mcpField
M
mathodology-whole-project

mathodology-whole-project

github.com/sweetcornnaData & databases316249 installsUpdated today
Repository

About mathodology-whole-project

A skills pack for modeling and research tasks that helps turn problems into justified models, reproducible results, and clear scientific communication. It provides prompts and supporting materials, not an application or execution engine.

Key features

  1. 01Guides starting and resuming modeling tasks
  2. 02Tracks key assumptions and decisions
  3. 03Keeps numerical results traceable
  4. 04Provides figure presets and evidence search
  5. 05Supports skill backup and installation

Use cases

  1. 01Turn a research question into a justified model
  2. 02Continue modeling from existing evidence
  3. 03Prepare figures and supporting evidence
  4. 04Back up or update a skills installation

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sweetcornna/mathodology --skill mathodology-whole-project

After installing, type/mathodology-whole-projectin Claude Code to confirm it loaded.

Bundled filesagents/openai.yamlscripts/create-source-backup.sh

Details

From the project README

Mathodology Modeling Companion

Mathodology helps turn a problem into a justified model, reproducible results and clear scientific communication. It is a skills pack, not an application or an execution engine. Use modeling prompts as a flexible guide. For figures use figure presets, including its image2 availability question. For evidence use evidence search.

Start or resume a modeling task

Read the problem, available data, existing results and applicable contest rules. Ask about missing constraints that would change the answer. Reuse established preferences and continue from the current evidence. Keep a short note of important assumptions and decisions if it helps continuity; no special schema is needed.

Work in the user's chosen directory or an ignored work/ directory in this checkout. Produce only artifacts needed for the requested deliverable. Keep numerical results traceable. Use specialists where they help and the host allows it; an independent review can challenge important claims without fixed panels.

Maintain and distribute

The maintained source is .claude/skills/. Claude Code roles and workflow prompts are adjacent. Codex may use an installed .agents/skills/ mirror. Back up this project's mirror before updating its Mathodology entries. Do not modify unrelated skills, project instructions, custom MCP settings or global configuration.

For installation in other projects, use the standard skills CLI; for a clean repository checkout, use git pull --ff-only. Resolve local edits before updating; do not reset them. Installation details are in the repository's docs/INSTALL.md. A skills-only global install does not install project roles or MCP settings.

The optional backup utility saves skills, references and repository docs, including local uncommitted source changes:

bash .claude/skills/mathodology-whole-project/scripts/create-source-backup.sh

It excludes the ignored Codex mirror, contest outputs and Git history. Back those up separately when needed. Extract a backup into an empty directory and verify its checksum before replacing an installation. No application build is required.

Comments

Markdown supported