Code Refine

Community

alexandru

code-refine

Refines code through the three lenses in `code-refinements` with verified, behavior-preserving edits. Use when the user asks to refine a scope of code, such as a module, a directory, or the changes on a branch.

Overview

Publisher	alexandru
Repository	`skills`
Skill name	`code-refine`
Stars	51
Forks	3
Bundled files	Instructions only
Links	Skill source Repository

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 alexandru on GitHub. Read the source before you install it.

Installation

Install the Code Refine AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/alexandru/skills/tree/main/skills/engineering/code-refine
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.

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/alexandru/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/engineering/code-refine .claude/skills/code-refine

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code Refine 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 Code Refine 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 Code Refine 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.

Code Refine

The scope is whatever the user asks to refine; without one, use the current staged and unstaged diff, including untracked source files. If there is no code to refine, say so and stop. A scope that names changes — pending changes, a branch, a pull request — is refined as the diff it names; everything else is an area.

Load the code-refinements skill and hold every change to its rules and its three lenses: constraints, simplicity, and parametricity. If it is not installed, install it with:

sh
npx skills add https://github.com/alexandru/skills --skill code-refinements

Workflow

Establish scope, contracts, and verification. Read the project's agent instructions, conventions, and relevant specifications. Identify the behavior and APIs to preserve, the scope's hot paths, and the required verification. Where a specification leaves behavior undefined, investigate existing contracts and callers; report unresolved ambiguity rather than inventing a requirement.
Identify and apply justified refinements. Review through the three lenses and trace callers to check behavior claims. Each change must name the complexity it removes and preserve the contracts below. Verify edits with the relevant tests; add characterization tests where observable behavior is uncovered. Report existing bugs that require behavior changes for approval; when a fix is authorized, demonstrate it with a failing test before fixing it.
Repeat until no worthwhile improvement remains. Reassess the changed code and its core model for further justified refinements within scope. Look beyond local cleanups: a different representation can eliminate invalid states, a pass, or an entire module.
Review, verify, and report. Review the aggregate diff for regressions and interactions between changes. Fix or revert regressions, run the project's required verification across supported configurations, and rerun after fixes. Check performance when hot paths change. Report the complexity removed, authorized bug fixes and their tests, verification results and limitations, and decisions left to the user.

Invariants

Refinement is refactoring: end-user behavior MUST NOT change without explicit user authorization, including changes to fix existing bugs. Internal structure, data types, call order and intermediate representations are free to change only while preserving observable behavior. Features stay, and hot paths must not get slower.
Input the code accepted before stays accepted: a value that parsed, a request that succeeded, data already stored. A stricter input rule is a behavior change and requires authorization.
The public API is behavior — the signatures users compile against, and their doc comments, which state the contract — unless the user or project's instructions explicitly permit API changes. A change updates a doc sentence it makes false.
Tests keep running everywhere they ran before: never narrowed to the configuration CI happens to run, never deleted while their case is uncovered.
For a diff scope, refine only what the diff added or changed; reach the surrounding code only when the diff's changes force it.

Frequently asked questions

What does the Code Refine AI skill do?

Why use Code Refine on TypingMind?

Because you install it once and use it with any model. Code Refine 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 Code Refine in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alexandru/skills/tree/main/skills/engineering/code-refine. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Code Refine?

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 Code Refine?

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

Is the Code Refine AI skill free?

It is published on GitHub by alexandru. 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

Release Openclaw Mac

openclaw

OrganizationPopular

Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion.

Release Openclaw Maintainer

openclaw

OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

Release Openclaw Plugin Testing

openclaw

OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

Solid

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Code Refine

Workflow

Invariants

Frequently asked questions

Related AI Skills

Set up your own AI workspace now