TypingMindTypingMindThe best frontend for AI
Drawing Analyzer logo

Drawing Analyzer

Organization
Cold-IQ
drawing-analyzer

Pre-process and analyze construction drawing PDFs (architectural, structural, MEP, civil) so Claude can answer questions and run quantity takeoffs accurately and cheaply. Use when the user works with construction drawings, building plans, blueprints, drawing sets, tender documents, quantity takeoffs, footing/slab/area counts, or uploads a large multi-sheet construction PDF that Claude struggles to read. Do NOT use for generic image reading or non-construction PDFs.

Overview

PublisherCold-IQ
RepositoryColdIQ-s-GTM-Skills
Skill namedrawing-analyzer
Stars
305
Forks
91
Bundled files
8
Links
Skill sourceRepository
  • 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.

  • 8 bundled files

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

  • Open source

    Published by Cold-IQ on GitHub. Read the source before you install it.

Installation

Install the Drawing Analyzer 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/Cold-IQ/ColdIQ-s-GTM-Skills/tree/main/skills/drawing-analyzer
  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/Cold-IQ/ColdIQ-s-GTM-Skills.git /tmp/ColdIQ-s-GTM-Skills
mkdir -p .claude/skills
cp -r /tmp/ColdIQ-s-GTM-Skills/skills/drawing-analyzer .claude/skills/drawing-analyzer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Drawing Analyzer 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 Drawing Analyzer 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 Drawing Analyzer 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.

Drawing Analyzer

Construction drawings are the worst possible input for an AI. They are large PDFs full of symbols and cross references, where a single-dashed line (cold water) and a double-dashed line (hot water) look almost identical but mean completely different things. Uploading a 10 MB set directly fails, overcounts, and burns 60-70k tokens per question.

This skill fixes that with one principle: scripts do the cheap mechanical work, the model does the understanding. You run the indexing pipeline once per drawing set, which turns a huge PDF into small markdown indexes plus per-sheet text and images. Every later question reads those tiny indexes instead of the full PDF.

Do NOT write pattern-matching scripts to classify drawings (e.g. "if title contains 'electrical' then electrical"). Drawing formats vary too much. Classification, cross-referencing, and symbol reading MUST be done by you reading each sheet. Scripts only split, render, extract text, and extract vectors.

Setup (first time only)

bash
pip install -r "$SKILL_DIR/scripts/requirements.txt"   # PyMuPDF

Mode A — INDEX (run once per drawing set)

Goal: turn merged.pdf into a analysis/ folder of small, queryable artifacts.

Step 1 — Split, render, extract (script).

bash
python3 "$SKILL_DIR/scripts/split_pdf.py" <merged.pdf> <project_dir>/analysis

Produces, per sheet: sheets/sheet_NNN.pdf, images/sheet_NNN.png (rendered at the max resolution Opus can read), text/sheet_NNN.txt, plus manifest.json.

Step 2 — Classify each sheet (YOU, not a script). For each sheet, read text/sheet_NNN.txt first (cheap). Only open images/sheet_NNN.png when the text is insufficient. Write analysis/sheet-classification.md using templates/sheet-classification.md. Use references/drawing-types.md to decide the type (layout / section / detail / schedule / general notes / legend) and the discipline. Capture the sheet number, title, scale, and what data lives on it.

Step 3 — Build the cross-reference matrix (YOU). Find detail callouts, section markers, schedule codes (e.g. TD7, F6), and "see drawing X" notes. Record, per sheet, which other sheets it points to and why. Write analysis/cross-references.md using the template.

Step 4 — Build the symbol legend (YOU). Read the legend/general-notes sheets and any in-sheet keys. Write analysis/symbol-legend.md mapping each symbol/linetype/abbreviation to its meaning. This is what lets you tell a cold-water line from a hot-water line later.

Step 5 — Write the master index (YOU). Write analysis/drawings.md using the template: one-line summary per sheet, the overall package summary, and the query rules. This is the file you ingest at the start of every query.

Mode B — QUERY (every question after indexing)

  1. Read analysis/drawings.md (and cross-references.md / symbol-legend.md only if relevant). Do NOT read the original merged PDF.
  2. From the index, identify the exact sheet(s) that hold the answer.
  3. Read that sheet's text/sheet_NNN.txt, then its images/sheet_NNN.png if needed, then follow cross references to other sheets (e.g. a footing mark on a plan -> its schedule -> its section).
  4. For quantity takeoffs (areas, counts, lengths): follow references/takeoff-methodology.md. Prefer the vector approach: 
    bash
    python3 "$SKILL_DIR/scripts/extract_vectors.py" <project_dir>/analysis/sheets/sheet_NNN.pdf --scale <units_per_point>
    Always run a second, independent sanity check (e.g. overall building dimensions) and compare.
  5. Answer with: the number, a confidence level (high/medium/low) and why, and the source sheets you used. Never give a precise count as certain. State uncertainty explicitly.

What good output looks like

Warehouse slab area ≈ 13,250 m² (confidence: high). Method: polygon extraction from the slab outline on S-201, cross-checked against overall building dimensions on A-101 (13,600 m² gross incl. external slabs). Source sheets: S-201, A-101.

Files

  • scripts/split_pdf.py — split + render + text extract (mechanical)
  • scripts/extract_vectors.py — vector/polygon extraction for takeoffs (mechanical)
  • references/drawing-types.md — how to classify and handle each drawing type
  • references/takeoff-methodology.md — accurate counts/areas with cross-checks
  • templates/ — markdown templates for the three indexes

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 Drawing Analyzer AI skill do?

Pre-process and analyze construction drawing PDFs (architectural, structural, MEP, civil) so Claude can answer questions and run quantity takeoffs accurately and cheaply. Use when the user works with construction drawings, building plans, blueprints, drawing sets, tender documents, quantity takeoffs, footing/slab/area counts, or uploads a large multi-sheet construction PDF that Claude struggles to read. Do NOT use for generic image reading or non-construction PDFs.

Why use Drawing Analyzer on TypingMind?

Because you install it once and use it with any model. Drawing Analyzer 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 Drawing Analyzer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Cold-IQ/ColdIQ-s-GTM-Skills/tree/main/skills/drawing-analyzer. 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 Drawing Analyzer?

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 Drawing Analyzer?

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

Is the Drawing Analyzer AI skill free?

It is published on GitHub by Cold-IQ. Check the repository for licensing terms. 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.

Related AI Skills

View all
openclaw logo

Feishu Doc

openclaw
OrganizationPopular

Feishu document read/write workflows. Activate when the user mentions Feishu docs, cloud docs, or docx links.

82.2K
391K
1 files
View
openclaw logo

Feishu Drive

openclaw
OrganizationPopular

Feishu cloud-storage and comment workflows. Activate when the user mentions cloud space, folders, Drive files, or document comments.

82.2K
391K
Instructions
View
openclaw logo

Feishu Wiki

openclaw
OrganizationPopular

Feishu knowledge-base navigation workflows. Activate when the user mentions a knowledge base, wiki, or wiki link.

82.2K
391K
Instructions
View
openclaw logo

Wacli

openclaw
OrganizationPopular

Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.

82.2K
391K
Instructions
View

Set up your own AI workspace now

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