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-extract-theorems.md
View on GitHub# axle extract-theorems — Split File into Individual Theorems
Parses a Lean file and returns structured metadata for each theorem/definition, including its signature, type, dependencies, and proof statistics.
## CLI Invocation
```bash
python skills/cli/axle.py extract-theorems 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` |
| `--ignore-imports` | no | off | Ignore imports |
| `--timeout-seconds` | no | 120 | Max execution time (max 300) |
## Output
Returns per-theorem records containing:
- `declaration` — full declaration text
- `signature` — theorem signature
- `type` — elaborated type
- `type_hash` — hash of the type (for deduplication)
- `is_sorry` — whether the proof contains sorry
- `dependencies` — list of referenced declarations
- `tactic_counts` — frequency of each tactic used
- `proof_length` — number of proof steps
## Examples
```bash
python skills/cli/axle.py extract-theorems mathlib_file.lean --environment lean-4.28.0
python skills/cli/axle.py extract-theorems "theorem foo : 1 + 1 = 2 := by norm_num" --environment lean-4.28.0
```
## Notes
- Useful for analysis, dataset construction, or understanding a file's structure before modifying it.
- `is_sorry` can be used to quickly identify which theorems still need proofs.
- `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: 319k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 319k | 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: 319k | 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: 319k | Updated | Claude CodeCodex | Verified | Install |