Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Vibe Mathing Router

ASecurity

数学研究任务路由器。用户提出找问题、查文献、推公式、做计算、写证明或形式化验证,但当前瓶颈尚未明确时使用;每次只选择一个主 skill。

16,300 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythongo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add tradecatlabs/vibe-coding-cn --skill vibe-mathing-router --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Vibe Mathing Router?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Vibe Mathing Router
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tradecatlabs-vibe-mathing-router/badge)](https://www.skillsdirectory.com/skills/tradecatlabs-vibe-mathing-router)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: vibe-mathing-router
description: "数学研究任务路由器。用户提出找问题、查文献、推公式、做计算、写证明或形式化验证,但当前瓶颈尚未明确时使用;每次只选择一个主 skill。"
---

# Vibe Mathing Router

识别当前数学研究瓶颈,只把任务交给一个 owner;不把整条研究链同时启动。

## Position in the Method Map

路由器先问“规格和语义是否已经冻结”,再区分演绎证明、模型检查、抽象解释、SAT/SMT/符号推理(含符号执行)或精化/综合的验证范式。Lean 是依赖类型理论型演绎验证的主战场,不是整张形式化方法地图。完整的上位/二级地图见 [`FORMAL-METHODS-MAP.md`](../../../governance/standards/FORMAL-METHODS-MAP.md)。顶层编排语言见 [`RESEARCH-LIFECYCLE-MODEL-v0.1.md`](../../../governance/standards/RESEARCH-LIFECYCLE-MODEL-v0.1.md):路由器为 Step 选择 owner,不能把一次 Job 成功解释为数学结果。

## When to Use This Skill

- 用户提出开放式数学问题,但尚未说明需要检索、推导、计算还是证明。
- 输入混合了论文、公式、猜想和代码,需要先决定当前最短验证路径。
- 用户问“下一步该做什么”或“该用哪个数学 skill”。

## Not For / Boundaries

- 已明确要求符号计算、证明或 Lean 验证时,直接使用对应 owner。
- 不生成数学结论,不替代领域知识或机械验证。
- 不因输出文件类型选择路线;按当前阻塞选择。

## Quick Reference

```text
缺少问题边界/前人工作 -> math-discovery
公式对象、假设或近似不清 -> math-derivation
需要精确计算、数值实验、反例搜索 -> math-computation
需要定理证明、补步骤、攻击证明 -> math-proof
需要 Lean/内核级验证 -> math-formalization
```

路由输出必须包含:当前阶段、主 skill、选择理由、必需输入、停止条件、唯一下一步。

## Examples

### Example 1:开放问题
- 输入:“研究一下这个数列。”
- 动作:选择 `math-discovery`,先固定数列、已知项和检索边界。
- 验收:没有直接声称新定理,只给出可检索问题。

### Example 2:明确恒等式
- 输入:“检查这个积分恒等式。”
- 动作:选择 `math-computation`。
- 验收:产出可重跑计算和适用条件,不标记为一般性证明。

### Example 3:形式化请求
- 输入:“把这个证明写成 Lean。”
- 动作:选择 `math-formalization` 并先运行工具预检。
- 验收:Lean 缺失时状态为 blocked/calibration,不伪造 kernel-check。

## References

- `references/source-map.md`:项目 owner 映射来源。
- `references/pressure-tests.md`:路由误触发压力场景。

## Maintenance

- Sources:本项目 owner mapping 与供应链审计结果。
- Last updated:2026-09-07。
- Verification:`python3 scripts/validate_project.py`。

Attribution

tradecatlabstradecatlabs
View sourceMore from tradecatlabs →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →