Agent skill

Problem Classifier

by zhnnky329 in zhnnky329/MathModeling-skills

Classify each parsed mathematical-modeling subquestion by required output and structure, surface ambiguous framing trade-offs for human choice, and record primary/secondary task types without…

MITAuto-check passed

Install Problem Classifier

skills CLI

$ npx skills add zhnnky329/MathModeling-skills --skill problem-classifier -a claude-code

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

GitHub CLI

$ gh skill install zhnnky329/MathModeling-skills problem-classifier --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/zhnnky329/MathModeling-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/problem-classifier .claude/skills/problem-classifier && 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/

Paste into Claude Code

Install the "problem-classifier" agent skill from https://github.com/zhnnky329/MathModeling-skills/tree/main/.codex/skills/problem-classifier into .claude/skills/problem-classifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "problem-classifier", 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

$skill-installer install https://github.com/zhnnky329/MathModeling-skills/tree/main/.codex/skills/problem-classifier

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 zhnnky329/MathModeling-skills --skill problem-classifier -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install zhnnky329/MathModeling-skills problem-classifier --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zhnnky329/MathModeling-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/problem-classifier .agents/skills/problem-classifier && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "problem-classifier" agent skill from https://github.com/zhnnky329/MathModeling-skills/tree/main/.codex/skills/problem-classifier into .agents/skills/problem-classifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "problem-classifier", 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 zhnnky329/MathModeling-skills --skill problem-classifier -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install zhnnky329/MathModeling-skills problem-classifier --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zhnnky329/MathModeling-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/problem-classifier .cursor/skills/problem-classifier && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "problem-classifier" agent skill from https://github.com/zhnnky329/MathModeling-skills/tree/main/.codex/skills/problem-classifier into .cursor/skills/problem-classifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "problem-classifier", 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

$ gemini skills install https://github.com/zhnnky329/MathModeling-skills.git --path .codex/skills/problem-classifier

--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 zhnnky329/MathModeling-skills --skill problem-classifier -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install zhnnky329/MathModeling-skills problem-classifier --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zhnnky329/MathModeling-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/problem-classifier .gemini/skills/problem-classifier && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "problem-classifier" agent skill from https://github.com/zhnnky329/MathModeling-skills/tree/main/.codex/skills/problem-classifier into .gemini/skills/problem-classifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "problem-classifier", 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.

GitHub CLI

$ gh skill install zhnnky329/MathModeling-skills problem-classifier

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 zhnnky329/MathModeling-skills --skill problem-classifier -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/zhnnky329/MathModeling-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/problem-classifier .github/skills/problem-classifier && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "problem-classifier" agent skill from https://github.com/zhnnky329/MathModeling-skills/tree/main/.codex/skills/problem-classifier into .github/skills/problem-classifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "problem-classifier", 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 zhnnky329/MathModeling-skills --skill problem-classifier -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install zhnnky329/MathModeling-skills problem-classifier --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zhnnky329/MathModeling-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/problem-classifier .opencode/skills/problem-classifier && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "problem-classifier" agent skill from https://github.com/zhnnky329/MathModeling-skills/tree/main/.codex/skills/problem-classifier into .opencode/skills/problem-classifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "problem-classifier", 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: problem-classifier
GitHub stars: 1.1k
Token cost: ~611 tokens
SKILL.md length: 218 words
Files: 2 (incl. references)
Skills in repo: 29
Repo updated: Sep 24, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Classify each parsed mathematical-modeling subquestion by required output and structure, surface ambiguous framing trade-offs for human choice, and record primary/secondary task types without…

Works in 6 steps: Classify from the required output,… → Assign → Identify mixed or ambiguous framings… → …
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Problem Classifier is an agent skill from zhnnky329/MathModeling-skills. Classify each parsed mathematical-modeling subquestion by required output and structure, surface ambiguous framing trade-offs for human choice, and record primary/secondary task types without selecting algorithms.

Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/task-type-guide.md`).

The repository describes itself as: 面向数学建模竞赛的 Claude Code / Codex Skills ，支持分阶段建模流程与 Python、MATLAB/北太天元代码分支。 The licence is MIT.

Example prompts

“/problem-classifier”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

Classify from the required output, decision structure, constraints, and relationships—not keywords alone.
Assign
Identify mixed or ambiguous framings that would change what the team can claim.
For a load-bearing ambiguity, invoke one choice card explaining consequences. Do not silently settle it.
Save planning/classification/problem_classification.json.
Record the human framing decision in methods/Qx/qx_decisions.jsonl, or in planning/framing_decisions.jsonl when the Qx method directory…

What it can do on your machine

Read from SKILL.md and the folder at commit 0b46e9c. 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 (its code samples are json).
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

Problem Classifier loads about 611 tokens when it runs, and up to ~994 if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 218 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~58
When it runs · the whole SKILL.md, loaded when a task matches: ~611
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~994

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 zhnnky329/MathModeling-skills at commit 0b46e9c, republished under its MIT licence (© zhnnky329). 218 words, ~611 tokens.

Download SKILL.mdSave it as .claude/skills/problem-classifier/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: problem-classifier
description: Classify each parsed mathematical-modeling subquestion by required output and structure, surface ambiguous framing trade-offs for human choice, and record primary/secondary task types without selecting algorithms.

Preconditions

planning/parse/problem_parse.json exists and maps every Qx to an output.
Material framing ambiguities are visible.

Read legacy parse paths only during migration.

Task Types

evaluation/ranking;
prediction/estimation;
optimization/decision;
mechanism/dynamics;
classification/clustering;
graph/routing/network;
simulation/scenario;
descriptive/inference;
mixed.

Detailed cues are in references/task-type-guide.md.

Workflow

Classify from the required output, decision structure, constraints, and relationships—not keywords alone.
Assign:
- primary type;
- optional secondary type;
- confidence;
- evidence from the parse;
- consequences for validation and deliverables.
Identify mixed or ambiguous framings that would change what the team can claim.
For a load-bearing ambiguity, invoke one choice card explaining consequences. Do not silently settle it.
Save planning/classification/problem_classification.json.
Record the human framing decision in methods/Qx/qx_decisions.jsonl, or in planning/framing_decisions.jsonl when the Qx method directory does not yet exist.

Output Contract

json

{
  "schema_version": 1,
  "subquestions": [
    {
      "id": "Q1",
      "primary_type": "evaluation",
      "secondary_type": null,
      "confidence": "high",
      "evidence": [],
      "required_validation": [],
      "framing_decision_id": null,
      "risks": []
    }
  ]
}

Rules

Do not propose or choose methods.
Do not classify only from nouns such as “forecast” or “optimal”; verify the required output.
A subquestion may be mixed, but avoid listing many types without prioritization.
Human framing is required when alternative classifications lead to materially different outputs or claims.
Do not create a long taxonomy report when the JSON record is sufficient.

Verification

Every Qx has one primary type.
Mixed/secondary types are justified.
Classification evidence resolves to the parse.
Ambiguous framing is human-confirmed or remains a blocker.
No algorithm selection leaked into classification.

Reference

references/task-type-guide.md

Files

SKILL.md and 1 other file (references) in .codex/skills/problem-classifier of zhnnky329/MathModeling-skills.

SKILL.md
references/task-type-guide.md

Open the folder on GitHubat commit 0b46e9c

Compare with similar skills

Problem Classifier 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.

Problem Classifier compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Problem Classifier this skillzhnnky329/MathModeling-skills	1.1k	—	~611	Automated safety check: Pass	MIT	13 days ago
OmniRoute Model Catalogdiegosouzapw/OmniRoute	74k	1 repos	~589	Automated safety check: Pass	MIT	today
Math Modeling Problem Analysisjihe520/MathModelAgent	6.2k	—	~494	Automated safety check: Notes	None	5 days ago
Model Bank Metadatalobehub/lobehub	83k	—	~2k	Automated safety check: Pass	Custom licence	today
Harness Threat Modelruvnet/ruflo	74k	—	~363	Automated safety check: Notes	MIT	today
OmniRoute Model Catalog CLIdiegosouzapw/OmniRoute	74k	—	~554	Automated safety check: Pass	MIT	today

Similar skills

OmniRoute Model Catalog
diegosouzapw/OmniRoute
Looks up which AI models an OmniRoute gateway can reach, creates or updates model aliases and tests whether individual models respond.
74k GitHub starsUsed in 1 repo~589 tokens
AI & LLM EngineeringAuto-check passed
Math Modeling Problem Analysis
jihe520/MathModelAgent
Chinese-language stage that turns a math modeling contest problem and its data files into a modeling report with sub-problems, formulas and a task list for coding.
6.2k GitHub stars~494 tokensUpdated 5 days ago
Research & ScienceAuto-check: notes
Model Bank Metadata
lobehub/lobehub
Fills and maintains the knowledgeCutoff, family and generation fields on model cards in LobeHub's model bank, from a single new model up to repo-wide backfills.
83k GitHub stars~2k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Harness Threat Model
ruvnet/ruflo
Enterprise-review-grade threat model from harness threat-model <path.
74k GitHub stars~363 tokensUpdated today
SecurityAuto-check: notes
OmniRoute Model Catalog CLI
diegosouzapw/OmniRoute
Lists and manages AI models from the OmniRoute command line: browse a provider's catalog, search it, and add, edit, remove or test-add models.
74k GitHub stars~554 tokensUpdated today
AI & LLM EngineeringAuto-check passed
Math Modeling Problem Analyzer
yushui2022/MathModel-Skill
Parses a math modeling contest problem from PDF, Word or pasted text and produces a task breakdown, paper outline, scoring map and model route for each question.
452 GitHub starsUsed in 1 repo~1.4k tokens
Research & ScienceAuto-check passed

More from zhnnky329/MathModeling-skills

All 29 skills in this repo

Method Selector
zhnnky329/MathModeling-skills
Build and risk-screen a compact role-based method shortlist for a mathematical-modeling subquestion.
1.1k GitHub stars~1.6k tokensUpdated 13 days ago
Auto-check passed
Data Auditor Cleaner
zhnnky329/MathModeling-skills
Map contest attachments to subquestions, audit and clean raw data, and emit one reusable data profile with quality, coverage, imbalance, concentration, and method-readiness evidence for downstream…
1.1k GitHub stars~1.1k tokensUpdated 13 days ago
Auto-check passed
Decision Prompt Builder
zhnnky329/MathModeling-skills
Build one compact choice card at a genuine mathematical-modeling judgment point.
1.1k GitHub stars~837 tokensUpdated 13 days ago
Auto-check passed
Matlab Model Code Generator
zhnnky329/MathModeling-skills
Generate and run minimal reproducible MATLAB or Beita Tianyuan compatible code for the human-approved main method and usable baseline, with compact experiment artifacts and a canonical run summary.
1.1k GitHub stars~685 tokensUpdated 13 days ago
Auto-check passed
Model Code Analyzer
zhnnky329/MathModeling-skills
Translate a human-approved main method and usable baseline into a minimal language-neutral implementation and experiment contract.
1.1k GitHub stars~881 tokensUpdated 13 days ago
Auto-check passed
Modeler Decision Logger
zhnnky329/MathModeling-skills
Faithfully append a human modeler's choice and rationale to one canonical per-subquestion JSONL decision ledger.
1.1k GitHub stars~783 tokensUpdated 13 days ago
Auto-check passed

Questions about Problem Classifier

What does Problem Classifier do?

Classify each parsed mathematical-modeling subquestion by required output and structure, surface ambiguous framing trade-offs for human choice, and record primary/secondary task types without…. Problem Classifier is an agent skill from zhnnky329/MathModeling-skills. Classify each parsed mathematical-modeling subquestion by required output and structure, surface ambiguous framing trade-offs for human choice, and record primary/secondary task types without selecting algorithms.

How do I install Problem Classifier in Claude Code?

Run `npx skills add zhnnky329/MathModeling-skills --skill problem-classifier -a claude-code`. Or copy the skill folder (.codex/skills/problem-classifier in zhnnky329/MathModeling-skills) into .claude/skills/problem-classifier in your project. Claude Code loads it when a task matches its description.

How do I install Problem Classifier in Codex?

Run `npx skills add zhnnky329/MathModeling-skills --skill problem-classifier -a codex`. Or copy the skill folder (.codex/skills/problem-classifier in zhnnky329/MathModeling-skills) into .agents/skills/problem-classifier in your project. Codex loads it when a task matches its description.

Can I use Problem Classifier 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 zhnnky329/MathModeling-skills --skill problem-classifier -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/problem-classifier, .gemini/skills/problem-classifier, .github/skills/problem-classifier and .opencode/skills/problem-classifier in your project.

What does Problem Classifier need to run?

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

Does Problem Classifier 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 Problem Classifier 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 Problem Classifier use?

Problem Classifier 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 Problem Classifier use?

About 611 tokens (SKILL.md is roughly 2.4k 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 383 tokens, read only when the agent opens those files.

What are the alternatives to Problem Classifier?

Skills that share tags, products or a category with Problem Classifier: OmniRoute Model Catalog (diegosouzapw/OmniRoute, 74k stars), Math Modeling Problem Analysis (jihe520/MathModelAgent, 6.2k stars), Model Bank Metadata (lobehub/lobehub, 83k stars) and Harness Threat Model (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Problem Classifier?

zhnnky329 (a GitHub user) maintains it in zhnnky329/MathModeling-skills, which has 1,059 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on September 24, 2026.

Source: zhnnky329/MathModeling-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Problem Classifier

Facts

At a glance

What it does

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Preconditions

Task Types

Workflow

Output Contract

Rules

Verification

Reference

Files

Compare with similar skills

Similar skills

More from zhnnky329/MathModeling-skills

Questions about Problem Classifier