Create Validation logo

Create Validation

Community
ghbalf
create-validation

Generate a draft VALIDATION.md for a skill by analyzing its SKILL.md construction steps

Overview

Publisherghbalf
Repositoryfreecad-ai
Skill namecreate-validation
Stars
557
Forks
89
Bundled files
Instructions only
LicenseLGPL-2.1
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 ghbalf on GitHub. Read the source before you install it.

Installation

Install the Create Validation 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/ghbalf/freecad-ai/tree/master/skills/create-validation
  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/ghbalf/freecad-ai.git /tmp/freecad-ai
mkdir -p .claude/skills
cp -r /tmp/freecad-ai/skills/create-validation .claude/skills/create-validation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Validation 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 Create Validation 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 Create Validation 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.

Create Validation Rules

Generate a draft VALIDATION.md file for a skill by analyzing its SKILL.md.

WARNING — READ THIS FIRST

This skill generates a DRAFT, not a finished product. The generated VALIDATION.md will likely contain errors, especially in volume formulas. You MUST:

  1. Review every check — does it match what the skill actually builds?
  2. Verify all volume formulas by hand — volume calculations for complex geometry (shells with posts, lips, ridges) are easy to get wrong. Calculate the expected volume for one set of dimensions and compare with the formula.
  3. Test with --validate — run the skill with known-good parameters and --validate to see if the checks pass on correct geometry.
  4. Adjust tolerances — the defaults (0.5mm for bbox, 5% for volume) may be too tight or too loose for your skill.
  5. Check conditional rules — if your skill has variants, verify each when block covers the right checks.

Common errors in generated VALIDATION.md:

  • Volume formulas that forget to add/subtract features (posts, holes, lips, ridges)
  • Wrong body labels (FreeCAD may rename bodies)
  • Missing conditional branches for skill variants
  • Tolerances that are too tight for the geometry complexity

How to use

/create-validation skill-name

Where skill-name is the name of an existing skill (e.g., enclosure, gear).

What to do

  1. Read the specified skill's SKILL.md using execute_code:

    python
    import os
    skills_dirs = [
        os.path.expanduser("~/.config/FreeCAD/FreeCADAI/skills"),
    ]
    # Also check built-in skills
    builtin = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "skills") if '__file__' in dir() else ""

    Or use get_document_state context to find the skill path.

  2. Analyze the SKILL.md to extract:

    • Parameters: from the "Parameters to extract" section. Note types and defaults.
    • Bodies: from create_body instructions. Note their labels.
    • Geometry steps: pad dimensions, pocket depths, post positions, etc.
    • Variants: different lid types, optional features, conditional construction steps.
  3. Generate VALIDATION.md with this structure:

markdown
# Validation Rules

## Parameters
(one line per parameter: name: type = default)

## Checks

### Body count
- total_bodies: N

### BodyLabel
- exists: true
- bbox: X_expr, Y_expr, Z_expr (tolerance 0.5)
- volume: formula (tolerance 5%)
- solid_count: 1
- valid_solid: true

#### when variant_param == "value"
- (variant-specific checks)
  1. Write the file to the skill directory as VALIDATION.md.

  2. IMPORTANT: After writing, display this message to the user:

Draft VALIDATION.md created. This is a starting point, NOT a finished file.

You must verify:

  • All volume formulas — calculate expected values by hand for at least one set of dimensions
  • Body labels match what FreeCAD actually creates (use get_document_state after running the skill)
  • Conditional when blocks cover all variants
  • Tolerances are appropriate (0.5mm bbox, 5% volume are defaults)

Test it: Run /skill-name args --validate to check against actual geometry.

Fix it: Edit the VALIDATION.md directly if checks fail on correct geometry.

Rules for generating volume formulas

  • Rectangular shell (box with hollow interior): L*W*H - (L-2*T)*(W-2*T)*(H-T)
    • This gives 4 walls + floor, open top
  • Cylindrical posts added to interior: + N * pi * R**2 * post_height
    • N = number of posts, R = post radius
  • Cylindrical holes subtracted: - N * pi * R**2 * depth
  • Solid slab (lid): L * W * T
  • Lid with lip: lip volume + slab volume
  • Use pi constant, not 3.14159 (the expression evaluator supports pi)
  • Use ** for power, not ^ (the evaluator uses Python's ast module)

Available check types

CheckValue formatWhen to use
exists: true—Always, for each body
bbox: X, Y, Z (tolerance 0.5)Expressions, absolute mmAlways, for each body
volume: expr (tolerance 5%)Expression, relative %When geometry has calculable volume
solid_count: NIntegerAlways (usually 1 per body)
valid_solid: true—Always, for each body
total_bodies: NIntegerOnce, at document level
has_holes: NIntegerWhen through-all pockets expected
has_feature: "Name"StringWhen specific named features expected
min_children: NIntegerWhen minimum feature count matters

Parameter type reference

TypeDefault syntaxExample
float= 2.5T: float = 2
int= 4count: int = 4
str= valuelid_type: str = screw
bool= falseadd_vents: bool = false

Frequently asked questions

What does the Create Validation AI skill do?

Generate a draft VALIDATION.md for a skill by analyzing its SKILL.md construction steps

Why use Create Validation on TypingMind?

Because you install it once and use it with any model. Create Validation 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 Create Validation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ghbalf/freecad-ai/tree/master/skills/create-validation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Create Validation?

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 Create Validation?

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

Is the Create Validation AI skill free?

Yes. It is published on GitHub by ghbalf under the LGPL-2.1 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 👇