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-sorry2lemma.md
View on GitHub# axle sorry2lemma — Extract Sorry into Standalone Lemmas
Lifts `sorry` placeholders (and optionally errors) inside a proof into separate, standalone lemma declarations. This makes it easier to tackle each sub-goal independently.
## CLI Invocation
```bash
python skills/cli/axle.py sorry2lemma 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 |
| `--indices` | no | all | Comma-separated theorem indices |
| `--no-extract-sorries` | no | on | Disable lifting sorries into standalone lemmas |
| `--no-extract-errors` | no | on | Disable lifting errors into standalone lemmas |
| `--no-include-whole-context` | no | on | Don't include all context variables when extracting |
| `--reconstruct-callsite` | no | off | Replace sorry with extracted lemma call |
| `--verbosity` | no | 0 | Pretty-printer verbosity (0=default, 1=robust, 2=extra robust) |
| `--ignore-imports` | no | off | Ignore imports |
| `--timeout-seconds` | no | 120 | Max execution time (max 300) |
## Examples
```bash
python skills/cli/axle.py sorry2lemma proof.lean --environment lean-4.28.0
python skills/cli/axle.py sorry2lemma proof.lean --environment lean-4.28.0 --reconstruct-callsite
python skills/cli/axle.py sorry2lemma proof.lean --environment lean-4.28.0 --verbosity 1
```
## Notes
- Use `--reconstruct-callsite` to get a version of the file where each sorry is replaced by a call to the extracted lemma — this keeps the main proof structure intact while isolating sub-goals.
- Increase `--verbosity` if the default pretty-printing produces unreadable output.
- `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: 321k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |