ez-math-model

Use when solving CUMCM, MCM, ICM, or other mathematical modeling tasks that need contest problem intake, model selection, Python solving, figures, paper…

Skill by woodfishhhh

IndexedMIT★ 43

Write a review

Chalk Labs

Need help deploying ez-math-model?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code. Read the repository before you give any tool access to your data.

npx agentmarket install skill/woodfishhhh-ez-math-model

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Use when solving CUMCM, MCM, ICM, or other mathematical modeling tasks that need contest problem intake, model selection, Python solving, figures, paper writing, quality audit, and packaged deliverables.

Use cases: security, writing, research

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Files it touches

~/.claude/skills/ez-math-model
~/.claude
/home/user/projects/myproject
/Library/TeX/texbin/pdflatex
/opt/homebrew/bin/pdflatex
Your home directory (~)
~/.cursor/User/globalStorage

Tools it pre-approves 7

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

Read,
Write,
Edit,
Bash,
Glob,
Grep,
WebFetch

What's inside

Skill name: ez-math-model
Description: Use when solving CUMCM, MCM, ICM, or other mathematical modeling tasks that need contest problem intake, model selection, Python solving, figures, paper writing, quality audit, and packaged deliverables.
License: MIT
Allowed tools: Read,, Write,, Edit,, Bash,, Glob,, Grep,, WebFetch
Metadata: type: workflow-skill · author: woodfishhhh · version: 1.2.0 · repository: https://github.com/woodfishhhh/EZ_math_model · display_name: EZ Math Model · language_default: zh · marketplace_ready: true · python_min_version: 3.10
Instructions: 227 lines in SKILL.md · view on GitHub

Before installing

Ships executable scripts
Pre-approves some shell commands

Files (178)

.env.example
SKILL.md
CHANGELOG.md · external/paper-orchestra/
CITATION.cff · external/paper-orchestra/
LICENSE · external/paper-orchestra/
README.md · external/paper-orchestra/
requirements.txt · external/paper-orchestra/
setup.sh · external/paper-orchestra/
SKILL.md · external/paper-orchestra/skills/agent-research-aggregator/
extraction-prompt.md · external/paper-orchestra/skills/agent-research-aggregator/references/
log-formats.md · external/paper-orchestra/skills/agent-research-aggregator/references/
synthesis-prompt.md · external/paper-orchestra/skills/agent-research-aggregator/references/
discover_logs.py · external/paper-orchestra/skills/agent-research-aggregator/scripts/
extract_experiments.py · external/paper-orchestra/skills/agent-research-aggregator/scripts/
format_po_inputs.py · external/paper-orchestra/skills/agent-research-aggregator/scripts/
SKILL.md · external/paper-orchestra/skills/content-refinement-agent/
ai-failure-modes.md · external/paper-orchestra/skills/content-refinement-agent/references/
da-reviewer.md · external/paper-orchestra/skills/content-refinement-agent/references/
halt-rules.md · external/paper-orchestra/skills/content-refinement-agent/references/
prompt.md · external/paper-orchestra/skills/content-refinement-agent/references/
reviewer-rubric.md · external/paper-orchestra/skills/content-refinement-agent/references/
safe-revision-rules.md · external/paper-orchestra/skills/content-refinement-agent/references/
writing-quality-check.md · external/paper-orchestra/skills/content-refinement-agent/references/
apply_worklog.py · external/paper-orchestra/skills/content-refinement-agent/scripts/
score_delta.py · external/paper-orchestra/skills/content-refinement-agent/scripts/
score_trajectory.py · external/paper-orchestra/skills/content-refinement-agent/scripts/
snapshot.py · external/paper-orchestra/skills/content-refinement-agent/scripts/
SKILL.md · external/paper-orchestra/skills/literature-review-agent/
citation-density-rule.md · external/paper-orchestra/skills/literature-review-agent/references/
discovery-pipeline.md · external/paper-orchestra/skills/literature-review-agent/references/
exa-search-cookbook.md · external/paper-orchestra/skills/literature-review-agent/references/
prompt.md · external/paper-orchestra/skills/literature-review-agent/references/
s2-api-cookbook.md · external/paper-orchestra/skills/literature-review-agent/references/
verification-rules.md · external/paper-orchestra/skills/literature-review-agent/references/
bibtex_format.py · external/paper-orchestra/skills/literature-review-agent/scripts/
check_cutoff.py · external/paper-orchestra/skills/literature-review-agent/scripts/
citation_coverage.py · external/paper-orchestra/skills/literature-review-agent/scripts/
dedupe_by_id.py · external/paper-orchestra/skills/literature-review-agent/scripts/
exa_search.py · external/paper-orchestra/skills/literature-review-agent/scripts/
levenshtein_match.py · external/paper-orchestra/skills/literature-review-agent/scripts/
pre_dedup_candidates.py · external/paper-orchestra/skills/literature-review-agent/scripts/
s2_cache.py · external/paper-orchestra/skills/literature-review-agent/scripts/
s2_search.py · external/paper-orchestra/skills/literature-review-agent/scripts/
sync_keys.py · external/paper-orchestra/skills/literature-review-agent/scripts/
validate_pool.py · external/paper-orchestra/skills/literature-review-agent/scripts/
SKILL.md · external/paper-orchestra/skills/outline-agent/
allowed-values.md · external/paper-orchestra/skills/outline-agent/references/
example-output.json · external/paper-orchestra/skills/outline-agent/references/
outline-schema.md · external/paper-orchestra/skills/outline-agent/references/
outline_schema.json · external/paper-orchestra/skills/outline-agent/references/
prompt.md · external/paper-orchestra/skills/outline-agent/references/
validate_outline.py · external/paper-orchestra/skills/outline-agent/scripts/
SKILL.md · external/paper-orchestra/skills/paper-autoraters/
citation-f1-prompt.md · external/paper-orchestra/skills/paper-autoraters/references/
litreview-quality-prompt.md · external/paper-orchestra/skills/paper-autoraters/references/
sxs-litreview-prompt.md · external/paper-orchestra/skills/paper-autoraters/references/
sxs-paper-quality-prompt.md · external/paper-orchestra/skills/paper-autoraters/references/
compute_f1.py · external/paper-orchestra/skills/paper-autoraters/scripts/
SKILL.md · external/paper-orchestra/skills/paper-orchestra/
anti-leakage-prompt.md · external/paper-orchestra/skills/paper-orchestra/references/
…and 118 more

SKILL.md (first lines)

# ez-math-model

数学建模一站式 skill。把题目交给我，我会自动走完七个阶段：setup → 题目解析 →
建模方案 → 代码求解 → 论文撰写 → 质量审查 → 标准打包交付。首次使用必须完成 setup
提问；完成后写入 `external/tools/setup_state.json`。未经用户确认，只能使用本次临时默认，
不得写永久配置。

## 一句话主流程

> 收到题目 → 识别项目总文件夹 → 检查 `external/tools/setup_state.json` →
> 创建 `用户输入/runtime/output` 标准目录 → 判定 `formal/demo/blocked` →
> 识别赛事/年份/题号 → 选择模型 → 写脚本并执行 → 出图并过 chart gate →
> 写论文 → 跑对象级质量门 → staging 导出与审查 → 原子同步到 `output/` 并打包
> `output.zip`。

## 触发后的第一动作

先读以下七份文件确认本次运行的契约：

1. `pipeline/00-environment-setup.md` — 验环境（Python、字体、工作目录、上游缓存状态）
2. `references/project-root-protocol.md` — 项目总文件夹与 `用户输入/runtime/output`
3. `references/setup-policy.md` — setup 硬门与临时默认边界
4. `references/run-mode-protocol.md` — `formal/demo/blocked` 判定
5. `references/workdir-protocol.md` — runtime 产物结构与命名
6. `references/chart-quality-gate.md` — 图表有效性门
7. `references/artifact-manifest.md` — 产物 manifest 契约

formal 交付不得只检查“文件是否存在”。质量门必须覆盖图表语义、公式语法、
表格对象、优秀论文格式抽取、正文工程痕迹、DOCX/PDF 对象级导出和 zip/manifest
一致性。

然后立刻执行 setup gate：

- 读取 `external/tools/setup_state.json`。
- 若文件不存在、JSON 无法解析、`setup_completed` 不是 `true`，或用户说"重新配置工具 /
  重置 setup / 重新 setup"，**必须先运行 pipeline 00 的强制提问**，禁止进入
  pipeline 01、建模、写代码或写论文。
- setup 提问完成后，必须写入 `external/tools/setup_state.json`，再继续本次任务。
- 若 `setup_completed: true`，默认跳过交互式 setup，只做本次任务所需的轻量环境检查
  和工作目录创建。

不要用"默认不追问"绕过首次 setup；首次 setup 是硬门禁。若用户要求继续但无法
完成交互式 setup，只能写 `runtime/{task_id}/setup_assumptions.json`，并把
`setup_status` 标为 `temporary_default`，最终质量等级最高为 `provisional_pass`。

## Pipeline 索引

| # | 文件 | 入口条件 | 关键产出 |
|---|---|---|---|
| 00 | `pipeline/00-environment-setup.md` | 用户给出题目或附件；setup gate 未完成时必须先问 | setup 状态明确、`runtime/` 创建完成、env-check 通过 |
| 01 | `pipeline/01-problem-intake.md` | env-check 通过 | `runtime/.../problem.md`、`intake.json`、`attachments/`、`run_state.json` |
| 02 | `pipeline/02-modeling-plan.md` | intake 完成 | `modeling_plan.md`、（首次询问 zhanwen 拉取） |
| 03 | `pipeline/03-coding-solve.md` | modeling_plan 落盘 | `src/*.py`、`results/*`、`figures/*.png` |
| 04 | `pipeline/04-paper-writing.md` | coding 完成 | `paper.md` |
| 05 | `pipeline/05-quality-audit.md` | paper.md 落盘 | `quality_report.json`、`quality_report.md`（含证据与未通过项） |
| 06 | `pipeline/06-packaging-output.md` | 质量门评估完成 | `export_report.json`、`export_audit.json`、`output/paper/*` 四格式、`output/manifest.json`、`output.zip` |

## 角色 prompt 索引

需要在阶段中扮演具体角色时载入：

| 角色 | 文件 | 用途 |
|---|---|---|
| coordinator | `prompts/coordinator.md` | 拆题，识别赛事/年份/题号/小问 |
| modeler | `prompts/modeler.md` | 建模分析，模型选择树 + 物理可行性 |
| coder | `prompts/coder.md` | 写脚本、出图、防数据泄露、参数有据 |
| writer | `prompts/writer.md` | 写论文，段落式、图必引、文献唯一编号 |

## 角色守则索引

执行阶段开始前必读对应角色守则（比 prompt 更关注流程纪律）：

- `references/roles/modeler-guide.md`
- `references/roles/coder-guide.md`
- `references/roles/writer-guide.md`

## 模板索引

- `templates/paper_zh.md` — 中文 CUMCM 论文 markdown 兜底模板
- `templates/paper_en.md` — 英文 MCM/ICM 论文 markdown 兜底模板
- `templates/chapter_outline.toml` — 章节占比与必备小节
- `templates/readme_workdir.md` — 任务工作目录的 README 模板

## 算法库索引

`references/algorithms/README.md` 提供「问题类型 → 推荐算法」速查表；按类别细看：

01 优化 / 02 预测 / 03 评价 / 04 图论 / 05 统计 / 06 综合 / 07 机器学习。

## 优秀论文样例

`references/exemplar-papers/` 下提供 7 篇 CUMCM / MCM 优秀论文的 markdown
摘录（由 MinerU 从 zhanwen/MathModel 转换，前 20 页）。modeler 与 writer
在动笔前应读取与本题最相关的 1-2 篇，抽取格式规则并写
`style_reference_notes.md`，**仅作风格 / 章节 / 表述参考**，禁止照抄或同义改写。
索引详见 `references/exemplar-papers/README.md`。

## 容错与失败处理

`references/fault-tolerance.md` 是单一信息源，定义 4 层容错：
L1 Bounded Retry / L2 Fallback Switch / L3 Evaluator Shadow / L4 Feedback
Rerun。每个 pipeline 阶段都遵守同一套容错协议，绝不死循环。

## Agent 工作模式

`references/agent-mode.md` 单一信息源，定义三种工作模式：

- **single**：所有阶段在主对话顺序推进；上下文压力大但失败定位最容易
- **multi**：每个独立子任务派 subagent 并行；并发强但 token 成本高
- **hybrid（默认）**：关键阶段主对话、琐碎阶段 subagent；兼顾稳定与并发

pipeline 00 首次会强制询问，决策落到 `external/tools/setup_state.json` 与
`external/tools/agent_mode.{single,multi,hybrid}`。

## 继承的辅助 Skills

ezmm 内置 9 个辅助子 skills（在用户机器上检测到才启用）：

| 子 skill | 何时调 |

From woodfishhhh/EZ_math_model, MIT.

Signals

Stars: 43
Forks: 1
Open issues: 0
Last commit (this folder): May 22, 2026 (5 months ago)
Last release: May 22, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version: 1.2.0
License: MIT
Repository: github.com/woodfishhhh/EZ_math_model
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ez-math-model running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying ez-math-model?

Call Get help

Cite this page

ez-math-model skill. Agent Mart. https://agentmart.dev/skills/woodfishhhh-ez-math-model (last updated 2026-10-24)

Need help deploying ez-math-model?

Install

About

Reviews

Permissions

Network hosts it talks to 10

Files it touches

Tools it pre-approves 7

What's inside

Signals

Details

Rather not set it up yourself?

Get ez-math-model running in your business