Solution Package Builder logo

Solution Package Builder

CommunityPopular
zhnnky329
solution-package-builder

Assemble a submission-ready writer package from final method, result, robustness, figure, and human-decision artifacts, then freeze approved numerical claims with provenance.

Overview

Publisherzhnnky329
RepositoryMathModeling-skills
Skill namesolution-package-builder
Stars
1.1K
Forks
42
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Solution Package Builder 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/solution-package-builder
  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/solution-package-builder .claude/skills/solution-package-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Solution Package Builder 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 Solution Package Builder 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 Solution Package Builder 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 the writer's single source package and immutable numerical snapshot. Do not manufacture missing judgments or freeze unapproved claims.

Preconditions

  • rigor_profile is submission.
  • Final method explanation, final result analysis, robustness report, and figure plan exist.
  • Human method, result, stability, and claim-scope decisions exist in qx_decisions.jsonl.
  • Canonical sources are current.

Workflow

  1. Collect final method structure, result claims, limitations, figures, tables, and decision provenance.
  2. Draft results/Qx/reports/qx_solution_package_for_writer.md.
  3. Flag every proposed top-line claim with:
    • value and unit;
    • canonical source path and location;
    • robustness support;
    • decision ID for claim scope or rationale;
    • confidence/limitation.
  4. Invoke one final choice card when package sign-off is missing:
    • keep;
    • downgrade;
    • drop.
  5. Route the human answer to modeler-decision-logger as package_signoff.
  6. Only after sign-off, generate results/Qx/reports/frozen_numbers.json.
  7. Verify every numerical package claim resolves to the freeze and every judgment claim resolves to a human decision ID.

Frozen Number Contract

Each entry contains:

json
{
  "claim_id": "q1_main_rmse",
  "value": 2.4,
  "unit": "units",
  "source_file": "results/Q1/experiments/final/metrics/main.json",
  "source_locator": "$.rmse",
  "frozen_at": "ISO-8601",
  "frozen_by_skill": "solution-package-builder",
  "decision_id": "q1_package_signoff"
}

Use a source line only for stable text files; use a JSON path, table key, or row/column identifier for structured data.

Rules

  • Do not create solution-package-builder_modeler_decision.md.
  • Do not emit frozen_numbers.json before human package sign-off.
  • Never edit an existing freeze by hand.
  • Transcribe human rationales; do not re-compose them as stronger claims.
  • The package may cite the compact method-card history but must not depend on a separate iteration log.
  • Do not copy raw exploratory outputs into the package without final validation.

Change and Re-freeze

When a canonical source changes after freeze:

  1. append the reason to freeze_change_log.md;
  2. update and rerun the canonical source;
  3. obtain renewed human judgment when the evidence changed materially;
  4. regenerate the freeze;
  5. run scoped consistency for Qx.

Verification

  • All prerequisites are final and current.
  • Package sign-off exists in the JSONL ledger.
  • Every frozen value has a real canonical source and stable locator.
  • Every package number matches the freeze.
  • Every modeling judgment traces to a human decision.
  • Writer can use the package without searching scattered results.

Frequently asked questions

What does the Solution Package Builder AI skill do?

Assemble a submission-ready writer package from final method, result, robustness, figure, and human-decision artifacts, then freeze approved numerical claims with provenance.

Why use Solution Package Builder on TypingMind?

Because you install it once and use it with any model. Solution Package Builder 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 Solution Package Builder in TypingMind?

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

Which AI models can use Solution Package Builder?

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 Solution Package Builder?

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

Is the Solution Package Builder 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 👇