Agent skill

LLM Wiki

by Yeachan-Heo in Yeachan-Heo/oh-my-claudecode

Keeps a persistent markdown wiki of project and session knowledge that the agent can ingest into, query, lint and read across sessions.

MITAuto-check passedKnowledge Management

Install LLM Wiki

skills CLI
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill wiki -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Yeachan-Heo/oh-my-claudecode wiki --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/wiki .claude/skills/wiki && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
wiki
GitHub stars
40k
Token cost
~721 tokens
SKILL.md length
272 words
Files
1
Skills in repo
47
Repo updated
First seen
Licence
MIT

At a glance

Keeps a persistent markdown wiki of project and session knowledge that the agent can ingest into, query, lint and read across sessions.

  • Recording an architecture decision so later sessions can find it
  • SKILL.md covers Operations, Categories, Storage and Cross-References, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Looking up what earlier sessions learned about a subsystem

What it does

This skill maintains a project-local wiki of markdown pages under .omc/wiki, with an auto-maintained index.md and an append-only log.md. The operations are wiki_ingest (one ingest may touch several pages), wiki_add for a quick single page, wiki_query, wiki_lint, wiki_list, wiki_read and wiki_delete. Pages carry a title, content, tags and one of six categories: architecture, decision, pattern, debugging, environment or session-log.

Queries match on keywords and tags only, with no vector embeddings, and the agent writes the cited answer itself from the returned snippets. Lint finds orphan and stale pages, broken cross-references, oversized pages and contradictions, and pages link to each other with double-bracket page names. Significant discoveries are saved as session-log pages at the end of a session unless wiki.autoCapture is turned off in .omc-config.json. Pages are git-ignored by default, and the idea comes from Karpathy's LLM Wiki concept.

When your agent uses it

  • Recording an architecture decision so later sessions can find it
  • Looking up what earlier sessions learned about a subsystem
  • Checking the wiki for stale pages or broken links

Example prompts

  • “Add a wiki page on our auth architecture with the tags auth and architecture.”
  • “Search the wiki for what we decided about authentication.”
  • “Lint the wiki and list any orphan or stale pages.”

Requirements

  • oh-my-claudecode with its wiki tools
  • A project directory to hold the .omc/wiki folder

What it can do on your machine

Read from SKILL.md and the folder at commit 454bae0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

LLM Wiki loads about 721 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 272 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~721

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Yeachan-Heo/oh-my-claudecode at commit 454bae0, republished under its MIT licence (© Yeachan-Heo). 272 words, ~721 tokens.

Download SKILL.mdSave it as .claude/skills/wiki/SKILL.md (or your agent's skills folder).
name
wiki
description
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)
triggers
wiki, wiki this, wiki add, wiki lint, wiki query

Wiki

Persistent, self-maintained markdown knowledge base for project and session knowledge. Inspired by Karpathy's LLM Wiki concept.

Operations

Ingest

Process knowledge into wiki pages. A single ingest can touch multiple pages.

wiki_ingest({ title: "Auth Architecture", content: "...", tags: ["auth", "architecture"], category: "architecture" })
Query

Search across all wiki pages by keywords and tags. Returns matching pages with snippets — YOU (the LLM) synthesize answers with citations from the results.

wiki_query({ query: "authentication", tags: ["auth"], category: "architecture" })
Lint

Run health checks on the wiki. Detects orphan pages, stale content, broken cross-references, oversized pages, and structural contradictions.

wiki_lint()
Quick Add

Add a single page quickly (simpler than ingest).

wiki_add({ title: "Page Title", content: "...", tags: ["tag1"], category: "decision" })
List / Read / Delete
wiki_list()           # Show all pages (reads index.md)
wiki_read({ page: "auth-architecture" })  # Read specific page
wiki_delete({ page: "outdated-page" })    # Delete a page
Log

View wiki operation history by reading .omc/wiki/log.md.

Categories

Pages are organized by category: architecture, decision, pattern, debugging, environment, session-log

Storage

  • Pages: .omc/wiki/*.md (markdown with YAML frontmatter)
  • Index: .omc/wiki/index.md (auto-maintained catalog)
  • Log: .omc/wiki/log.md (append-only operation chronicle)

Cross-References

Use [[page-name]] wiki-link syntax to create cross-references between pages.

Auto-Capture

At session end, significant discoveries are automatically captured as session-log pages. Configure via wiki.autoCapture in .omc-config.json (default: enabled).

Hard Constraints

  • NO vector embeddings — query uses keyword + tag matching only
  • Wiki pages are git-ignored by default (.omc/wiki/ is project-local)

Model Routing

  • haiku — quick lookups, lightweight inspection, narrow docs work
  • sonnet — standard implementation, debugging, and review
  • opus — architecture, deep analysis, consensus planning, and high-risk review
  • fable — Claude Fable 5 (above Opus); pass it explicitly on the Task call or pin it per agent with agents.<name>.model
  • The session model chosen with /model applies to the main loop only. Delegated agents run on their pinned tier unless the Task call passes model explicitly or the agent is overridden via agents.<name>.model. To run delegated work on Fable, use one of those two surfaces; selecting Fable in /model alone does not change delegation.

© Yeachan-Heo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/wiki of Yeachan-Heo/oh-my-claudecode.

Open the folder on GitHubat commit 454bae0

Compare with similar skills

LLM Wiki next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

LLM Wiki compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
LLM Wiki this skillYeachan-Heo/oh-my-claudecode40k—~721Automated safety check: PassMIT
TeamAI Team SyncTencent/teamai-cli5.2k—~632Automated safety check: PassCustom licence
Forgetful File StorageScottRBK/forgetful301—~618Automated safety check: PassMIT
MemPalace Memory SearchMemPalace/mempalace59k—~1.4kAutomated safety check: PassMIT
Claude-Mem Knowledge Agentthedotmack/claude-mem99k—~617Automated safety check: PassApache-2.0
Swarmvaultswarmclawai/swarmvault709—~6.1kAutomated safety check: PassMIT

Similar skills

  • TeamAI Team Sync

    Tencent/teamai-cli

    Make every team AI native — TeamAI syncs a team's AI skills, rules, docs and env across AI coding tools. Use when the task operates on team-shared AI…

    5.2k GitHub stars~632 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Forgetful File Storage

    ScottRBK/forgetful

    Stores screenshots, PDFs, diagrams, fonts and other binary files in the Forgetful knowledge base, with a retrieval-friendly description and an attachment route.

    301 GitHub stars~618 tokensUpdated yesterday
    Knowledge ManagementAuto-check passed
  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    59k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Claude-Mem Knowledge Agent

    thedotmack/claude-mem

    Builds focused knowledge corpora from claude-mem observations, loads them into an AI session and answers questions about past work.

    99k GitHub stars~617 tokensUpdated yesterday
    Knowledge ManagementAuto-check passed
  • Swarmvault

    swarmclawai/swarmvault

    Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval…

    709 GitHub stars~6.1k tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • Remember Project Knowledge

    zereight/gitlab-mcp

    Sorts what you learned in a session into the right memory surface, filtering out ephemeral notes and duplicates before anything is stored.

    2k GitHub starsUsed in 1 repo~846 tokens
    Agent WorkflowsAuto-check passed

More from Yeachan-Heo/oh-my-claudecode

All 47 skills in this repo
  • Ask Advisor Routing

    Yeachan-Heo/oh-my-claudecode

    Sends a question or task to another locally installed agent CLI, such as Codex or Gemini, through omc ask and saves the answer as a file.

    40k GitHub stars~572 tokensUpdated 2 days ago
    Auto-check passed
  • Ask Navigator

    Yeachan-Heo/oh-my-claudecode

    Charts a foggy effort into a map of decision tickets on the repo's issue tracker and works through them one per session, producing decisions rather than deliverables.

    40k GitHub stars~4.1k tokensUpdated 2 days ago
    Auto-check passed
  • Self-Improve Evolutionary Loop

    Yeachan-Heo/oh-my-claudecode

    Runs an autonomous improvement loop on a repository: agents propose and execute plans, a tournament picks the winner by benchmark, and each round is recorded and plotted.

    40k GitHub stars~5.3k tokensUpdated 2 days ago
    Auto-check: warnings
  • Autopilot

    Yeachan-Heo/oh-my-claudecode

    Takes a short product idea through requirements, design, planning, parallel implementation, QA cycles and multi-reviewer validation to produce working code.

    40k GitHub stars~4.4k tokensUpdated 2 days ago
    Auto-check passed
  • OMC Mode Cancellation

    Yeachan-Heo/oh-my-claudecode

    Detects and gracefully cancels whichever OMC mode, autopilot, ralph, swarm, pipeline, or team, is currently active, then clears its state.

    40k GitHub stars~4.6k tokensUpdated 2 days ago
    Auto-check passed
  • Hierarchical AGENTS.md Generator

    Yeachan-Heo/oh-my-claudecode

    Maps a codebase directory by directory and writes linked AGENTS.md files, each pointing to its parent, to document what each area contains.

    40k GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed

Questions about LLM Wiki

What does LLM Wiki do?

Keeps a persistent markdown wiki of project and session knowledge that the agent can ingest into, query, lint and read across sessions. md. The operations are wiki_ingest (one ingest may touch several pages), wiki_add for a quick single page, wiki_query, wiki_lint, wiki_list, wiki_read and wiki_delete.

When should I use LLM Wiki?

LLM Wiki fits situations like: recording an architecture decision so later sessions can find it; looking up what earlier sessions learned about a subsystem; checking the wiki for stale pages or broken links.

How do I install LLM Wiki in Claude Code?

Run `npx skills add Yeachan-Heo/oh-my-claudecode --skill wiki -a claude-code`. Or copy the skill folder (skills/wiki in Yeachan-Heo/oh-my-claudecode) into .claude/skills/wiki in your project. Claude Code loads it when a task matches its description.

How do I install LLM Wiki in Codex?

Run `npx skills add Yeachan-Heo/oh-my-claudecode --skill wiki -a codex`. Or copy the skill folder (skills/wiki in Yeachan-Heo/oh-my-claudecode) into .agents/skills/wiki in your project. Codex loads it when a task matches its description.

Can I use LLM Wiki in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Yeachan-Heo/oh-my-claudecode --skill wiki -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wiki, .gemini/skills/wiki, .github/skills/wiki and .opencode/skills/wiki in your project.

What does LLM Wiki need to run?

SKILL.md names no scripts, command-line tools or credentials: LLM Wiki is instructions for the agent only. Our summary lists: oh-my-claudecode with its wiki tools; A project directory to hold the .omc/wiki folder.

Does LLM Wiki access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is LLM Wiki safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does LLM Wiki use?

LLM Wiki is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does LLM Wiki use?

About 721 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to LLM Wiki?

Skills that share tags, products or a category with LLM Wiki: TeamAI Team Sync (Tencent/teamai-cli, 5.2k stars), Forgetful File Storage (ScottRBK/forgetful, 301 stars), MemPalace Memory Search (MemPalace/mempalace, 59k stars) and Claude-Mem Knowledge Agent (thedotmack/claude-mem, 99k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains LLM Wiki?

Yeachan-Heo (a GitHub user) maintains it in Yeachan-Heo/oh-my-claudecode, which has 39,751 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on October 8, 2026.

Source: Yeachan-Heo/oh-my-claudecode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.