odinfree/storm-ecdsa-harness / skills/fast-lean-proof-loop
fast-lean-proof-loop
VerifiedShorten Lean 4 proof iteration with a warm editor session, dependency-aware reverse-import build plans, and lemma lookup that Lean itself confirms, while a separate full build plus axiom audit stays the promotion gate.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.5 KB |
| agents/openai.yaml | config | 324 B |
| references/promotion-gate.md | markdown | 1.1 KB |
| scripts/lean_fast_loop.pyexecutable | script | 10.3 KB |
| scripts/lean_symbol_check.pyexecutable | script | 6.3 KB |
| scripts/test_lean_fast_loop.pyexecutable | script | 3.8 KB |
| scripts/test_lean_symbol_check.pyexecutable | script | 2.6 KB |
references/promotion-gate.md
View on GitHub# Promotion gate
Incremental compilation answers whether the changed dependency closure builds against the current cache. It does not establish acceptance.
Before promoting a better.codes Lean candidate, record and pass every project-required gate, including:
1. authoritative worktree, Git head, dirty-state scope, pinned Lean version, and ArkLib revision;
2. exact official `Solution.lean` target build after the final edit;
3. repository-wide build or evaluator build required by the benchmark policy;
4. `sorry`, `admit`, placeholder, forbidden import, and source-size checks;
5. `#print axioms` or the repository axiom checker for the submitted theorem and its load-bearing providers;
6. independent exact replay or falsifier for the claimed arithmetic or construction;
7. refreshed live frontier and separate official evaluator receipt when authorized.
A passing language server, one affected target, an existing `.olean`, or a successful `#check` batch cannot replace these gates. If final-gate output disagrees with the incremental receipt, classify the incremental result as stale or incomplete and repair the dependency model before continuing.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |