The opencode binding of the AutoMCM-Pro math modeling pipeline for CUMCM and MCM/ICM contests, with tool mappings, install prompts and checkpointed runs.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/auto-mcm .claude/skills/auto-mcm && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.opencode/skills/auto-mcm into .claude/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.opencode/skills/auto-mcmType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/auto-mcm .agents/skills/auto-mcm && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.opencode/skills/auto-mcm into .agents/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/auto-mcm .cursor/skills/auto-mcm && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.opencode/skills/auto-mcm into .cursor/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/RealSeaberry/AutoMCM-Pro.git --path .opencode/skills/auto-mcm--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/auto-mcm .gemini/skills/auto-mcm && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.opencode/skills/auto-mcm into .gemini/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcmInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/auto-mcm .github/skills/auto-mcm && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.opencode/skills/auto-mcm into .github/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/auto-mcm .opencode/skills/auto-mcm && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.opencode/skills/auto-mcm into .opencode/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
auto-mcmThe opencode binding of the AutoMCM-Pro math modeling pipeline for CUMCM and MCM/ICM contests, with tool mappings, install prompts and checkpointed runs.
This is the opencode runtime binding of the AutoMCM-Pro protocol, not a separate protocol. Behavior is defined by AutoMCM_SOP.md at the repository root, with sibling bindings for Claude Code, Codex and the DeepSeek Harness. A table maps Claude Code tool names to opencode ids such as task, question, bash and read, and says all 12 were tested on real tasks. The SKILL.md is written in Chinese.
On first trigger in a session it asks, through the question tool, whether to install the core Python modeling dependencies and the optional Lean 4 gate, and never installs silently. Interactive steps, including manual-mode stage confirmations and the mandatory human review at a checkpoint, need the opencode TUI or web mode, since question is denied by default in opencode run. The pipeline covers stages, five checkpoints, a quality gate, plot styling, an Andon emergency stop and a launch check.
Read from SKILL.md and the folder at commit 90c4727. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
opencodepythonbashFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
AutoMCM-Pro for opencode loads about 1.2k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 274 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from RealSeaberry/AutoMCM-Pro at commit 90c4727, republished under its MIT licence (© RealSeaberry). 274 words, ~1,169 tokens.
.claude/skills/auto-mcm/SKILL.md (or your agent's skills folder).这是 AutoMCM-Pro 协议在 opencode（sst/opencode，
MIT 授权）上的运行时绑定（Binding），不是另一套独立协议。 行为规范权威来源仍是
仓库根目录的 AutoMCM_SOP.md（工具无关，原样复用）；可选探索层见
LOS_ALAMOS_DESIGN.md。Claude Code 绑定是 .claude/skills/auto-mcm/SKILL.md，
DeepSeek Harness 绑定是 .dsh/skills/auto-mcm/SKILL.md，Codex 绑定是
.agents/skills/auto-mcm/SKILL.md——几份文件描述同一套流程，只是把"怎么调用
工具"换成各自 runtime 的实际工具名。完整背景见
OPENCODE_INTEGRATION.md。
| Claude Code | opencode 工具 |
|---|---|
Agent(description, prompt) | task |
AskUserQuestion | question |
Bash | bash |
Read | read |
Write | write |
Edit | edit |
Glob | glob |
Grep | grep |
WebSearch | websearch |
WebFetch | webfetch |
TodoWrite | todowrite |
| （载入其他 skill） | skill |
以上 12 个工具 id 全部用真实任务实测过（不是文档推断），详见
OPENCODE_INTEGRATION.md §3。
每个新的 OpenCode 会话首次触发本 Skill 时，先用 question 分别询问是否安装核心
Python 建模依赖，以及是否准备可选的 LeanGate / Lean 4。不预扫描、不静默安装；
用户同意后才调用 bash install.sh --with-python-deps 和/或 --with-lean，拒绝后
同一会话不重复询问。opencode run 无法等待回答时，显示问题并暂停，不得自行选择。
⚠ 关键限制：question 在 opencode run（单次任务/headless）模式下默认权限
是 deny——模型会尝试提问，但工具调用被权限系统挡下，退化成打印文字、没人能
回答。【唤醒协议】Step 2a、MANUAL 模式的逐阶段确认、Checkpoint LA 的强制人类
终审，这几个环节都依赖 question 真正等到回复，必须用交互式的 opencode
（TUI）或 opencode web 跑，不能用 opencode run。 工作区初始化完成后，如果
某一段流程确定不会触发任何需要人类介入的分支，才可以考虑用 opencode run 做
单次调用。
task（子代理委派）实测发现：委派子代理访问项目工作区之外的绝对路径会触发
工作区边界限制、卡在 running 状态问不到答案；委派子代理操作工作目录内的相对
路径则正常。Los Alamos 路径 C 用 task 派发 Division/红队/评审子代理时，
prompt 里给的路径应该是当前工作区内的相对路径，不要用跨目录的绝对路径。
opencode # 交互式 TUI
opencode run "task" # 单次任务模式Skill 发现路径是 .opencode/skills/<name>/SKILL.md（opencode 自己的仓库
sst/opencode 就用这个路径放它自己的内部 skill，.opencode/skills/auto-mcm/
是同一套约定）。opencode 额外还有 .opencode/agent/*.md（子代理人格定义，
frontmatter 支持 mode/tools 白名单/黑名单）和 .opencode/command/*.md
（slash command，支持 !`shell命令` 内联执行）两种配置文件类型，本次绑定
用不到，仅供后续想做更深度定制时参考。
阶段定义、状态机、Checkpoint 编号（①~⑤）、质量门控（quality_gate.py）、
Los Alamos 探索层（路径 C）、图表风格规范（plot_style.py）、Andon 紧急停止
（pipeline_manager.py andon-pull/andon-clear/andon-status）、Go/No-Go 发射前检查
（quality_gate.py launch-check，final_compile 前强制）、Skunk Works 轻量模式
（pipeline_manager.py init --skunk-works）、Track2 的 RAND Delphi 多轮收敛
（adjudicate.py delphi-summary）、Kaizen 质量打磨循环
（pipeline_manager.py kaizen-assess/kaizen-round-start/kaizen-status）、工作日志
（worklog.py append/tail，单文件简体中文完整记录，唤醒协议 Step 0）、文献引用
真实性核验+共享池（cite_check.py register/verify/list/export-bibitems）、写作
风格打磨（style_check.py scan，latex_draft 固有规范非可选 addon）、官方格式
合规（quality_gate.py anon-check、ai_usage_doc.py generate/cite-format/ mcm-entry、compile_pdf.py 编译后页数提醒，AutoMCM_SOP.md §17）、画图前先查
领域惯例（AutoMCM_SOP.md §18）全部内容
与 Claude Code 版本一致，见
.claude/skills/auto-mcm/SKILL.md 对应小节（标题相同），
按上方【工具映射表】逐一替换调用方式即可——由于工具名高度对应，这份绑定的
替换规则比 dsh/Codex 都更直接：几乎是把 Agent( 换成 task(、
AskUserQuestion 换成 question，其余照搬。
scripts/*.py 系列命令（pipeline_manager.py/quality_gate.py/
los_alamos/*.py/plot_style.py）完全不变，全部通过 bash 调用。
AutoMCM_SOP.md 的 S1~S5 原样适用。
LeanGate 默认关闭；共享规范见 AutoMCM_SOP.md §19。OpenCode 用 bash 调用同一实现：
python scripts/leangate.py doctor
python scripts/leangate.py --workspace CUMCM_Workspace init --policy selected
python scripts/leangate.py --workspace CUMCM_Workspace status --problem-n 1
python scripts/leangate.py --workspace CUMCM_Workspace verify --problem-n 1
python scripts/quality_gate.py formal --problem-n 1LeanGate 启用后，离开 problem_analysis 前必须逐问题登记适用性并执行
leangate.py seal-assessment；安全边界、整数可行性、守恒、不变量、递推、收敛、
求解器证书或决策关键结论必须用 --risk-category 标注，自动成为 mandatory。
不得直接编辑权威状态或用 reviewer 意见升级 FORMALLY_PROVED。输入变化后必须重新审查、
冻结和验证；Lean FAIL、UNKNOWN、STALE 或 Python FAIL 都是 NO-GO。
LeanGate 启用后的 model_N_verify 推进必须传入工作区内真实验证脚本：
pipeline_manager.py advance model_N_verify --verify-script CUMCM_Workspace/src/verifications/verify_*.py。
required claim 还必须使用人类文件中的 [APPROVED LeanGate ...] 与 [REQUIRED LeanGate ...] 标记。
© RealSeaberry, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .opencode/skills/auto-mcm of RealSeaberry/AutoMCM-Pro.
Open the folder on GitHubat commit 90c4727
AutoMCM-Pro for opencode next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| AutoMCM-Pro for opencode this skillRealSeaberry/AutoMCM-Pro | 257 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Nucleus Delivery Evidence Finalizerprotect-my-hair/nucleus-marketplace | 164 | — | ~454 | Automated safety check: Pass | MIT | |
| Light Research OrchestratorLight0305/Light-skills | 640 | — | ~3.8k | Automated safety check: Pass | MIT | |
| Research Writing AssistantNorman-bury/research-writing-skill | 3.4k | — | ~1.3k | Automated safety check: Notes | MIT | |
| Aer Statspaibrycewang-stanford/Auto-Empirical-Research-Skills | 4.6k | — | ~3k | Automated safety check: Pass | Custom licence | |
| Arxiv MCP Serverblazickjp/arxiv-mcp-server | 3.2k | — | ~353 | Automated safety check: Pass | Apache-2.0 |
protect-my-hair/nucleus-marketplace
Combines the evidence from completed Nucleus workflow steps into a final evidence report and result package, without scheduling steps, updating trackers or opening pull requests.
Light0305/Light-skills
Coordinates and recovers multi-stage Light research projects from a single passport file, with checkpoints, stale-work tracking and rerouting only when you approve.
Norman-bury/research-writing-skill
A skill your agent uses when writing academic papers, theses, or research articles - supports brainstorming, chapter writing, literature review, and LaTeX output
brycewang-stanford/Auto-Empirical-Research-Skills
A skill your agent uses when aer-identification has fixed the design, after methodology choice and before aer-robustness or aer-tables-figures, to run an AER-track analysis with StatsPAI — the…
blazickjp/arxiv-mcp-server
A skill your agent uses when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or…
congcongwang0122/zotero-skill
Use Zotero Desktop to enable/probe the local API, search a local Zotero library, list items/collections/tags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full…
RealSeaberry/AutoMCM-Pro
Runs a math modeling contest pipeline for CUMCM and MCM/ICM entries in Codex CLI, with git checkpoints, verified solver code and human review at each stage.
RealSeaberry/AutoMCM-Pro
Runs a staged workflow for math modeling contests such as CUMCM and MCM/ICM, with checkpoints, verified solver code and a LaTeX paper, on DeepSeek Harness.
RealSeaberry/AutoMCM-Pro
Drives an end-to-end workflow for the CUMCM math modeling contest: reads the problem and data, researches, codes and verifies models, then writes a LaTeX paper and PDF.
RealSeaberry/AutoMCM-Pro
Generates diagrams, flowcharts and conceptual illustrations with OpenAI's gpt-image models, while leaving data plots and result figures to real plotting code.
RealSeaberry/AutoMCM-Pro
Runs an MCM/ICM math modeling competition end to end: collects contest metadata, builds and verifies models and code, then generates an English LaTeX paper and any required memo.
RealSeaberry/AutoMCM-Pro
Runs a math modeling competition entry end to end, in AI-led or human-led mode, with Git checkpoints and self-verified solver code before it enters the LaTeX paper.
Categories
The opencode binding of the AutoMCM-Pro math modeling pipeline for CUMCM and MCM/ICM contests, with tool mappings, install prompts and checkpointed runs. This is the opencode runtime binding of the AutoMCM-Pro protocol, not a separate protocol.md at the repository root, with sibling bindings for Claude Code, Codex and the DeepSeek Harness.
AutoMCM-Pro for opencode fits situations like: running the AutoMCM-Pro math modeling workflow inside opencode; entering a CUMCM or MCM/ICM modeling contest with an AI-led pipeline; choosing between AI-led and human-spec-led modes for a modeling paper.
Run `npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a claude-code`. Or copy the skill folder (.opencode/skills/auto-mcm in RealSeaberry/AutoMCM-Pro) into .claude/skills/auto-mcm in your project. Claude Code loads it when a task matches its description.
Run `npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a codex`. Or copy the skill folder (.opencode/skills/auto-mcm in RealSeaberry/AutoMCM-Pro) into .agents/skills/auto-mcm in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-mcm, .gemini/skills/auto-mcm, .github/skills/auto-mcm and .opencode/skills/auto-mcm in your project.
Going by SKILL.md and its folder, AutoMCM-Pro for opencode needs the command-line tools its instructions call (opencode, python and bash). Our summary lists: opencode, the sst/opencode CLI, in interactive or web mode; Python modeling dependencies, installed with `install.sh --with-python-deps`; Optional Lean 4, installed with `--with-lean`.
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
AutoMCM-Pro for opencode is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with AutoMCM-Pro for opencode: Nucleus Delivery Evidence Finalizer (protect-my-hair/nucleus-marketplace, 164 stars), Light Research Orchestrator (Light0305/Light-skills, 640 stars), Research Writing Assistant (Norman-bury/research-writing-skill, 3.4k stars) and Aer Statspai (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
RealSeaberry (a GitHub user) maintains it in RealSeaberry/AutoMCM-Pro, which has 257 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 10, 2026.
Source: RealSeaberry/AutoMCM-Pro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
