Pipeline stage that turns a mathematical modeling report into runnable programs per sub-question, frozen numerical results and reviewable evidence files.
Install the "computational-realization" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/computational-realization into .claude/skills/computational-realization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computational-realization", 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.
Type 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.
skills CLI
$ npx skills add WuXinbo-bo/Math-model-skills --skill computational-realization -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "computational-realization" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/computational-realization into .agents/skills/computational-realization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computational-realization", 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.
skills CLI
$ npx skills add WuXinbo-bo/Math-model-skills --skill computational-realization -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "computational-realization" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/computational-realization into .cursor/skills/computational-realization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computational-realization", 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.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add WuXinbo-bo/Math-model-skills --skill computational-realization -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "computational-realization" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/computational-realization into .gemini/skills/computational-realization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computational-realization", 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.
Installs 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).
skills CLI
$ npx skills add WuXinbo-bo/Math-model-skills --skill computational-realization -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "computational-realization" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/computational-realization into .github/skills/computational-realization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computational-realization", 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.
skills CLI
$ npx skills add WuXinbo-bo/Math-model-skills --skill computational-realization -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "computational-realization" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/computational-realization into .opencode/skills/computational-realization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computational-realization", 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.
Facts
Skill name
computational-realization
GitHub stars
111
Token cost
~4.5k tokens
SKILL.md length
899 words
Files
9 (incl. references)
Skills in repo
9
Repo updated
First seen
Licence
MIT
At a glance
Pipeline stage that turns a mathematical modeling report into runnable programs per sub-question, frozen numerical results and reviewable evidence files.
Works in 4 steps: 建模报告.md 里有几问?你是不是真的为每问都写了独立的 .py? → 图表/ 下是不是每问都有相应的 问题_*_结果.json 且文件非空? → 计算结果.md 是不是已经出现, 涵盖每问的方法和数值结果? → …
Implementing every sub-question of a mathematical modeling report as runnable code
SKILL.md covers DATA_PREPARATION 条件子流程, 发布声明与新增机制验证, 稳定执行契约 and ⛔⛔⛔ 工作项规模警示(先读这段, 再读后面全部内容), plus 5 more sections
Calls python
What it does
This protocol belongs to a multi-stage pipeline for mathematical modeling contests and is written in Chinese. Starting from the modeling report, the problem analysis, the topic plan and the contest data, the agent writes an independent program for every sub-question and records real results. Deliverables include the programs with a main script and a code manifest holding source hashes, a 计算结果.md summary, JSON result files under 图表/, a dependency list and run logs.
When data exists, a preprocessing sub-flow validates it, freezes one canonical input and records file hashes and quality statistics. A publication-claims ledger registers each key figure that reaches the paper with its derivation, and the paper may only use numbers from it. Added mechanisms get specific checks, and sensitivity results must not be presented as proof the model is correct. Before ending, the agent runs a shell check that the required output files exist and meet minimum sizes. Ten bundled files hold checks and error-prevention code.
When your agent uses it
Implementing every sub-question of a mathematical modeling report as runnable code
Freezing numerical results and evidence files before writing up a contest paper
Running sensitivity and baseline comparisons for a model with a recorded derivation of each figure
Example prompts
“根据建模报告.md为每一问编写独立程序,并把计算结果写入计算结果.md。”
“Implement all sub-questions from the modeling report and save a results JSON for each one.”
“用户数据里有原始数据,先做预处理并冻结规范输入,再跑模型。”
Requirements
Modeling report, problem analysis and topic plan files from earlier pipeline stages
A Python environment that can run the generated programs
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
1建模报告.md 里有几问?你是不是真的为每问都写了独立的 .py?
2图表/ 下是不是每问都有相应的 问题_*_结果.json 且文件非空?
3计算结果.md 是不是已经出现, 涵盖每问的方法和数值结果?
4跑过完成铁律最后那段 bash 校验脚本了吗?
What it can do on your machine
Read from SKILL.md and the folder at commit ee8a616. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Modeling Competition Computation Stage loads about 4.5k tokens when it runs, and up to ~20k if it reads all its reference files. Until then it costs about 21 tokens; SKILL.md has 899 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~21
When it runs· the whole SKILL.md, loaded when a task matches
~4.5k
With references· SKILL.md plus every file in references/, read only if the agent opens them
~20k
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.
Safety
Auto-check passed
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.
Download SKILL.mdSave it as .claude/skills/computational-realization/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
When no user data is available and you need to produce or simulate data:
Realistic ranges: values needs to match the problem domain — e.g., temperature in °C not arbitrary 0-1, population in millions not random integers
Meaningful patterns: data is expected to show the trends/relationships the model is designed to capture — e.g., if modeling seasonal demand, the data is expected to have seasonal patterns
Visualization-friendly: design data so the resulting visuals look informative and professional:
Avoid extreme outliers that compress the primary data into a tiny range
Confirm different methods/groups have visible but not identical differences (5-20% gaps, not 0.1% or 500%)
Cover enough data points for smooth curves (≥50 for line plots, ≥200 for distributions)
For method comparison: the proposed method is expected to be best but not unrealistically dominant — other methods is expected to have their own strengths on some metrics
Consistent with problem statement: all generated numbers are expected to be traceable to the problem description — if the problem says "30 provinces", produce 30 data points, not 10
Reproducible: set random seeds (np.random.seed(42)) so outcomes are deterministic
Modeling Competition Computation Stage 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.
Modeling Competition Computation Stage compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Modeling Competition Computation Stage this skillWuXinbo-bo/Math-model-skills
A skill your agent uses when drafting the response to an INFORMS Journal on Computing (IJOC) decision letter — turning referee objections (especially about experiments and reproducibility) into a…
A skill your agent uses when building or auditing Journal of Economic Growth (JEG) empirical estimates, calibrated growth models, transition paths, cross-country and subnational panels, historical…
Analyzes Neuropixels recordings from SpikeGLX or Open Ephys through preprocessing, drift correction, Kilosort4 spike sorting, quality metrics and curation.
Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores.
Generates result-evidence contracts, tables and runnable q1 to q3 modeling code scaffolds for a math modeling paper from a model route, a data plan and cleaned data.
Six-phase process for reproducing a published paper's results from provided data, from variable mapping and sample filtering through regression tables and a written report.
Runs a staged pipeline for mathematical modeling research and contest papers, from problem analysis and computation to paper writing, review rounds and submission checks.
Stage protocol for a math-modeling pipeline that turns a problem analysis into a unified mathematical mechanism, formulas, a solution route and a validation plan.
Breaks a math modeling competition problem statement into sub-problems, variables, constraints and evidence needs, and writes the result to a problem analysis file.
Questions about Modeling Competition Computation Stage
What does Modeling Competition Computation Stage do?
Pipeline stage that turns a mathematical modeling report into runnable programs per sub-question, frozen numerical results and reviewable evidence files. This protocol belongs to a multi-stage pipeline for mathematical modeling contests and is written in Chinese. Starting from the modeling report, the problem analysis, the topic plan and the contest data, the agent writes an independent program for every sub-question and records real results.
When should I use Modeling Competition Computation Stage?
Modeling Competition Computation Stage fits situations like: implementing every sub-question of a mathematical modeling report as runnable code; freezing numerical results and evidence files before writing up a contest paper; running sensitivity and baseline comparisons for a model with a recorded derivation of each figure.
How do I install Modeling Competition Computation Stage in Claude Code?
Run `npx skills add WuXinbo-bo/Math-model-skills --skill computational-realization -a claude-code`. Or copy the skill folder (references/stage_protocols/computational-realization in WuXinbo-bo/Math-model-skills) into .claude/skills/computational-realization in your project. Claude Code loads it when a task matches its description.
How do I install Modeling Competition Computation Stage in Codex?
Run `npx skills add WuXinbo-bo/Math-model-skills --skill computational-realization -a codex`. Or copy the skill folder (references/stage_protocols/computational-realization in WuXinbo-bo/Math-model-skills) into .agents/skills/computational-realization in your project. Codex loads it when a task matches its description.
Can I use Modeling Competition Computation Stage in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add WuXinbo-bo/Math-model-skills --skill computational-realization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/computational-realization, .gemini/skills/computational-realization, .github/skills/computational-realization and .opencode/skills/computational-realization in your project.
What does Modeling Competition Computation Stage need to run?
Going by SKILL.md and its folder, Modeling Competition Computation Stage needs the command-line tools its instructions call (python). Our summary lists: Modeling report, problem analysis and topic plan files from earlier pipeline stages; A Python environment that can run the generated programs.
Does Modeling Competition Computation Stage access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Modeling Competition Computation Stage safe to install?
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.
What licence does Modeling Competition Computation Stage use?
Modeling Competition Computation Stage is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Modeling Competition Computation Stage use?
About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 16k tokens, read only when the agent opens those files.
What are the alternatives to Modeling Competition Computation Stage?
Skills that share tags, products or a category with Modeling Competition Computation Stage: Ijoc Rebuttal (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars), Jeg Data Analysis (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars), Neuropixels Data Analysis (davila7/claude-code-templates, 33k stars) and CHARLS Paper Reproduction Guide (xjtulyc/MedgeClaw, 617 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Modeling Competition Computation Stage?
WuXinbo-bo (a GitHub user) maintains it in WuXinbo-bo/Math-model-skills, which has 111 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 21, 2026.
Source: WuXinbo-bo/Math-model-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.