x402agent/SolanaOS / skills/qedgen
qedgen
FlaggedFormally verify programs by writing Lean 4 proofs. Trigger this skill whenever the user wants to formally verify code, generate Lean 4 proofs, prove properties about algorithms or smart contracts, verify invariants, convert program logic into formal specifications, or anything involving Lean 4 and formal verification. Also trigger when the user mentions "qedgen", "lean proof", "formal proof", "verify my code", "prove correctness", "formal verification", or wants mathematical guarantees about their implementation.
crates/qedgen/templates/README.lean.md
View on GitHub# QEDGen Generated Proofs
This directory contains Lean 4 proof artifacts generated by [QEDGen](https://qedgen.dev), Mistral's proof engineering model.
## Files
- **Best.lean** - The selected proof candidate
- **prompt.txt** - The original verification prompt
- **metadata.json** - Generation metadata (timing, tokens, rankings)
- **attempts/** - All completion attempts for comparison
- **validation/** - Optional local build logs when generation was run with `--validate`
- **lean_solana/** - Local Lean support library used by generated proofs
## Verifying the Proofs
### Prerequisites
Install [Lean 4](https://leanprover.github.io/lean4/doc/setup.html):
```bash
curl https://raw.githubusercontent.com/leanprover/elan/master/elan-init.sh -sSf | sh
```
### Build and Verify
```bash
# Build the best proof
lake build Best
# Or build everything
lake build
```
If the build succeeds with no errors, the proof is formally verified!
## Notes
- The first `mathlib` build is slow. On a typical laptop, expect roughly 15 to 45 minutes.
- Zero `sorry` markers do not guarantee the file elaborates. Lean compilation is the real check.
- If Lake reports that `.lake/packages/mathlib` cannot resolve `HEAD`, remove `.lake/packages/mathlib` and rerun `lake build`.
### Checking for Incomplete Proofs
Search for `sorry` markers (incomplete proof steps):
```bash
grep -r "sorry" Best.lean attempts/
```
A proof with zero `sorry` markers is a useful signal, but not a substitute for `lake build`.
## Generated by
Generated by [qedgen-solana-skills](https://github.com/qedgen/solana-skills)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |