Clj Refactor logo

Clj Refactor

Community
humorless
clj-refactor

Scan files for mechanism/policy separation opportunities

Overview

Publisherhumorless
Repositoryclj-native-agent
Skill nameclj-refactor
Stars
51
Forks
0
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by humorless on GitHub. Read the source before you install it.

Installation

Install the Clj Refactor 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/humorless/clj-native-agent/tree/main/skills/clj-refactor
  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/humorless/clj-native-agent.git /tmp/clj-native-agent
mkdir -p .claude/skills
cp -r /tmp/clj-native-agent/skills/clj-refactor .claude/skills/clj-refactor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Clj Refactor 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 Clj Refactor 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 Clj Refactor 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.

Scan the specified files or directory for opportunities to improve mechanism/policy separation, following the principles below.

What to Look For

Using Arne Brasseur's definitions:

Mechanism is code that is:

  • Unopinionated and context-free
  • Reusable across different business domains
  • Easy to test in isolation
  • Stable — changes slowly over time

Policy is code that is:

  • Opinionated — reflects current business decisions
  • Contextual — tied to a specific domain
  • Expected to change frequently

The distinction is not in what the code does, but in how it is written. The goal is to push code toward the edges of this spectrum.

Diagnostic Heuristics

When assessing where code sits on the spectrum, ask:

  • Does this code accept all its dependencies as explicit parameters, or does it rely on defaults, globals, or implicit context? (More explicit → more mechanism)

  • If you needed to reuse this logic elsewhere, would you call it with different parameters, or copy-paste and modify it? (Parametric reuse → mechanism; copy-paste reuse → policy)

  • Is this code expressing a stable technical fact, or a current business decision? Business decisions belong in policy.

  • How hard-coded are the values? Hard-coded constants are a sign that policy has leaked into mechanism.

  • Does this code prioritize convenience (easy) over explicitness (simple)? Convenience-oriented defaults are often policy leaking into mechanism.

Your Task

For each file or module examined, report:

  1. Mixed code — functions or modules where mechanism and policy are tangled together. Describe what is mixed and where the boundary should be drawn.

  2. Extraction candidates — pieces of mechanism that are currently embedded in policy code and could be extracted into a separate module or library. For each candidate, explain why it qualifies as mechanism (context-free, stable, reusable).

  3. Misplaced policy — business logic that has drifted into what should be low-level mechanism. Describe what assumption is hidden and where it belongs.

  4. Proposed refactoring — for each finding, suggest a concrete refactoring. Show the before/after structure, not just the principle.

Constraints

  • Do not refactor prematurely. Only suggest extraction when a pattern appears in at least two distinct use cases.
  • Preserve existing behavior. This is a structural refactor, not a rewrite of business logic.
  • Keep suggestions grounded in the actual code. Do not propose abstractions that have no evidence in the current codebase.

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 Clj Refactor AI skill do?

Scan files for mechanism/policy separation opportunities

Why use Clj Refactor on TypingMind?

Because you install it once and use it with any model. Clj Refactor 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 Clj Refactor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/humorless/clj-native-agent/tree/main/skills/clj-refactor. 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 Clj Refactor?

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 Clj Refactor?

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

Is the Clj Refactor AI skill free?

It is published on GitHub by humorless. 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 👇