openmath-open-theorem

Queries open formal verification theorems from the OpenMath platform. Use when the user asks for a list of open theorems, wants Lean or Rocq-specific theorems, needs full detail for a theorem ID, or wants to download a theorem and scaffold a local proof workspace.

3,891 stars

Best use case

openmath-open-theorem is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Queries open formal verification theorems from the OpenMath platform. Use when the user asks for a list of open theorems, wants Lean or Rocq-specific theorems, needs full detail for a theorem ID, or wants to download a theorem and scaffold a local proof workspace.

Teams using openmath-open-theorem should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/openmath-open-theorem/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/bennyzhe/openmath-open-theorem/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/openmath-open-theorem/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How openmath-open-theorem Compares

Feature / Agentopenmath-open-theoremStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Queries open formal verification theorems from the OpenMath platform. Use when the user asks for a list of open theorems, wants Lean or Rocq-specific theorems, needs full detail for a theorem ID, or wants to download a theorem and scaffold a local proof workspace.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# OpenMath Open Theorem

## Instructions

Query the OpenMath library to discover and scaffold open theorems. The discovery scripts use `OPENMATH_SITE_URL` and `OPENMATH_API_HOST` when set, and otherwise fall back to the default production endpoints.

### First-run gate

Before discovery on a new machine or workspace, check the shared `openmath-env.json`. Auto-discovery only checks `./.openmath-skills/openmath-env.json` and `~/.openmath-skills/openmath-env.json`.

This gate is mandatory. If `openmath-env.json` is missing, or if it exists but `preferred_language` is missing, stop. Do not query the OpenMath theorem list, theorem detail, or download APIs until setup is complete.

If no config exists, stop and ask the user where to create it, then collect at least:

- `preferred_language`: `lean` or `rocq`
- config visibility / save scope: `./.openmath-skills` or `~/.openmath-skills`
- the submit/authz fields only if the user wants end-to-end submission later

Command:

```bash
python3 scripts/check_openmath_env.py
```

### Workflow checklist

- [ ] **Env**: Run `check_openmath_env.py`. If `openmath-env.json` is missing from `./.openmath-skills` and `~/.openmath-skills`, or `preferred_language` is missing, ask the user to finish setup before continuing.
- [ ] **Explore**: Run `fetch_theorems.py [language]` only after the first-run gate passes. If no language is passed, it uses `preferred_language` from `openmath-env.json` and must not fan out to other languages automatically.
- [ ] **Detail**: Run `fetch_theorem_detail.py <id>` only after the first-run gate passes.
- [ ] **Download**: Run `download_theorem.py <id>` only after the first-run gate passes.
- [ ] **Prove**: Use the `openmath-lean-theorem` skill for environment setup, preflight checks, and proving.
- [ ] **Submit**: Use the `openmath-submit-theorem` skill to hash and submit the proof.
- [ ] **Verify**: Run `fetch_theorem_detail.py <id>` and confirm your address is the prover and status is verified.
- [ ] **Claim**: Use the `openmath-claim-reward` skill to generate the withdrawal command.

### Scripts

| Script | Command | Use when |
|--------|---------|----------|
| Shared env check | `python3 scripts/check_openmath_env.py [--config <path>]` | Mandatory first-run gate; validates shared config, preferred language, and the resolved OpenMath website/API endpoints. |
| List open theorems | `python3 scripts/fetch_theorems.py [--config <path>] [language]` | Listing or filtering open theorems after the first-run gate passes. `language`: optional `lean` or `rocq`. Without an explicit CLI language, query only the configured `preferred_language`. |
| Theorem detail | `python3 scripts/fetch_theorem_detail.py [--config <path>] <id>` | Need description, metadata, and formal definition (source) for a theorem ID; refuses to run until the first-run gate passes. |
| Download & scaffold | `python3 scripts/download_theorem.py [--config <path>] <id> [--output-dir <path>] [--force]` | Creating a local Lean or Rocq proof workspace after the first-run gate passes. |

`openmath_api.py` is the shared API client. `openmath_env_config.py` reads shared user preferences from `openmath-env.json`.

### Notes

- **Endpoints**: Default website is `https://openmath.shentu.org`; default API host is `https://openmath-be.shentu.org`. Runtime overrides: `OPENMATH_SITE_URL`, `OPENMATH_API_HOST`.
- **Language**: User-facing and API language naming is `rocq`.
- **No fallback**: If `preferred_language` is `lean`, query only Lean by default. If no theorems are found, report that result and stop; do not automatically query Rocq, and vice versa.
- **Lean scaffold**: Pins Lean and mathlib4 to `v4.28.0`. Rocq scaffold is `_CoqProject`-based.
- **After download**: Use the `openmath-lean-theorem` skill for Lean environment setup, preflight, external skill installation, and the proving workflow.

## References

Load when needed (one level from this file):

- **[references/init-setup.md](references/init-setup.md)** — Discovery-first setup flow for shared `openmath-env.json`, preferred language, and config visibility.
- **[references/reward_overview.md](references/reward_overview.md)** — How rewards are calculated and how to claim them.

Related Skills

openclaw-youtube

3891
from openclaw/skills

YouTube SERP Scout for agents. Search top-ranking videos, channels, and trends for content research and competitor tracking.

Content & Documentation

openclaw-search

3891
from openclaw/skills

Intelligent search for agents. Multi-source retrieval with confidence scoring - web, academic, and Tavily in one unified API.

Data & Research

openclaw-media-gen

3891
from openclaw/skills

Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key.

Content & Documentation

OpenClaw Mastery — The Complete Agent Engineering & Operations System

3891
from openclaw/skills

> Built by AfrexAI — the team that runs 9+ production agents 24/7 on OpenClaw.

DevOps & Infrastructure

openclaw-safe-change-flow

3891
from openclaw/skills

Safe OpenClaw config change workflow with backup, minimal edits, validation, health checks, and rollback. Single-instance first; secondary instance optional.

DevOps & Infrastructure

jqopenclaw-node-invoker

3891
from openclaw/skills

统一通过 Gateway 的 node.invoke 调用 JQOpenClawNode 能力(file.read、file.write、process.exec、process.manage、system.run、process.which、system.info、system.screenshot、system.notify、system.clipboard、system.input、node.selfUpdate)。当用户需要远程文件读写、文件移动/删除、目录创建/删除、进程管理(列表/搜索/终止)、远程进程执行、命令可执行性探测、系统信息采集、截图采集、系统弹窗、系统剪贴板读写、输入控制(鼠标/键盘)、节点自更新、节点命令可用性排查或修复 node.invoke 参数错误时使用。

DevOps & Infrastructure

openclaw-stock-skill

3891
from openclaw/skills

使用 data.diemeng.chat 提供的接口查询股票日线、分钟线、财务指标等数据,支持 A 股等市场。

Data & Research

openclaw-whatsapp

3891
from openclaw/skills

WhatsApp bridge for OpenClaw — send/receive messages, auto-reply agents, QR pairing, message search, contact sync

Workflow & Productivity

open-webui

3891
from openclaw/skills

Complete Open WebUI API integration for managing LLM models, chat completions, Ollama proxy operations, file uploads, knowledge bases (RAG), image generation, audio processing, and pipelines. Use this skill when interacting with Open WebUI instances via REST API - listing models, chatting with LLMs, uploading files for RAG, managing knowledge collections, or executing Ollama commands through the Open WebUI proxy. Requires OPENWEBUI_URL and OPENWEBUI_TOKEN environment variables or explicit parameters.

AI Platforms & Services

polymarket-openclaw-trader

3891
from openclaw/skills

Reusable Polymarket + OpenClaw trading operations skill for any workspace. Use when the user needs to set up, run, tune, monitor, and deploy an automated Polymarket trading project (paper/live), including env configuration, risk controls, reporting, and dashboard operations.

Trading Automation

openclaw-version-monitor

3891
from openclaw/skills

监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明

Workflow & Productivity

openclaw-essesseff

3891
from openclaw/skills

Interact with the essesseff DevOps platform — call the essesseff Public API (templates, organizations, apps, deployments, images, image lifecycle, environments, retention policies, packages) and automate app creation and Argo CD setup using the essesseff onboarding utility. Use when the user wants to create essesseff apps, manage deployments, promote images through the DEV→QA→STAGING→PROD lifecycle, configure Argo CD environments, manage retention policies, or run the essesseff-onboard.sh script.