Lean Workflow

Community

scottnarmstrong

lean-workflow

Route Lean 4 work through a repository's Mathlib/Lake conventions. Use when editing Lean files, checking source fidelity or axioms, searching dependencies, validating focused targets, or protecting dependency build artifacts.

Overview

Publisher	scottnarmstrong
Repository	`LeanAutoformalizationSkills`
Skill name	`lean-workflow`
Stars	66
Forks	7
Bundled files	1
License	CC-BY-4.0
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.
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 scottnarmstrong on GitHub. Read the source before you install it.

Installation

Install the Lean Workflow 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/scottnarmstrong/LeanAutoformalizationSkills/tree/main/skills/lean-workflow
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/scottnarmstrong/LeanAutoformalizationSkills/tree/main/skills/lean-workflow

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

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/scottnarmstrong/LeanAutoformalizationSkills.git /tmp/LeanAutoformalizationSkills
mkdir -p .claude/skills
cp -r /tmp/LeanAutoformalizationSkills/skills/lean-workflow .claude/skills/lean-workflow

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

Use it in TypingMind

Enable Lean Workflow 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 Lean Workflow 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 Lean Workflow 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.

Lean workflow

Use this as the general router for a Lean 4 repository built with Lake and Mathlib. Read the repository's own instructions first; they override generic commands and thresholds here. Select a more focused sibling skill when it applies:

lean-project-architecture for public declarations, abstractions, module boundaries, or imports;
lean-search-discovery before attempting a new proof;
lean-proof-patterns while translating or repairing a proof;
lean-naming-style for declarations, files, namespaces, and docstrings;
lean-elaboration for measured performance diagnosis or repair;
lean-elaboration-test for a repository-wide performance snapshot;
lean-statement-audit for exact source-to-declaration correspondence;
lean-orchestrator for an explicitly authorized multi-agent formalization effort.

Use build-proof-dependency-graph for a source-level proof dependency database. It records source topology; it does not determine Lean proof status.

Build and dependency hygiene

Treat pinned dependencies and their compiled artifacts as read-only during routine project work.
Never delete dependency .olean, .ilean, trace, hash, IR, or object files as an invalidation shortcut.
Follow repository-provided build wrappers and cache guards. Otherwise validate the narrowest project target that covers the edit, for example lake build Project.Foo.Bar.
Do not run lake clean, update the toolchain or dependency pins, or trigger a full dependency rebuild without explicit authorization.
Before a destructive project-artifact invalidation, resolve the exact project-owned path and confirm that no dependency tree can match it.
Distinguish project compilation from dependency compilation in build and performance reports.

Workflow

Read AGENTS.md or CLAUDE.md, the Lake configuration, toolchain file, target module, and nearby imports.
Identify the authoritative mathematical source when a declaration represents an external claim. Preserve its binders, carriers, quantifiers, hypotheses, constants, and endpoint conditions.
Search Mathlib and the project before adding a declaration or inventing a proof route.
Do not move proof obligations into hypotheses, introduce custom axioms, or disguise unfinished proofs. Keep any explicitly authorized draft theorem quarantined and visibly marked under the repository's draft policy.
Make the smallest coherent edit and validate it with the repository's guarded command or the narrowest appropriate Lake/Lean command.
Audit affected public declarations for sorry, custom axioms, hidden stronger hypotheses, quantifier drift, and constant-dependence drift. Run #print axioms from an untracked probe or other repository-approved audit path, not from a compiled source file.
Report exact commands and targets, skipped validation, remaining placeholders, and source mismatches.

If work is delegated, obey the repository's agent policy and give each worker a bounded, disjoint task. Do not infer a model requirement, concurrency policy, or permission to spawn agents from this skill.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

agents/openai.yaml1 KB

Frequently asked questions

What does the Lean Workflow AI skill do?

Why use Lean Workflow on TypingMind?

Because you install it once and use it with any model. Lean Workflow 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 Lean Workflow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/scottnarmstrong/LeanAutoformalizationSkills/tree/main/skills/lean-workflow. 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 Lean Workflow?

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 Lean Workflow?

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

Is the Lean Workflow AI skill free?

Yes. It is published on GitHub by scottnarmstrong under the CC-BY-4.0 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

Dce Edge

vercel

OrganizationPopular

DCE-safe require() patterns and edge runtime constraints. Use when writing conditional require() calls, guarding Node-only imports (node:stream etc.), or editing define-env-plugin.ts / app-render /…

Gh Stack

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or…

Agent Transcript

Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.

Openclaw Refactor Docs

openclaw

OrganizationPopular

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Lean workflow

Build and dependency hygiene

Workflow

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now