lean4 theorem proving

Name: lean4 theorem proving
Author: benchflow-ai

by benchflow-ai·18d ago

Use when working with Lean 4 (.lean files), writing mathematical proofs, seeing "failed to synthesize instance" errors,…

Claude CodeCodexLow risk · 低风险open source · 开源

Editor's verdict· 编辑结论

Auto-published by GitHub discovery based on star threshold.
— Editorial team · 编辑团队

Install via Skills CLI

Use npx skills add to install this skill into the selected agent. Phase 0 commands are generated from source rules, not verified.

Codex

npx skills add https://github.com/benchflow-ai/skillsbench/blob/main/tasks/lean4-proof/environment/skills/lean4-theorem-proving/SKILL.md -g -a codex -y

Drop `-g` to install project-locally

✓

Best for适合什么场景

High-star GitHub skill discovery candidate.

✗

Not for不适合什么场景

Sensitive or production workflows without local review.

vs alternativesvs 其他选择

Full compare table完整对比表 →

#1Anthropic Skill Creator

Create, test, and improve skills in an eval loop.

★ 4.9·122k stars

diff · 差异Best first pick for teams getting serious about authoring reusable skills. The workflow is built around an eval loop: describe the workflow, write trigger examples and expected outputs, then iterate until the skill fires only when it should. Official Anthropic provenance means trigger-description quality and frontmatter format match what Claude actually loads. Not for one-off automation — the eval setup overhead doesn't pay off unless the skill ships to other people.

#2Nuwa Skill

Distill how a person thinks into a reusable skill.

★ 4.7·14k stars

diff · 差异Best when the skill you want to ship is really a captured way of thinking — a researcher's framing, a senior engineer's review checklist, a designer's heuristics. Walks through source material in a research-first loop, extracts mental models, then encodes them into a triggerable skill. Slow and material-hungry on purpose. Skip it for quick automation; use anthropic-skill-creator for that.

#3everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

187k stars

diff · 差异Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

Side-by-side compare维度对比

Key differences with same-lane alternatives

	this skill · 当前lean4 theorem proving	Anthropic Skill Creator	Nuwa Skill	everything-claude-code-conventions
Rating · 评分	—	4.9	4.7	—
Stars · 星标	1.1k	122k	14k	187k
Risk · 风险	Low risk · 低风险	Medium risk · 中风险	Medium risk · 中风险	Medium risk · 中风险
Best for · 最适合	High-star GitHub skill discovery candidate.	New skill creation	Distill how a person thinks into a reusable skill.	Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.
Not for · 不适合	Sensitive or production workflows without local review.	One-off task automation	Workflows that require stronger human review than this catalog entry documents.	Workflows that require stronger human review than this catalog entry documents.

Audit notes审计备注

last reviewed 2026-06-03 · 复查

Source源码open on GitHub · 公开✓

Author作者community · 社区!

Network网络访问read-only · 只读✓

Filesystem文件写入sandboxed · 沙箱✓

Dependencies依赖audited · 已审计✓

Telemetry遥测none · 无✓