Arkon Review logo

Arkon Review

CommunityPopular
nduckmink
arkon-review

Review, approve, request changes on, or reject pending wiki edit drafts in Arkon. Requires editor or admin role. Triggers on: review drafts, pending reviews, check draft queue, approve draft, reject draft, request changes, send draft back, review wiki changes.

Overview

Publishernduckmink
Repositoryarkon
Skill namearkon-review
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 Review 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-review .claude/skills/arkon-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Arkon Review 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 Review 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 Review 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-review: Review Wiki Drafts

Editor/admin only. If list_pending_drafts returns a permission error, you don't have the required role.


Review Workflow

1. List pending drafts

list_pending_drafts()

Returns: draft ID, page slug, author, timestamp, note. Filter by workspace if needed:

list_pending_drafts(workspace_id="<uuid>")

2. Read a draft for review

review_draft(draft_id)

Returns side-by-side: proposed content and current page content (vN). Read both carefully.

You may also call read_wiki_page(slug) independently for fuller backlink context.

3. Decide

Approve as-is:

approve_draft(draft_id, reviewer_note="optional feedback to author")

Approve with your own edits (you want to tweak before publishing):

approve_draft(draft_id, edited_content_md="...", reviewer_note="approved with minor edits")

Request changes (the draft is on the right track but needs fixes; preferred over reject when iteration is realistic):

request_changes_on_draft(draft_id, reviewer_note="20+ char explanation — what to change and why")

The draft moves to needs_revision; author can resubmit_draft after addressing the note. The original draft stays — revision_round increments each round and prior submissions are snapshotted for diffing.

Reject (only when the proposal is fundamentally wrong — out of scope, factually broken, or duplicates an existing page):

reject_draft(draft_id, reviewer_note="clear reason why — required")

reviewer_note is required for both reject and request_changes — the author needs to understand what to fix. Prefer request_changes over reject unless the proposal cannot be salvaged.

Conflict on approve: if the page advanced past the draft's base_version while you were reviewing, approve_draft returns a conflict error. Re-call with allow_conflict=true to overwrite, or supply edited_content_md after merging the latest content yourself.

Self-approve is blocked: the server rejects approve attempts where the reviewer is also the author. Ask another editor.


Approving a create draft

When the draft was filed via propose_wiki_create, it has draft_kind: "create" and no page exists yet — approval materialises a new page using the contributor's suggested metadata. The reviewer may override before commit via the REST endpoint body (in the portal UI):

  • final_slug — adjust the URL slug
  • final_title — adjust the display title
  • final_page_type — change page_type
  • final_knowledge_type_slugs — fix the taxonomy tags (matters for RBAC)

Why adjust metadata? RBAC visibility is driven by knowledge_type_slugs; slug shapes the URL forever; page_type affects how the page renders in the index. Contributors are often not aware of the conventions — quietly fixing these at approve is cheaper than asking them to resubmit.

If the slug already exists in the target scope, approval returns 409 slug_conflict — override final_slug or send the draft back with a request_changes note explaining why.


AI pre-review signals

Every draft carries an AI verdict (ai_check_status plus a list of checks):

  • passed — no warnings. Most likely safe to approve after a quick read.
  • warned — soft issues: broken wikilinks, possible duplicates, tone drift, scope-fit doubts. Read them; some are noise, some matter.
  • failed — at least one PII / secret regex match. Read each match carefully. The contributor may have meant to include it (look for a <!-- pii-allow: ... --> marker above the match). If not, that's a request_changes situation.

The AI never blocks approval — it's a checklist, not a gate. Trust your own judgment.


Review Checklist

Before approving, verify:

  • Content is factually consistent with other wiki pages (check backlinks if unsure)
  • No sensitive data (PII, credentials, confidential figures) exposed
  • Wikilinks [[slug]] point to real pages, not broken references
  • Tone matches the KB style (factual, neutral, encyclopedic)
  • The change note from the author makes the intent clear

Batch Review

For multiple drafts:

  1. list_pending_drafts() — get the full queue.
  2. Group by page type or workspace if useful.
  3. review_draft each one in order.
  4. Approve/reject individually — do not bulk approve without reading each.

Always confirm with the user before approving a batch of more than 3 drafts in one go.


Notes

  • Approving a draft writes directly to the wiki page and creates a revision in history.
  • Rejected drafts stay in the system with status: rejected — they are not deleted.
  • You cannot approve your own drafts (the server enforces this).

Frequently asked questions

What does the Arkon Review AI skill do?

Review, approve, request changes on, or reject pending wiki edit drafts in Arkon. Requires editor or admin role. Triggers on: review drafts, pending reviews, check draft queue, approve draft, reject draft, request changes, send draft back, review wiki changes.

Why use Arkon Review on TypingMind?

Because you install it once and use it with any model. Arkon Review 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 Review in TypingMind?

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

Which AI models can use Arkon Review?

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 Review?

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

Is the Arkon Review 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 👇