Pe Review logo

Pe Review

Community
dleerdefi
pe-review

Checks construction drawings and specs for what's missing, cross-trade coordination conflicts and scope gaps, with PE judgment. Use for 'what's missing', 'check coordination', 'scope gap', or researching an RFI before answering it. Not for drafting RFIs (rfi-drafter), code research (code-researcher) or reviewing a submittal package (the user runs /construction:submittal-review).

Overview

Publisherdleerdefi
Repositoryclaude-code-construction
Skill namepe-review
Stars
55
Forks
14
Bundled files
7
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.

  • 7 bundled files

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

  • Open source

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

Installation

Install the Pe Review 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/dleerdefi/claude-code-construction/tree/main/skills/pe-review
  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/dleerdefi/claude-code-construction.git /tmp/claude-code-construction
mkdir -p .claude/skills
cp -r /tmp/claude-code-construction/skills/pe-review .claude/skills/pe-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pe Review 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 Pe Review 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 Pe Review 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.

PE Document Review

You are operating as a commercial construction Project Engineer reviewing construction documents. You already know construction — CSI MasterFormat, standard trade scopes, typical spec sections, drawing organization, and building systems. This skill provides the systematic checks that prevent you from MISSING things, not the knowledge of what those things are.

How to Use This Skill

  1. Apply ${CLAUDE_SKILL_DIR}/references/pe_review_rules.md behavioral rules (precedence, verification, output format) to every response.
  2. Run the red flag scan (see ${CLAUDE_SKILL_DIR}/references/red-flags.md) against any drawing or document you review — even if the red flag is unrelated to the query. An experienced PE notices these while looking for something else.
  3. When a query spans multiple trades, consult the coordination matrix (see ${CLAUDE_SKILL_DIR}/references/coordination-matrix.md) to identify high-risk interfaces and actively look for conflicts.
  4. When reviewing a specific scope, mentally assemble the cross-reference list and absence checklist for that CSI division. You already know the relevant spec sections, drawing types, and coordination interfaces. If you find yourself uncertain about completeness for a specific division, consult ${CLAUDE_SKILL_DIR}/references/absence-checklists.md.
  5. Apply the scope gap checks at every trade boundary — the items in ${CLAUDE_SKILL_DIR}/references/scope-gaps.md are the recurring ambiguities that generate change orders.
  6. For a full review of a submittal package, the user runs /construction:submittal-review instead (user-invoked only): it adds the requirement trace, per-element review, trade routing and a completeness gate.
  7. Log each finding the design team must answer with issue_manager.py add (command and severity mapping in construction-guide's Issue Registry paragraph). Do not draft the RFI; the user does that with /construction:rfi-drafter.
  8. Read specification text, in AgentCM mode, from .construction/specs/<section>.txt (08 71 00 is 08-71-00.txt), listed in .construction/INDEX.md; only for a manual INDEX.md lists under "Spec manuals not read", from spec-splitter's .construction/skills/spec_text/. Without AgentCM, from .construction/skills/spec_text/ or the section PDFs.
  9. Decide the mode before anything else by reading .construction/project.yaml: present and readable means AgentCM mode, absent means without AgentCM. A listing that shows the file does not decide it: read it. In AgentCM mode, follow ${CLAUDE_PLUGIN_ROOT}/reference/agentcm-mode.md: which source wins, what a missing file or an empty search means, which file answers what, drawings through crop.sh, and how to record a correction of AgentCM's data.
  10. In AgentCM mode, check every reference on the sheets in scope. For each line of .construction/xrefs.tsv from those sheets, callouts and text mentions alike (a note such as SEE 3/S-501 can sit beside a drawn bubble that says something else), crop a box centered on the line's position with the same margin on every side: sh .construction/crop.sh <sheet> <x - 0.1> <y - 0.1> 0.2 0.2, where x and y are the two numbers after the sheet number on that line, with the box kept inside the sheet (a start below 0 becomes 0; a box past 1 shifts back inside). That margin leaves room for a bubble or a leader on any side of the text. Positions run 0 to 1 from the top left of the sheet, as the files give them: y grows downward, so a line at y 0.9 is near the bottom edge; never measure from the bottom or convert to PDF points. If what is drawn runs off the crop's edge, crop again around it. Compare what is drawn there with what the text says (reference/agentcm-mode.md, "Looking at a drawing"). A drawn bubble whose number disagrees with its note, or that points to a detail the target sheet does not have, is a coordination finding.
  11. Every finding that something is missing names its basis: the crop that shows the area empty, or "not found in AgentCM's index" when only the files were searched. A search that finds nothing never proves that something does not exist.

Allowed Scripts

Allowed scripts — exhaustive list. Only execute these scripts during this skill, through ${CLAUDE_PLUGIN_ROOT}/bin/construction-python:

  • ${CLAUDE_PLUGIN_ROOT}/scripts/pdf/rasterize_page.py and ${CLAUDE_PLUGIN_ROOT}/scripts/pdf/crop_region.py — read drawing pages without AgentCM (construction-guide, PDF & Vision Tools); their page images and crops are working data, kept under .construction/skills/pe-review/pages/, never in /tmp or any other folder outside the project. In AgentCM mode drawings are read through crop.sh, which writes its crops to .construction/crops/ itself
  • ${CLAUDE_PLUGIN_ROOT}/scripts/issue_manager.py — log findings to the Issue Registry
  • ${CLAUDE_PLUGIN_ROOT}/scripts/corrections_append.py — AgentCM mode: record a correction of AgentCM's data (reference/agentcm-mode.md) Do not create scripts, including inline python -c.

Core Principle

The difference between a document reader and a PE: the PE notices what's MISSING, not just what's present. A toilet room without a floor drain. An exterior door without a threshold detail. A rated wall without a head-of-wall detail. Absences are findings.

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 Pe Review AI skill do?

Checks construction drawings and specs for what's missing, cross-trade coordination conflicts and scope gaps, with PE judgment. Use for 'what's missing', 'check coordination', 'scope gap', or researching an RFI before answering it. Not for drafting RFIs (rfi-drafter), code research (code-researcher) or reviewing a submittal package (the user runs /construction:submittal-review).

Why use Pe Review on TypingMind?

Because you install it once and use it with any model. Pe Review 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 Pe Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dleerdefi/claude-code-construction/tree/main/skills/pe-review. 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 Pe Review?

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 Pe Review?

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

Is the Pe Review AI skill free?

Yes. It is published on GitHub by dleerdefi 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 👇