Cross Platform Care logo

Cross Platform Care

Community
adamentwistle
cross-platform-care

Write scripts, paths, and file I/O that survive a machine they weren't developed on — path separators, shell dialects, quoting, line endings, case-sensitivity, missing or divergent tools, timezones. Use when writing shell or PowerShell scripts, CI steps, Makefiles or justfiles, path manipulation, file reads and writes, or install/setup instructions others will run. Not for pure in-memory logic.

Overview

Publisheradamentwistle
Repositoryfable-skills
Skill namecross-platform-care
Stars
98
Forks
11
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 adamentwistle on GitHub. Read the source before you install it.

Installation

Install the Cross Platform Care 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/adamentwistle/fable-skills/tree/main/cross-platform-care
  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/adamentwistle/fable-skills.git /tmp/fable-skills
mkdir -p .claude/skills
cp -r /tmp/fable-skills/cross-platform-care .claude/skills/cross-platform-care
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cross Platform Care 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 Cross Platform Care 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 Cross Platform Care 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.

cross-platform-care

"Works on my machine" is an environment assumption you didn't notice making (environment-first is the cure; this is the prevention). Weak portability is a script tested once on the author's laptop; strong portability names its targets and checks against the one it isn't on.

Before writing: name the targets

State which platforms and shells the artifact must run on (e.g. "Linux CI with /bin/sh = dash, macOS zsh, Windows PowerShell 7"). Check what the repo already commits to: CI matrix, existing shebangs, .editorconfig, .gitattributes, engines / requires-python. If it targets one platform only, say so in a comment at the top and stop portability work there.

1. Paths

Build paths with the path library, never string concatenation with / or \: pathlib / os.path.join, path.join, filepath.Join. Same for home (~ doesn't expand everywhere), temp dirs (platform API or the session scratchpad), and current-dir assumptions (derive absolute paths from a known root such as the script's own location). On Windows also avoid reserved names (CON, NUL, aux) and trailing dots or spaces in filenames.

2. Shell dialect

Declare the shell you actually target. Bashisms ([[, arrays, set -o pipefail, local, $'...') fail in POSIX sh; CI images often ship dash as /bin/sh; zsh differs on word splitting and globs. Use #!/usr/bin/env bash if you need bash, #!/bin/sh only if it is genuinely POSIX. PowerShell is a different language, not a dialect — never mix its syntax with sh.

3. Quoting and arguments

Quote every expansion ("$var", "$@"); unquoted expansion breaks on the first path with a space, which is every macOS user directory. Put -- before positional args to guard filenames with leading dashes. Never build a command by pasting user-supplied strings into a shell line — pass argv arrays.

4. Case-sensitivity

macOS and Windows filesystems are usually case-insensitive; Linux is not. import utils finds Utils.py locally and dies in CI. Imports, includes, asset URLs, and case-only renames must match the file's real casing — verify with git ls-files, not the editor's view.

5. Line endings and encodings

CRLF from Windows checkouts breaks shebangs, heredocs, and string comparisons; declare *.sh text eol=lf in .gitattributes. Declare encoding explicitly when reading or writing text (encoding="utf-8"); never inherit the platform default. Choose newline handling explicitly on write.

6. Tools and versions

Don't assume a tool exists or matches: GNU vs BSD flags differ (sed -i '', date -d vs -v, grep -P, readlink -f, xargs -r); python may be v2, absent, or a Store alias on Windows. Probe with command -v <tool> and fail with a message naming what's missing; version-check anything whose behavior you depend on; prefer the portable subset when it's cheap.

7. Time

Servers run UTC; laptops don't. Code that formats, parses, or compares timestamps names its zone explicitly; tests that depend on "today" pin the clock (see edge-case-sweep).

Exit check

Run a check under the target you're not on before shipping: shellcheck or sh -n / bash -n for a Linux target from macOS or Windows, WSL or a container for a full run, pwsh -NoProfile -File for PowerShell. Then answer: "would this run on a fresh Linux CI container and on a laptop with a space in the username?" Both, or the header says which one it targets.

Frequently asked questions

What does the Cross Platform Care AI skill do?

Write scripts, paths, and file I/O that survive a machine they weren't developed on — path separators, shell dialects, quoting, line endings, case-sensitivity, missing or divergent tools, timezones. Use when writing shell or PowerShell scripts, CI steps, Makefiles or justfiles, path manipulation, file reads and writes, or install/setup instructions others will run. Not for pure in-memory logic.

Why use Cross Platform Care on TypingMind?

Because you install it once and use it with any model. Cross Platform Care 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 Cross Platform Care in TypingMind?

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

Which AI models can use Cross Platform Care?

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 Cross Platform Care?

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

Is the Cross Platform Care AI skill free?

Yes. It is published on GitHub by adamentwistle 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 👇