Cyberwise Feedback logo

Cyberwise Feedback

Organization
zenobi-us
cyberwise-feedback

Help someone report a problem with Cyberwise itself, or correct something it got wrong - gather the facts the author needs, write it up, and send it to the right place (Discord or a GitHub issue). Use when someone says a cyberwise skill or tool is broken, gave wrong advice, or contradicts what they see in game; when they ask how to report a bug, request a feature, or contact the author; and when you yourself have just got something wrong and they are visibly annoyed.

Overview

Publisherzenobi-us
Repositorydotfiles
Skill namecyberwise-feedback
Stars
67
Forks
6
Bundled files
2
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.

  • 2 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 Feedback 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-feedback .claude/skills/cyberwise-feedback
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cyberwise Feedback 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 Feedback 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 Feedback 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: reporting a problem

Verified: August 2026 Re-check after a patch: Nothing here depends on a game patch. Re-check the Discord invite and the GitHub URL if either moves.

This is about Cyberwise being wrong, not about a mod being broken. If the game is misbehaving, the topic skills are for that; come here when the notes, a tool, or your own answer let somebody down.

Do the work yourself

They are reporting because they are already stuck. Handing back a form to fill in is asking them to do the diagnosis a second time, by hand.

Run the tool, write the report, then show it to them for approval. The only thing they should have to supply is what they expected to happen - and often they have already said it in the conversation you are reading.

powershell
tools\New-ProblemReport.ps1 -Summary '<one line, reads like a title>' `
    -Detail '<what happened, their words where possible>' `
    -Expected '<what they thought would happen>' -Area '<skill or tool, or unsure>'

It writes two files: the full report, and a .discord.md trimmed to fit one message. Discord refuses a message over 2000 characters rather than shortening it, so an untrimmed paste does not arrive short - it does not arrive at all.

It collects the version, the branch, whether the checkout has uncommitted changes, how the skills are installed in each agent, PowerShell and Windows versions, and the game patch only if a game root is passed. It never guesses a game path: a default that happens to exist on the wrong machine produces a plausible report about a game nobody was playing.

For anything install-shaped, attach a system profile too (cyberwise-reports) - that is where manager, load order and framework detection live, and duplicating it here is how two implementations come to disagree.

Where it goes

Both routes reach the same person. Offer both and let them pick; if they have no preference, Discord - it is faster and it does not need an account they may not have.

routewherebest for
Discordhttps://discord.gg/UltraPlace - post in the cyberpunk channel and tag @GhostWorldTourist"is this me or the tool", anything needing back-and-forth, screenshots, quick questions
GitHubhttps://github.com/GhostWorldTourist/cyberwise/issues/new/choosesomething reproducible, a wrong note, a tool that errors, a feature request - anything worth a record

Open the link for them. Do not print a URL and stop. Same rule as every other tool here: if something can be launched, launch it.

You cannot post to Discord for them. What you can do is put a finished message in their hands so the entire job is one paste.

What makes a report actionable

In order of how often each is the thing that was missing:

  1. What you expected instead. The single most useful line, and the one people leave out. "It said F3" is a fact; "it said F3 but I rebound that to F7" is a bug report.
  2. The exact text, pasted rather than paraphrased. A paraphrased error is a different error.
  3. Which version. The tool reads it from the checkout; a hand-installed copy reports unknown, which is itself worth knowing.
  4. What you were doing when it happened, in one sentence.
  5. Whether it repeats. Once is an anecdote. "Every time, on this file" is a reproduction.

Report yourself honestly

You are frequently the thing that went wrong, and you are writing the report. That is a conflict of interest and it has to be handled explicitly.

  • If your own answer was the failure, say so in the report, in the same plain words you would use about somebody else's code. A report that quietly reframes "the assistant asserted something false" as "the documentation could be clearer" wastes the author's time and buries the actual defect.
  • Do not upgrade their complaint into something more flattering, or downgrade it into something smaller. Quote them where you can.
  • Do not invent reproduction steps. If you do not know what they did, write that you do not know. A confident wrong repro sends the author looking in the wrong file for an afternoon.
  • Do not apologise in the report. It is not correspondence; it is evidence.

A correction is the most valuable kind of report

The repo's stated position is that a note which turns out to be wrong is worse than no note. So when the user's own observation contradicts something written here, that is not a minor complaint - it is the report the author most wants.

Say which file and which claim, and what they saw instead. SKILL.md files and references/*.md carry a Verified stamp naming the patch it was checked against; include it, because "true on 2.2, false on 2.31" is a different bug from "never true".

Before you send: privacy

The report is redacted by default - profile path, account name, machine name - and -NoRedact turns that off for local use only.

Three things it cannot decide for them, so ask:

  • A mod list is personal data. It discloses interests. Never attach a manifest without asking, and offer -HideNSFW when you do.
  • Never attach a save file or a decoded save. They are personal, large, and almost never the evidence anyone needs.
  • Read the report back before it goes. It is their words going out under their name, to a stranger on the internet. Show them the text, not a summary of it.

Tools

toolwhat it does
tools/New-ProblemReport.ps1gathers version, install shape and environment; writes the full report and a Discord-sized paste

The repo also ships GitHub issue forms under .github/ISSUE_TEMPLATE/ - a bug report and a "something here is wrong" correction - whose fields are the same ones this skill gathers, so a report written here can be pasted straight in.

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 Feedback AI skill do?

Help someone report a problem with Cyberwise itself, or correct something it got wrong - gather the facts the author needs, write it up, and send it to the right place (Discord or a GitHub issue). Use when someone says a cyberwise skill or tool is broken, gave wrong advice, or contradicts what they see in game; when they ask how to report a bug, request a feature, or contact the author; and when you yourself have just got something wrong and they are visibly annoyed.

Why use Cyberwise Feedback on TypingMind?

Because you install it once and use it with any model. Cyberwise Feedback 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 Feedback 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-feedback. 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 Feedback?

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 Feedback?

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

Is the Cyberwise Feedback 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 👇