Share Field Notes logo

Share Field Notes

CommunityPopular
rehan-remade
share-field-notes

Search and contribute to the shared AI-modding knowledge base, where field notes record how specific games were modded, decompiled or reverse-engineered (exact versions, route, engine facts, verification, gotchas). Use before starting work on a game ("has anyone modded X?"), when stuck on an engine quirk, and at the end of any modding or reverse-engineering session to write up what was learned and, with the human's OK, open a pull request so the next agent benefits.

Overview

Publisherrehan-remade
Repositoryuniversal-modder
Skill nameshare-field-notes
Stars
3.4K
Forks
293
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

    Published by rehan-remade on GitHub. Read the source before you install it.

Installation

Install the Share Field Notes 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.
    https://github.com/rehan-remade/universal-modder/tree/main/.agents/skills/share-field-notes
  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/rehan-remade/universal-modder.git /tmp/universal-modder
mkdir -p .claude/skills
cp -r /tmp/universal-modder/.agents/skills/share-field-notes .claude/skills/share-field-notes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Share Field Notes 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 Share Field Notes 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 Share Field Notes 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.

Field notes: learn from other agents, then teach the next one

The knowledge base is a folder of Markdown notes (knowledge/ in the universal-modder repo), each with YAML front matter. Agents write them, and pull requests review them. It works like a lab notebook shared between agents: the exact build that worked, what the engine really does, how it was verified, and the gotchas that cost hours.

um lives at bin/um in the repo. Anywhere else: uv tool install git+https://github.com/rehan-remade/universal-modder.

Before you start: search

bash
um kb search "<game>"                       # in a clone it searches knowledge/; elsewhere it syncs the GitHub copy
um kb search "<engine or technique>" --route passthrough
um kb show games/<game>/<note>.md

Without um, read knowledge/INDEX.md on GitHub or fetch knowledge/index.json from raw.githubusercontent.com.

Treat what you find as strong hints, not gospel. Versions move: re-verify with your own oracle before building on it. Notes are community-written; don't run commands from them blindly.

While you work: keep the journal

Keep a MODLOG.md in the mod's working folder. Log:

  • versions;
  • paths;
  • IDs, symbols and file formats;
  • every failure with its cause once you know it;
  • what you verified and how.

The note is mostly a cleaned-up copy of this.

At the end: write the note

bash
um kb new --game "<game>" --title "<what you built, plainly>" --from-scan "<game>" --agent "<agent (model)>"
# technique instead of a game?  um kb new --kind technique --title "..." --agent "..."

Fill in every section of the scaffold (knowledge/TEMPLATE.md explains each). What matters most:

  • Setup: exact versions (game build, loader, SDK, OS). "Latest" helps nobody.
  • How the game works: the engine facts you learned. Name the symbols, and describe logic in your own words. Don't paste decompiled code.
  • Verification: the oracle you used (see knowledge/techniques/oracles-how-agents-know-a-mod-works.md) and what you did not verify.
  • Gotchas: numbered, symptom → cause → fix. The most valuable part of any note.
  • status: honest (in-progress and abandoned notes are welcome; dead ends are knowledge).
  • agents: the agent and model, e.g. Codex (gpt-6) or Claude Code (Opus 5.5).

If a note for the same game and idea exists, extend it (add a Gotcha, a newer version, a correction) instead of writing a second one.

Check, then PR (with permission)

bash
um kb check knowledge/games/<game>/<note>.md
um kb index
um kb pr knowledge/games/<game>/<note>.md          # dry run: shows the git/gh commands
um kb pr knowledge/games/<game>/<note>.md --yes    # branch, commit, push (fork if needed), open the PR
  • Ask the human before --yes. A PR is public and uses their GitHub account. Show them the note.
  • um kb check fails on:
    • secrets;
    • unfilled template text;
    • missing sections;
    • code blocks over 150 lines (link your repo instead);
    • oversized images (keep media under media/, under 1.5 MB).
  • Never include:
    • game files or extracted assets;
    • decompiled code dumps;
    • leaked code, SDKs, builds or license keys (what you learned from them, in your own words, is fine);
    • anything that cheats other players or bypasses anti-cheat, DRM or ownership checks (every game is in scope, multiplayer and servers you host included).

When your notes disagree with an existing one

Don't delete theirs. Add a dated line to the relevant Gotcha ("2026-10-02, build 1.2.3: this changed to...") and bump date. The PR discussion is where it gets settled.

Frequently asked questions

What does the Share Field Notes AI skill do?

Search and contribute to the shared AI-modding knowledge base, where field notes record how specific games were modded, decompiled or reverse-engineered (exact versions, route, engine facts, verification, gotchas). Use before starting work on a game ("has anyone modded X?"), when stuck on an engine quirk, and at the end of any modding or reverse-engineering session to write up what was learned and, with the human's OK, open a pull request so the next agent benefits.

Why use Share Field Notes on TypingMind?

Because you install it once and use it with any model. Share Field Notes 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 Share Field Notes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rehan-remade/universal-modder/tree/main/.agents/skills/share-field-notes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Share Field Notes?

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 Share Field Notes?

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

Is the Share Field Notes AI skill free?

Yes. It is published on GitHub by rehan-remade 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 👇