Cyberwise Recommends logo

Cyberwise Recommends

Organization
zenobi-us
cyberwise-recommends

Tell someone a mod is missing only when it actually blocks what they are doing, and never twice - the capability checks behind "you cannot do that without X", and the on-disk preference that records a no. Use when a requested task needs a tool the install does not have, and before mentioning any mod nobody asked about.

Overview

Publisherzenobi-us
Repositorydotfiles
Skill namecyberwise-recommends
Stars
67
Forks
6
Bundled files
3
LicenseMIT
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zenobi-us on GitHub. Read the source before you install it.

Installation

Install the Cyberwise Recommends 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/zenobi-us/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/files/devtools/agent/bundles/developer/skills/game-dev/cyberwise-recommends .claude/skills/cyberwise-recommends
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cyberwise Recommends 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 Cyberwise Recommends 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 Cyberwise Recommends 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.

Cyberwise: recommending, sparingly

Verified: Cyberpunk 2077 patch 2.31 - August 2026

Load cyberwise alongside this for the method rules.

This skill exists to say one useful sentence at the right moment, and to shut up otherwise. It is not a modlist, not a starter pack, and not a curated collection. cyberwise-reports/tools/Compare-Collection.ps1 already carries the rule this skill inherits:

It is not a shopping list and must not be presented as one.

Hard cap: about six items. If the capability table grows past that, this skill has become the thing it was written to avoid. Adding a row requires a concrete loss - something that becomes impossible or invisible without it. "Popular", "most people use it" and "it's really good" are not criteria.

The distinction the whole skill turns on

what it iscan the user mute it?
Prerequisitethey asked for something this install cannot doNo. It is the answer to their question
Recommendationnobody asked; you noticed something missingYes, and permanently

Getting this backwards in either direction is the failure mode.

Suppressing a prerequisite leaves someone staring at an empty result with no explanation - "you have no appearance presets" is a lie of omission when the truth is "nothing here creates them". Treating a recommendation as a prerequisite is how a helpful tool turns into an upsell.

Concretely: asked to read appearance presets on an install with no ACU, say that ACU is what creates them and there are none. Asked about textures on that same install, say nothing about ACU at all.

Before you mention a mod nobody asked about

powershell
. tools\ModPreference.ps1
Test-RecommendAllowed -Item 'Appearance Change Unlocker'    # false -> silence

False means silence, not a softer mention. A user who said no and gets a gentler version of the same suggestion has been ignored, and knows it.

Then, if they say no:

powershell
Register-Decline -Item 'Appearance Change Unlocker' -Reason 'not interested'
Set-RecommendMode -Mode off        # "don't recommend mods to me, ever"

One item per conversation. Once, ever. A decline is permanent and dated. Asking twice is the failure this skill exists to prevent, and "I forgot" is not a defence the user can see.

Where the preference lives, and why not in memory

%USERPROFILE%\Saved Games\CD Projekt Red\Cyberpunk 2077\Cyberwise\preferences.json

An agent's memory is good local mutable config and a bad authority for a rule that governs behaviour:

  • this family runs under Claude Code and Codex, and one agent's memory is invisible to the other;
  • the skills ship to other people, whose agent has no memory of anyone's preferences and must not need one;
  • a preference that governs a tool should be readable and editable by the person it governs.

An agent may also note the preference in its own memory. That is a cache. When the two disagree the file wins, and the memory is what gets corrected.

The store fails closed: an unreadable preferences.json is treated as recommendations: off. A corrupt file must never silently re-enable something the user switched off.

Tools here

toolwhat it does
tools/Test-Capabilities.ps1what this install cannot do, and what is missing to do it
tools/ModPreference.ps1read and record what the user has already said
powershell
tools\Test-Capabilities.ps1 -GameRoot '<path>'                # the table
tools\Test-Capabilities.ps1 -GameRoot '<path>' -For presets   # exit 1 if blocked

-For is the gate other skills call before promising something. It names the missing dependency chain too - "install ACU" is useless advice to somebody who has no CET.

What is deliberately not here

The framework layer. cyberwise/tools/Test-InstallReady.ps1 already checks RED4ext, redscript, CET, ArchiveXL, TweakXL and Codeware, and answers "would launching work". That is a readiness question. This skill answers a capability question, and covers the CET-mod layer readiness does not - ACU above all, because its absence is invisible: the appearance tools in cyberwise-saves find an empty folder and report nothing wrong.

Anything version-shaped. "Your ArchiveXL is out of date" belongs to readiness, not here.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cyberwise Recommends AI skill do?

Tell someone a mod is missing only when it actually blocks what they are doing, and never twice - the capability checks behind "you cannot do that without X", and the on-disk preference that records a no. Use when a requested task needs a tool the install does not have, and before mentioning any mod nobody asked about.

Why use Cyberwise Recommends on TypingMind?

Because you install it once and use it with any model. Cyberwise Recommends 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 Cyberwise Recommends in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zenobi-us/dotfiles/tree/master/files/devtools/agent/bundles/developer/skills/game-dev/cyberwise-recommends. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cyberwise Recommends?

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 Cyberwise Recommends?

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

Is the Cyberwise Recommends AI skill free?

Yes. It is published on GitHub by zenobi-us under the MIT license. 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 👇