@llm-wikiRemove:
codex plugin remove wiki@llm-wiki
codex plugin marketplace remove llm-wikiTroubleshooting:
- codex plugin marketplace add registers the catalog; codex plugin add wiki@llm-wiki installs and enables the cached plugin non-interactively.
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Wiki (wiki-3)?
Wiki (wiki-3) is a skill for Claude Code and Claude Cowork from the nvk/llm-wiki repository on GitHub. LLM-compiled knowledge base manager for Codex. Use it to initialize, ingest, import source collections, collect catalogs, track inventory…
How do I install Wiki (wiki-3) in Claude Code?
Download the wiki-3 folder from the repository. Save it as ~/.claude/skills/<skill-name>/SKILL.md for all projects, or .claude/skills/<skill-name>/SKILL.md for one project. Claude loads it automatically when a task matches; you can also run it with / and its name.
Can I use Wiki (wiki-3) in Claude Cowork?
Zip the skill folder so SKILL.md sits at the top level of the folder. Open Customize → Skills, click +, then upload the ZIP. Start a task that matches the description, or call it by name with /.
Is Wiki (wiki-3) safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Wiki LLM-compiled knowledge base with Project Knowledge Checkpoints Export, personal specialist skills, trusted adapters, Idea-to-Project workflows, compact queries, inventory, datasets, ingestion, audits, sessions, research, and outputs. Plugin · nvk/llm-wiki
- Create Skill Create new skills for Claude Code. Use when users ask to create a skill, add a skill, make a new command, build a skill, add a slash… Skill · moazbuilds/claudeclaw
- 360 Feedback Template Design a 360-degree feedback survey or write a structured 360 feedback report. Use when asked to build a 360 feedback process, write 360… Skill · mohitagw15856/pm-claude-skills
- Adding A Command Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry… Skill · caliber-ai-org/ai-setup
- A11y Audit Audit a UI or design against WCAG 2.2 AA/AAA and ARIA patterns, returning criterion-referenced findings with severity and specific fixes. Use when the user wants an accessibility check, contrast verification, keyboard/screen-reader review, or wants to confirm a component meets POUR. Skill · plugin87/ux-ui-agent-skills
- Claude Typer Render a Claude-style prompt typing animation video by calling Remotion CLI against the remote site https://www.laosunwendao.com. Use when the user asks for "做一个 claude 的提示词打字机动画", "做 Claude 打字动画", "创建提示词动画", or similar requests that convert a text prompt into a typing-animation video. Skill · vibe-motion/skills
- Cc Safety Net Configure CC Safety Net rulebooks for user, project, or shareable GitHub scope. Skill · kenryu42/cc-safety-net
- Ios Simulator Skill 21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation… Skill · conorluddy/ios-simulator-skill