New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Mathodology Agent Pipeline

by sweetcornna in sweetcornna/mathodology

A skill your agent uses when planning a modeling solution, selecting the next useful step or briefing a specialist.

MITAuto-check passed

Install Mathodology Agent Pipeline

skills CLI
$ npx skills add sweetcornna/mathodology --skill mathodology-agent-pipeline -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sweetcornna/mathodology mathodology-agent-pipeline --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sweetcornna/mathodology.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/mathodology-agent-pipeline .claude/skills/mathodology-agent-pipeline && rm -rf skills-src

Use ~/.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/

Facts

Skill name
mathodology-agent-pipeline
GitHub stars
305
Token cost
~617 tokens
SKILL.md length
306 words
Files
2
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when planning a modeling solution, selecting the next useful step or briefing a specialist.

  • Planning a modeling solution
  • SKILL.md covers Understand the problem, Formulate a model, Challenge the result and Communicate the answer, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Selecting the next useful step

What it does

Mathodology Agent Pipeline is an agent skill from sweetcornna/mathodology. Use when planning a modeling solution, selecting the next useful step or briefing a specialist.

Its SKILL.md is about 620 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: 专为数学建模竞赛设计的数模 Agent Skills：MCM/ICM 美赛、CUMCM 国赛、华数杯、M3、HiMCM 等，面向 Claude Code 与 Codex 的获奖级建模工作流。Math modeling contest skills for Claude Code & Codex. The licence is MIT.

When your agent uses it

  • Planning a modeling solution
  • Selecting the next useful step
  • Briefing a specialist

Example prompts

  • “/mathodology-agent-pipeline”

What it can do on your machine

Read from SKILL.md and the folder at commit 0cfcd93. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Mathodology Agent Pipeline loads about 617 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 306 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~617

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.

SKILL.md

The full file from sweetcornna/mathodology at commit 0cfcd93, republished under its MIT licence (© sweetcornna). 306 words, ~617 tokens.

Download SKILL.mdSave it as .claude/skills/mathodology-agent-pipeline/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
mathodology-agent-pipeline
description
Use when planning a modeling solution, selecting the next useful step or briefing a specialist.

Mathodology Modeling Prompts

Use the following questions in whatever order the task needs. They are prompts for reasoning, not mandatory stages or files.

Understand the problem

What decision is the reader trying to make? What is given, unknown or required? Which mechanisms must the solution represent? Check the actual contest rules when applicable, including deadline, page limits and AI-use requirements.

Formulate a model

Start with a useful baseline. Define variables, units, assumptions, constraints and the objective. Compare plausible alternatives when there is a real choice; do not invent extra models to meet a quota. Explain why the added complexity changes the answer. Check identifiability, data requirements and limiting cases.

Challenge the result

Which observation could disprove the model? Can a simpler baseline perform as well? Test influential assumptions and plausible adverse scenarios. Separate parameter uncertainty, observation noise and structural uncertainty. Match the paper's claims to the implemented mathematics and the data actually used.

Communicate the answer

Answer the problem's questions with interpretable quantities and limitations. Choose figures from figure presets, including the once-per-task image2 question. Build the explanation around the results, not the history of experiments. Review with review questions.

Focused collaboration

When delegation is useful and available, give a specialist a bounded question, relevant data, current assumptions and a concrete output. Agree file ownership for concurrent editing. Ask for ordinary prose: finding, reasoning, artifact paths and unresolved uncertainty. The lead integrates the answer and resolves conflicting evidence; it does not collect points or gate every intermediate step.

For a fresh task, a compact prompt is:

Solve the supplied modeling problem. State assumptions, build and test a useful baseline, add justified complexity, and connect each recommendation to evidence. Adapt the workflow to the available time. Select purposeful figures using mathodology-figure-presets and ask once about image2 availability. Keep calculations reproducible and explain what could change the conclusion.

© sweetcornna, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .claude/skills/mathodology-agent-pipeline of sweetcornna/mathodology.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 0cfcd93

Compare with similar skills

Mathodology Agent Pipeline 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.

Mathodology Agent Pipeline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mathodology Agent Pipeline this skillsweetcornna/mathodology305—~617Automated safety check: PassMIT
Model Selectionbradygaster/squad3.3k—~2kAutomated safety check: WarnMIT
Model Selectionbradygaster/squad3.3k—~1.3kAutomated safety check: PassMIT
Model Selectionbradygaster/squad3.3k—~563Automated safety check: PassMIT
Model Selectionawslabs/agent-plugins916—~844Automated safety check: PassApache-2.0
Cursor Model Selectionjeremylongshore/tons-of-skills-marketplace2.8k—~2kAutomated safety check: PassMIT

Similar skills

  • Model Selection

    bradygaster/squad

    Per-agent model selection with 4-layer hierarchy and fallback chains

    3.3k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check: warnings

  • Model Selection

    bradygaster/squad

    Determines which LLM model to use for each agent spawn. An agent skill from bradygaster/squad.

    3.3k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Model Selection

    bradygaster/squad

    Resolve explicit and persistent model preferences for Squad spawns without pinning stale defaults

    3.3k GitHub stars~563 tokensUpdated yesterday
    Auto-check passed

  • Model Selection

    awslabs/agent-plugins

    Official

    Selects a base model for the user's use case by querying SageMaker Hub.

    916 GitHub stars~844 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Cursor Model Selection

    jeremylongshore/tons-of-skills-marketplace

    Configure and select AI models in Cursor for Chat, Composer, and Agent mode.

    2.8k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Threat Modeling

    sickn33/agentic-awesome-skills

    Conduct threat modeling using STRIDE methodology. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~4.3k tokens
    SecurityAuto-check passed

More from sweetcornna/mathodology

All 8 skills in this repo

  • Mathodology Figure Presets

    sweetcornna/mathodology

    A skill your agent uses when selecting, designing, generating or reviewing scientific figures, complex modeling charts, paper illustrations or image2-assisted visuals.

    305 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed

  • Mathodology Award Gates

    sweetcornna/mathodology

    A skill your agent uses when reviewing mathematical validity, evidence, reproducibility, figures or a submission draft.

    305 GitHub stars~709 tokensUpdated 1 mo ago
    Auto-check passed

  • Mathodology Whole Project

    sweetcornna/mathodology

    A skill your agent uses when starting a modeling task or installing, backing up or maintaining the skills pack.

    305 GitHub stars~617 tokensUpdated 1 mo ago
    Auto-check passed

  • Mathodology Dev Test Release

    sweetcornna/mathodology

    A skill your agent uses when checking skill metadata, references or repository boundaries, or preparing an explicitly requested skills release.

    305 GitHub stars~603 tokensUpdated 1 mo ago
    Auto-check passed

  • Mathodology Evidence Search

    sweetcornna/mathodology

    A skill your agent uses when finding literature, datasets, domain facts, citation details or licensed figure references.

    305 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Mathodology Project Orientation

    sweetcornna/mathodology

    A skill your agent uses when maintaining the skills-only repository or checking whether a change belongs here.

    305 GitHub stars~390 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Mathodology Agent Pipeline

What does Mathodology Agent Pipeline do?

A skill your agent uses when planning a modeling solution, selecting the next useful step or briefing a specialist. Mathodology Agent Pipeline is an agent skill from sweetcornna/mathodology. Use when planning a modeling solution, selecting the next useful step or briefing a specialist.

When should I use Mathodology Agent Pipeline?

Mathodology Agent Pipeline fits situations like: planning a modeling solution; selecting the next useful step; briefing a specialist.

How do I install Mathodology Agent Pipeline in Claude Code?

Run `npx skills add sweetcornna/mathodology --skill mathodology-agent-pipeline -a claude-code`. Or copy the skill folder (.claude/skills/mathodology-agent-pipeline in sweetcornna/mathodology) into .claude/skills/mathodology-agent-pipeline in your project. Claude Code loads it when a task matches its description.

How do I install Mathodology Agent Pipeline in Codex?

Run `npx skills add sweetcornna/mathodology --skill mathodology-agent-pipeline -a codex`. Or copy the skill folder (.claude/skills/mathodology-agent-pipeline in sweetcornna/mathodology) into .agents/skills/mathodology-agent-pipeline in your project. Codex loads it when a task matches its description.

Can I use Mathodology Agent Pipeline 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 sweetcornna/mathodology --skill mathodology-agent-pipeline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mathodology-agent-pipeline, .gemini/skills/mathodology-agent-pipeline, .github/skills/mathodology-agent-pipeline and .opencode/skills/mathodology-agent-pipeline in your project.

What does Mathodology Agent Pipeline need to run?

SKILL.md names no scripts, command-line tools or credentials: Mathodology Agent Pipeline is instructions for the agent only.

Does Mathodology Agent Pipeline 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 Mathodology Agent Pipeline 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 Mathodology Agent Pipeline use?

Mathodology Agent Pipeline 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 Mathodology Agent Pipeline use?

About 617 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mathodology Agent Pipeline?

Skills that share tags, products or a category with Mathodology Agent Pipeline: Model Selection (bradygaster/squad, 3.3k stars), Model Selection (bradygaster/squad, 3.3k stars), Model Selection (bradygaster/squad, 3.3k stars) and Model Selection (awslabs/agent-plugins, 916 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mathodology Agent Pipeline?

sweetcornna (a GitHub user) maintains it in sweetcornna/mathodology, which has 305 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 7, 2026.

Source: sweetcornna/mathodology on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.