Proof Readability logo

Proof Readability

Community
morankor
proof-readability

Polish verified mathematical proofs without changing their mathematical content. Use after a proof has been accepted by the user, a reviewer, Lean, or a co-math review cycle; or when asked to improve proof exposition, readability, signposting, notation, references, or grammar while preserving the original argument.

Overview

Publishermorankor
Repositorytheorist-toolbox
Skill nameproof-readability
Stars
92
Forks
23
Bundled files
1
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.

  • 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 morankor on GitHub. Read the source before you install it.

Installation

Install the Proof Readability 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/morankor/theorist-toolbox/tree/master/codex/.agents/skills/proof-readability
  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/morankor/theorist-toolbox.git /tmp/theorist-toolbox
mkdir -p .claude/skills
cp -r /tmp/theorist-toolbox/codex/.agents/skills/proof-readability .claude/skills/proof-readability
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Proof Readability 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 Proof Readability 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 Proof Readability 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.

Proof Readability

Edit only proofs whose correctness has already been accepted. This is an exposition pass, not a proving pass.

Prime invariant: never change the mathematics. Do not strengthen, weaken, replace, or silently repair an argument. If you find a real gap, stop editing that proof and report the gap precisely.

Preconditions

Before editing, confirm one of:

  • the user says the proof is already verified,
  • a co-math workstream has an approval file,
  • a Lean build or other formal check accepted the statement,
  • the task is explicitly limited to readability comments rather than direct edits.

If correctness is not established, offer a math-proof or codex-math verification pass first.

Six-Layer Pass

Work in this order:

  1. Architecture: restate deferred results, add proof sketches where appropriate, make theorem/lemma roles clear, close composite proofs explicitly.
  2. Signposting: add proof openers, named steps, exhaustive case labels, assumption open/close markers, and goal statements before algebra.
  3. Line-level justification: add reasons for inequalities, signs, substitutions, citations, and relation chains.
  4. Notation hygiene: define symbols before use, recall object types, stabilize names, check argument order, and avoid notation dumps.
  5. Intuition: add short "in words" or intuition paragraphs outside the formal proof. Keep every intuition sentence literally defensible.
  6. Sentence and formula grammar: make formulas part of grammatical sentences, avoid starting sentences with symbols, replace logical shorthand in prose, and run read-aloud checks.

Safe Edits

  • Add signposts and roadmap sentences.
  • Expand an algebraic step already implicit in the proof.
  • Move definitions earlier when the definition itself is unchanged.
  • Fix references, labels, theorem names, punctuation, and prose grammar.
  • Add intuition after the proof or outside the formal argument.

Contested Edits

Propose these in a report; do not apply them without explicit approval:

  • replacing a contradiction proof with a direct proof,
  • merging or splitting lemmas,
  • changing standing assumptions,
  • changing theorem statements, quantifiers, bounds, or conclusions,
  • reordering an equality or inequality chain when the new order itself needs proof.

Banned Phrases

Remove or replace:

  • clearly,
  • obviously,
  • it is easy to see,
  • straightforward,
  • similar argument omitted,
  • by inspection,
  • this dominates that,
  • follows naturally.

Replace each with the actual reason, a precise reference, or a flagged gap.

Report

When done, summarize:

  • edits by layer,
  • any suspected gaps that were not edited,
  • any derived intermediate lines that need correctness spot-checking,
  • contested edits proposed but not applied,
  • remaining unresolved references or undefined symbols.

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 Proof Readability AI skill do?

Polish verified mathematical proofs without changing their mathematical content. Use after a proof has been accepted by the user, a reviewer, Lean, or a co-math review cycle; or when asked to improve proof exposition, readability, signposting, notation, references, or grammar while preserving the original argument.

Why use Proof Readability on TypingMind?

Because you install it once and use it with any model. Proof Readability 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 Proof Readability in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/morankor/theorist-toolbox/tree/master/codex/.agents/skills/proof-readability. 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 Proof Readability?

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 Proof Readability?

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

Is the Proof Readability AI skill free?

Yes. It is published on GitHub by morankor 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 👇