New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

LLM Wiki

by HybridAIOne in HybridAIOne/hybridclaw

Build and maintain a persistent markdown wiki from raw sources using incremental ingest, indexed pages, and append-only logging.

MITAuto-check passedKnowledge Management

Install LLM Wiki

skills CLI
$ npx skills add HybridAIOne/hybridclaw --skill llm-wiki -a claude-code

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

GitHub CLI
$ gh skill install HybridAIOne/hybridclaw llm-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/HybridAIOne/hybridclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/llm-wiki .claude/skills/llm-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
llm-wiki
GitHub stars
159
Token cost
~1.9k tokens
SKILL.md length
1,048 words
Files
11
Skills in repo
72
Repo updated
First seen
Licence
MIT

At a glance

Build and maintain a persistent markdown wiki from raw sources using incremental ingest, indexed pages, and append-only logging.

  • Works in 4 steps: a user-specified wiki root → an already-structured repo or vault… → a confirmed markdown vault or notes repo… → …
  • Tasks that involve LLM wikis
  • SKILL.md covers Core Model, Resolve The Wiki Root, Orient Every Session and Default Layout, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

LLM Wiki is an agent skill from HybridAIOne/hybridclaw. Build and maintain a persistent markdown wiki from raw sources using incremental ingest, indexed pages, and append-only logging.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files (for example `templates/AGENTS.md`, `templates/index.md` and `templates/log.md`).

It sits in Knowledge Management, covering LLM wikis. The repository describes itself as: Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and memory. The licence is MIT.

When your agent uses it

  • Tasks that involve LLM wikis

Example prompts

  • “/llm-wiki”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. a user-specified wiki root
  2. an already-structured repo or vault containing raw/, wiki/, index.md,
  3. a confirmed markdown vault or notes repo chosen by the user
  4. the current workspace only if the user explicitly wants the wiki here

What it can do on your machine

Read from SKILL.md and the folder at commit 8162701. 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 (its code samples are markdown).

    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 1.9k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 1,048 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 HybridAIOne/hybridclaw at commit 8162701, republished under its MIT licence (© HybridAIOne). 1,048 words, ~1,923 tokens.

Download SKILL.mdSave it as .claude/skills/llm-wiki/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
llm-wiki
description
Build and maintain a persistent markdown wiki from raw sources using incremental ingest, indexed pages, and append-only logging.
user-invocable
true

LLM Wiki

Use this skill when the user wants a persistent knowledge base that compounds over time instead of answering from raw documents from scratch on every turn.

Core Model

Treat the wiki as three layers:

  • raw/ is the immutable source collection. Read from it; do not edit or rewrite it during normal maintenance.
  • wiki/ is the maintained knowledge layer. This is where summaries, entity pages, concept pages, and durable analyses live.
  • AGENTS.md, index.md, and log.md define and track the system: AGENTS.md is the schema and workflow contract, index.md is the catalog, and log.md is the append-only timeline.

This is not a one-shot note dump. The goal is to integrate new information into existing pages, preserve cross-references, and keep the wiki internally coherent as the source set grows.

Resolve The Wiki Root

Use this order:

  1. a user-specified wiki root
  2. an already-structured repo or vault containing raw/, wiki/, index.md, and log.md
  3. a confirmed markdown vault or notes repo chosen by the user
  4. the current workspace only if the user explicitly wants the wiki here

Do not assume the current workspace is the wiki root just because it contains Markdown files.

If the target is an Obsidian vault, also follow skills/obsidian/SKILL.md.

Orient Every Session

When the user already has a wiki, always orient yourself before acting:

  1. Read AGENTS.md first to understand the local schema, domain, taxonomy, link style, and workflow rules.
  2. Read index.md to learn what pages exist and how the wiki is organized.
  3. Read the most recent entries in log.md to understand recent ingest, query, lint, archive, and cleanup activity.
  4. For large wikis, search the relevant topic across wiki/**/*.md before creating anything new.

Do this every session before ingest, query, lint, archive, or broad cleanup. Skipping orientation causes duplicate pages, weak cross-references, and schema drift.

Default Layout

Unless the user already has a stronger convention, initialize or preserve this shape:

  • raw/
  • raw/assets/
  • wiki/
  • wiki/sources/
  • wiki/entities/
  • wiki/concepts/
  • wiki/analyses/
  • index.md
  • log.md
  • AGENTS.md

Use the starter files in skills/llm-wiki/templates/ when bootstrapping a new wiki. Copy only missing files unless the user asks to replace existing ones.

Initialization Workflow

When the wiki does not exist yet:

  1. Confirm the wiki root.
  2. Create the default layout.
  3. Seed missing starter files from skills/llm-wiki/templates/.
  4. Adapt AGENTS.md to the user's domain if they gave one.
  5. Add an initialization entry to log.md.

Do not overwrite an existing AGENTS.md, index.md, or log.md without reading them first.

Schema Contract

AGENTS.md is the local schema for the wiki. It should define:

  • the domain and out-of-scope topics
  • file naming and link conventions
  • the frontmatter contract for maintained pages
  • the allowed tag taxonomy
  • page thresholds for create vs update vs split
  • update policy for contradictions and superseded claims

When bootstrapping or upgrading a wiki, make sure AGENTS.md contains a usable schema, not just a short description.

The authoritative default schema lives in skills/llm-wiki/templates/AGENTS.md. Use that file as the source of truth for default frontmatter, taxonomy, page thresholds, lint checks, archive behavior, and link style. Adapt the copied AGENTS.md to the user's domain instead of duplicating those defaults here.

Ingest Workflow

When the user asks to ingest a source:

  1. Orient first by reading AGENTS.md, index.md, and recent log.md.
  2. Capture or read the source from raw/ or the user-provided path.
  3. Create or update a source summary page under wiki/sources/.
  4. Search the wiki for relevant entities, concepts, and analyses before creating anything new.
  5. Update relevant entity, concept, and analysis pages instead of duplicating facts across many unrelated notes.
  6. Update index.md for every created, renamed, archived, or merged page.
  7. Append a structured entry to log.md listing the files created or updated.

Preferred source page sections:

  • summary
  • key facts
  • claims and evidence
  • related entities or concepts
  • open questions
  • source details

Favor synthesis over excerpt hoarding. Pull forward the durable information and cite where it came from.

When a source conflicts with existing wiki content:

  1. check dates and provenance
  2. record both positions if the conflict is real
  3. mark the disagreement explicitly in the affected page
  4. surface it in lint results if still unresolved

If one ingest would touch many pages, narrate the scope clearly before making a large coordinated update.

Apply the local AGENTS.md rules for frontmatter, tags, thresholds, page shape, and link style. If the wiki still uses the default bundled schema, that means following the defaults copied from skills/llm-wiki/templates/AGENTS.md.

Show full SKILL.md (315 more words)Show less

Query Workflow

When answering a wiki question:

  1. Orient first.
  2. Read index.md to find the relevant pages.
  3. For large wikis, search for key terms across the wiki before choosing pages.
  4. Read only the relevant wiki pages and source summaries.
  5. Answer with citations back to wiki pages and, when helpful, raw sources.
  6. If the answer is durable, save it under wiki/analyses/ and log it.

Do not pretend the wiki is comprehensive. Call out gaps, unresolved questions, and contradictions clearly.

Lint Workflow

When the user asks for a health check, audit the wiki against the rules in the local AGENTS.md.

If the wiki uses the bundled default schema, the checks in skills/llm-wiki/templates/AGENTS.md are authoritative. Report findings by severity, then record meaningful lint passes in log.md.

Working With The Wiki

Bulk Ingest

When ingesting multiple sources at once:

  1. read all sources first
  2. identify shared entities and concepts across the batch
  3. search the wiki once before writing
  4. update all affected pages in one pass
  5. update index.md once at the end
  6. write one clear batch entry to log.md

For archive behavior, page shape, link style, and other schema defaults, defer to the local AGENTS.md. If the wiki was bootstrapped from the bundled defaults, skills/llm-wiki/templates/AGENTS.md is the authoritative reference.

Logging Convention

Use headings like:

md
## [2026-04-07] create | Wiki initialized
## [2026-04-07] ingest | Source Title
## [2026-04-07] query | Market map of competitors
## [2026-04-07] lint | Weekly health check
## [2026-04-07] archive | Superseded page

Keep log entries concise but specific about what changed, which files moved, and what follow-ups remain. Rotate long logs when they stop being usable.

Pitfalls

  • Do not edit or delete files under raw/ unless the user explicitly asks.
  • Do not skip orientation on an existing wiki.
  • Do not answer solely from raw sources when the wiki already contains the relevant synthesis.
  • Do not create placeholder pages with no substance just to increase coverage.
  • Do not drift from the local AGENTS.md schema defaults or customizations.
  • Do not let index.md or log.md drift behind the actual wiki state.

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

Files

SKILL.md and 10 other files in skills/llm-wiki of HybridAIOne/hybridclaw.

  • SKILL.md
  • templates/AGENTS.md
  • templates/index.md
  • templates/log.md
  • templates/raw/README.md
  • templates/raw/assets/.gitkeep
  • templates/wiki/README.md
  • templates/wiki/analyses/.gitkeep
  • templates/wiki/concepts/.gitkeep
  • templates/wiki/entities/.gitkeep
  • templates/wiki/sources/.gitkeep

Open the folder on GitHubat commit 8162701

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 skillHybridAIOne/hybridclaw159—~1.9kAutomated safety check: PassMIT
Karpathy LLM WikiAstro-Han/karpathy-llm-wiki2.5k—~3.6kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Wiki Builderrohitg00/pro-workflow2.9k—~1kAutomated safety check: PassNone
Codex History IngestAr9av/obsidian-wiki3.5k—~2.2kAutomated safety check: NotesMIT
Arkon Editnduckmink/arkon1.5k—~1.6kAutomated safety check: PassCustom licence

Similar skills

  • Karpathy LLM Wiki

    Astro-Han/karpathy-llm-wiki

    A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.

    2.5k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed

  • Wiki Builder

    rohitg00/pro-workflow

    Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.

    2.9k GitHub stars~1k tokensUpdated 12 days ago
    Knowledge ManagementAuto-check passed

  • Codex History Ingest

    Ar9av/obsidian-wiki

    Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge.

    3.5k GitHub stars~2.2k tokensUpdated today
    Knowledge ManagementAuto-check: notes

  • Arkon Edit

    nduckmink/arkon

    Propose or directly apply edits to Arkon wiki pages, including proposing brand new pages.

    1.5k GitHub stars~1.6k tokensUpdated 4 mo ago
    Knowledge ManagementAuto-check passed

  • Research Wiki Builder

    dair-ai/dair-academy-plugins

    Creates and maintains configurable research wikis: scaffold a folder, add sources, compile pages and indexes, and file query answers back.

    614 GitHub stars~1.3k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

More from HybridAIOne/hybridclaw

All 72 skills in this repo

  • Hermes3000 Writing

    HybridAIOne/hybridclaw

    Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API.

    159 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Manim Video

    HybridAIOne/hybridclaw

    Plan, script, render, and stitch Manim Community Edition videos in Python.

    159 GitHub stars~4.7k tokensUpdated today
    Auto-check: notes

  • Skill Creator

    HybridAIOne/hybridclaw

    Create and update SKILL.md-based skills with strong trigger metadata, lean docs, and reliable init, validate, package, and publish workflows.

    159 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • XLSX

    HybridAIOne/hybridclaw

    Create, edit, inspect, and analyze .xlsx spreadsheets and Excel workbooks.

    159 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Excalidraw

    HybridAIOne/hybridclaw

    Create and revise editable .excalidraw diagrams as Excalidraw JSON for architecture diagrams, flowcharts, sequence diagrams, concept maps, and other hand-drawn explainers.

    159 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Google Ads

    HybridAIOne/hybridclaw

    Manage Google Ads accounts with safe GAQL reporting, campaign planning, guarded mutations, and gateway-proxied REST API calls.

    159 GitHub stars~4k tokensUpdated today
    Auto-check passed

Categories

Questions about LLM Wiki

What does LLM Wiki do?

Build and maintain a persistent markdown wiki from raw sources using incremental ingest, indexed pages, and append-only logging. LLM Wiki is an agent skill from HybridAIOne/hybridclaw. Build and maintain a persistent markdown wiki from raw sources using incremental ingest, indexed pages, and append-only logging.

When should I use LLM Wiki?

LLM Wiki fits situations like: tasks that involve LLM wikis.

How do I install LLM Wiki in Claude Code?

Run `npx skills add HybridAIOne/hybridclaw --skill llm-wiki -a claude-code`. Or copy the skill folder (skills/llm-wiki in HybridAIOne/hybridclaw) into .claude/skills/llm-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 HybridAIOne/hybridclaw --skill llm-wiki -a codex`. Or copy the skill folder (skills/llm-wiki in HybridAIOne/hybridclaw) into .agents/skills/llm-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 HybridAIOne/hybridclaw --skill llm-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/llm-wiki, .gemini/skills/llm-wiki, .github/skills/llm-wiki and .opencode/skills/llm-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.

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 1.9k tokens (SKILL.md is roughly 7.7k 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: Karpathy LLM Wiki (Astro-Han/karpathy-llm-wiki, 2.5k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars), Wiki Builder (rohitg00/pro-workflow, 2.9k stars) and Codex History Ingest (Ar9av/obsidian-wiki, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains LLM Wiki?

HybridAIOne (a GitHub organization) maintains it in HybridAIOne/hybridclaw, which has 159 GitHub stars. The repository holds 72 skills in this directory. The repository was last updated on October 9, 2026.

Source: HybridAIOne/hybridclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.