lean-formalization
Skill0 starsChanged 33 days agoMITView on GitHub
Translate a specified mathematical statement and proof into Lean, reuse existing library results, and resolve formal proof obligations. Use when formalization is requested or a concrete research step benefits from it; general proof search does not require Lean.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- VeryMath/AI4Math-Lean-Agentstheir own version, first seen Oct 11, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- VeryMath/AI4Math-Lean-Agents★ 9same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- contribution-reviewSkill
- lean-verificationSkill
- proof-auditSkill
- research-briefSkill
- research-closeoutSkill
- research-momentumSkill
- research-orchestrationSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Use the formalization handoff when delegating a translation.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lean Formalization
Formalize the requested mathematics without changing the theorem to make the code easier. Treat successful translation as useful mathematical progress, and keep analytical research moving on complete proofs while formalization proceeds separately.
Establish the statement and environment
- Record the original statement, definitions, hypotheses, quantifiers, and conclusion. Map these to the Lean declaration, including implicit arguments, typeclasses, domains, and conventions. For an equivalent formulation, supply the equivalence argument.
- Inspect the project's
lean-toolchain, Lake configuration, dependency lockfile, existing modules, and conventions. Use that environment and its exact versions. Check the tools actually available; do not install or upgrade Lean, mathlib, or an MCP server without authorization. - Search the existing project and its libraries before proving a standard fact again. Cite the reused declaration and verify that its hypotheses match. Use available Lean-LSP tools for goals, diagnostics, or library search; otherwise use the project's Lean/Lake commands. An MCP connection is optional.
Work on the decisive obligations
Choose a small load-bearing lemma or requested theorem. Preserve the source proof's structure where useful, but use idiomatic library arguments rather than translating every prose sentence into a tactic. Temporary sorry placeholders can expose the remaining goals during development; label the file as incomplete and remove them from the target's dependency closure before claiming completion.
Never add the target, an equivalent conjecture, or the missing decisive lemma as an axiom to finish the task. Do not silently strengthen assumptions, specialize a universal theorem to finite cases, or substitute a different definition with the same printed name. If a requested statement is false, show the obstruction and propose an explicitly changed theorem.
Distinguish a missing library lemma, an elaboration problem, and a missing mathematical argument. Resolve concrete formal obstacles with a bounded next step. A stalled formalization does not revoke a complete analytical proof; a substantive counterexample or logical gap does justify reopening that proof.
Once one coherent proof change is ready, run the narrow relevant project check and inspect diagnostics. Pass the exact declaration, statement mapping, environment, and target dependencies to lean-verification when formal assurance is requested. Compilation alone is not that assurance.
Deliver and continue
State what is now formalized and why it matters. Report the exact remaining goals if incomplete, with a useful next action rather than a blanket inability claim. Use established analytical lemmas immediately within their proved scope; do not require external acceptance or whole-manuscript formalization before further research.
Use the formalization handoff when delegating a translation. Read Lean assurance when checking formal completion or interpreting tool limitations. Respect pauses: save the target declaration and unresolved goals, and start no new formalization campaign.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

