project-numina/numina-lean-agent / skills/code-transform
code-transform
VerifiedCode transformation tools for repairing, simplifying, and extracting Lean proofs
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.1 KB |
| reference-axle-extract-theorems.md | markdown | 1.5 KB |
| reference-axle-repair-proofs.md | markdown | 1.9 KB |
| reference-axle-simplify-theorems.md | markdown | 1.6 KB |
| reference-axle-sorry2lemma.md | markdown | 1.8 KB |
reference-axle-repair-proofs.md
View on GitHub# axle repair-proofs — Auto-Fix Broken Proofs
Attempts to automatically repair failing or incomplete Lean proofs using a set of configurable repair strategies.
## CLI Invocation
```bash
python skills/cli/axle.py repair-proofs CONTENT --environment ENV [OPTIONS]
```
| Argument | Required | Default | Description |
|----------|----------|---------|-------------|
| `CONTENT` | yes | — | Lean file path or code string |
| `--environment` | yes | — | Lean environment, e.g. `lean-4.28.0` |
| `--names` | no | all | Comma-separated theorem names to repair |
| `--indices` | no | all | Comma-separated theorem indices (0-based, supports negative) |
| `--repairs` | no | all | Which repairs to apply (see below) |
| `--terminal-tactics` | no | `grind` | Tactics for closing goals, comma-separated (e.g. `grind,aesop,simp,rfl`) |
| `--ignore-imports` | no | off | Ignore imports |
| `--timeout-seconds` | no | 120 | Max execution time (max 300) |
## Available Repairs
| Repair name | What it does |
|---|---|
| `remove_extraneous_tactics` | Strips unreachable tactics after proof completion |
| `apply_terminal_tactics` | Replaces `sorry` with terminal tactics (e.g. `grind`, `aesop`) |
| `replace_unsafe_tactics` | Converts unsafe tactics (e.g. `native_decide`) to safer alternatives |
## Examples
```bash
python skills/cli/axle.py repair-proofs proof.lean --environment lean-4.28.0
python skills/cli/axle.py repair-proofs proof.lean --environment lean-4.28.0 --repairs apply_terminal_tactics --terminal-tactics "grind,omega,simp,rfl"
python skills/cli/axle.py repair-proofs proof.lean --environment lean-4.28.0 --names my_theorem
```
## Notes
- Run `python skills/cli/lean_check.py FILE` first to identify which theorems are broken before calling repair-proofs.
- `apply_terminal_tactics` is most useful when a proof is almost complete but ends in `sorry`.
- `AXLE_API_KEY` environment variable is required.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |