Arkon Query logo

Arkon Query

CommunityPopular
nduckmink
arkon-query

Answer questions using the Arkon knowledge base. Searches wiki first, drills into raw sources only when needed. Supports quick, standard, and deep modes. Triggers on: what do we know about, find in KB, look up, query:, arkon query, search the wiki, tell me about, based on the KB.

Overview

Publishernduckmink
Repositoryarkon
Skill namearkon-query
Stars
1.4K
Forks
291
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by nduckmink on GitHub. Read the source before you install it.

Installation

Install the Arkon Query AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/nduckmink/arkon.git /tmp/arkon
mkdir -p .claude/skills
cp -r /tmp/arkon/skills/arkon-query .claude/skills/arkon-query
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Arkon Query in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Arkon Query on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Arkon Query is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

arkon-query: Query the Knowledge Base

The wiki has already done the synthesis work. Read strategically, answer precisely. Raw sources are a fallback — not the first stop.


Query Modes

ModeTriggerTools usedBest for
Quickquery quick: ... or simple factual Qsearch_wiki onlyDirect lookups, names, dates
Standarddefaultsearch_wiki → 2-4 pagesMost questions
Deepquery deep: ... or "thorough", "find everything"Full wiki traverse + source drill-downCross-cutting synthesis

Quick Mode

  1. Call search_wiki(query, top_k=5). If the top result has high similarity (≥ 80%) and its summary answers the question, respond immediately.
  2. If not satisfied, call read_wiki_page(slug) for the top 1-2 results.
  3. If still not found, say "Not in quick cache — run as standard query?"

Do not call read_wiki_index or source tools in quick mode.


Standard Query Workflow

  1. search_wiki(query) — ranked list of pages. Read summaries.
  2. read_wiki_page(slug) for the 2-4 most relevant results. Follow wikilinks [[slug]] at depth 1 only if they look essential.
  3. Synthesize the answer in chat. Cite with page slugs: (Source: concept/onboarding).
  4. If the question reveals a gap: "I don't have enough on X in the KB. Want to check the raw sources?"

Deep Mode

  1. search_wiki + read_wiki_index to map coverage.
  2. Read all relevant pages. Follow wikilinks at depth 2 if needed.
  3. If wiki coverage is thin for a specific claim, drill into raw sources (see below).
  4. Always cite both wiki pages and source documents used.

Source Drill-Down (citations or precise text)

Use when: the wiki has paraphrased something and you need the exact wording, or the user asks "what does the document actually say."

list_sources(knowledge_type=...)     → find source IDs by category
get_source(source_id)                → check metadata and page count
get_source_outline(source_id)        → find the right section (TOC)
get_source_pages(source_id, "5-7")   → read exact pages

Do not call get_source_pages without first checking get_source_outline on documents > 10 pages.


Browsing by Category

When the user asks "what's in the X category" or wants to explore a knowledge type:

list_knowledge_types()               → see all categories + doc counts
get_knowledge_type_docs(slug)        → docs in that category
list_wiki_pages(knowledge_type=slug) → wiki pages tagged to that category

Token Discipline

Start withWhen to stop
search_wikiIf summary has the answer
2-4 wiki pagesUsually sufficient for standard queries
get_source_outlineBefore reading pages of a long source
get_source_pagesRead only the specific pages needed

Never read more than 6 wiki pages for a standard query. For deep mode, cap at 15 unless the question explicitly demands full coverage.


RBAC Notes

  • Your MCP token determines which knowledge types you can access.
  • search_wiki, read_wiki_page, and list_wiki_pages automatically filter to your allowed types.
  • list_sources and get_source_pages enforce per-source scope.
  • If you get "Access denied" or "out of scope", the content exists but is outside your token's permissions — tell the user and suggest they contact an admin.

Frequently asked questions

What does the Arkon Query AI skill do?

Answer questions using the Arkon knowledge base. Searches wiki first, drills into raw sources only when needed. Supports quick, standard, and deep modes. Triggers on: what do we know about, find in KB, look up, query:, arkon query, search the wiki, tell me about, based on the KB.

Why use Arkon Query on TypingMind?

Because you install it once and use it with any model. Arkon Query is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Arkon Query in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nduckmink/arkon/tree/main/skills/arkon-query. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Arkon Query?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Arkon Query?

As many as you like. As long as a model supports skills, you can use Arkon Query with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Arkon Query AI skill free?

It is published on GitHub by nduckmink. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇