Submission Packager logo

Submission Packager

CommunityPopular
zhnnky329
submission-packager

Package a G6-approved mathematical-modeling paper and its exact supporting code, data, results, and figures without changing their behavior or the workspace.

Overview

Publisherzhnnky329
RepositoryMathModeling-skills
Skill namesubmission-packager
Stars
1.1K
Forks
42
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zhnnky329 on GitHub. Read the source before you install it.

Installation

Install the Submission Packager AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zhnnky329/MathModeling-skills/tree/main/.claude/skills/submission-packager
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zhnnky329/MathModeling-skills.git /tmp/MathModeling-skills
mkdir -p .claude/skills
cp -r /tmp/MathModeling-skills/.claude/skills/submission-packager .claude/skills/submission-packager
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Submission Packager in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Submission Packager on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Submission Packager is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Purpose

Create one paper Markdown and one 支撑材料/ directory after the submission audits. Preserve selected code, inputs, and outputs under their workspace-relative paths. The packaged code must retain its module imports, CSV parsing, and normal working-directory paths. A packaging manifest stays outside the package at planning/submission_packaging_manifest.json.

Preconditions

  • planning/session_config.json selects rigor_profile: submission.
  • Every planning/manifests/Qx.json is at G6 and allows final assembly.
  • paper/audits/cross_media_consistency_audit.md, paper/audits/completeness_audit.md, and paper/qa_report.md each contain an explicit Verdict: PASSED line. Ask the relevant auditor to record the verdict when an older report omits it; do not infer passage from file existence.
  • The paper and freezes have not changed after those audits. Renew affected audits when they have.
  • Each Qx has a current frozen_numbers.json. Its source files identify one successful experiment round; that round's run_summary.json lists scripts, inputs, and outputs as workspace-relative paths. Update canonical run evidence through the normal workflow when a field is missing. Never select a round by its number alone.
  • A final paper/main.md exists, or supply another Markdown with --paper.

If the human explicitly authorizes packaging before G6, record their choice and rationale as a DECIDED human packaging_waiver in a decision ledger. Pass its decision_id with --allow-unaudited. The package manifest records this waiver and every failed gate or audit; never label it G6-approved.

Workflow

  1. Run python <skill-dir>/scripts/package_submission.py --workspace <ws> with Python 3.9 or newer. This is a dry run and prints every copied source, its destination, blocked items, and a SHA-256 plan digest. Check the actual contest's submission format and present the full inclusion list to the human.
  2. After the human confirms that exact list, run the same command with --confirm <plan digest>. A changed source or plan blocks packaging. --out selects another output directory. --force replaces only a previous, unchanged package recorded in the external manifest.
  3. The script copies selected source files into a staging directory, preserves their workspace-relative paths, rewrites only the packaged Markdown's image paths, checks Python syntax, then moves the verified stage into place. It rejects output paths containing the workspace or selected sources. The original workspace and the frozen sources stay untouched.
  4. When a safe reproduction command is available, pass --verify-command 'python code/Q1/run_all.py' (repeat per required command). Commands execute from the packaged 支撑材料/ directory after copied frozen outputs are removed, so they must recreate those outputs. Numerical JSON claims with a $.path locator are checked against frozen values using --atol and --rtol. Review command side effects before running. A missing command or unsupported locator is reported as UNVERIFIED, never as a runtime pass. MATLAB execution requires a compatible local runtime and an explicit command.
  5. Review the external manifest, package file hashes, runtime status, and actual Markdown image links. Only describe the package as runnable when the required reproduction checks passed.

Selection and limits

  • Code comes from run_summary.json and its local Python/MATLAB dependencies. Inputs come from the summary and literal data paths in selected code. Outputs come from the summary and frozen sources. Paper images come from references in the delivered Markdown.
  • Preserve filenames and directories. Do not consolidate modules, prune comments, convert CSV files, rename data, or copy exploratory rounds, decision ledgers, audit files, or logs into 支撑材料/.
  • The paper is the only Markdown at the package root. Local paper images are copied beneath 支撑材料/ and their references in the packaged paper are updated. Unresolved image paths block packaging.
  • The manifest records evidence hashes, exact source-to-destination mapping, gate and audit evidence, selected frozen rounds, the confirmation digest, package hashes, and runtime status.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Submission Packager AI skill do?

Package a G6-approved mathematical-modeling paper and its exact supporting code, data, results, and figures without changing their behavior or the workspace.

Why use Submission Packager on TypingMind?

Because you install it once and use it with any model. Submission Packager is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Submission Packager in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhnnky329/MathModeling-skills/tree/main/.claude/skills/submission-packager. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Submission Packager?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Submission Packager?

As many as you like. As long as a model supports skills, you can use Submission Packager with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Submission Packager AI skill free?

Yes. It is published on GitHub by zhnnky329 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇