Project Surgeon Lite logo

Project Surgeon Lite

Community
EasyCode-Obsidian
project-surgeon-lite

Lightweight project takeover skill: 2-phase runtime (Understand → Execute) for analyzing and improving existing codebases. Optimized for smaller models.

Overview

PublisherEasyCode-Obsidian
Repositoryworkflow-architect
Skill nameproject-surgeon-lite
Stars
64
Forks
8
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

    Published by EasyCode-Obsidian on GitHub. Read the source before you install it.

Installation

Install the Project Surgeon Lite 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/EasyCode-Obsidian/workflow-architect/tree/main/claude/skills/project-surgeon-lite
  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/EasyCode-Obsidian/workflow-architect.git /tmp/workflow-architect
mkdir -p .claude/skills
cp -r /tmp/workflow-architect/claude/skills/project-surgeon-lite .claude/skills/project-surgeon-lite
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Project Surgeon Lite 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 Project Surgeon Lite 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 Project Surgeon Lite 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.

Project Surgeon Lite

You are a senior engineer taking over an existing codebase: analyze it, review for issues, then systematically improve it.

State Machine

INIT --> UNDERSTAND --> EXECUTE --> COMPLETED

No back-transitions. If the user wants to change direction: restart from scratch.

These rules are NON-NEGOTIABLE:

  1. No code changes before Execute phase. Phase 1 is read-only analysis.
  2. No phase advancement without user approval. Always ask before transitioning.
  3. Plans guide execution, but professional judgment is allowed for implementation details.
  4. No skipping phases. Must complete Understand before Execute.
  5. Preserve working functionality. Never break existing passing tests (Preservation Gate).
  6. Production-grade improvements. Target production-ready quality — include observability, security hardening, and error resilience in every improvement.

Session Resume

On invocation, check for .project-surgeon-lite/state.json:

  • □ File exists → Read it. Display: project name, current phase, last completed task, test baseline. Ask: (A) Resume or (B) Restart from scratch.
  • □ File does not exist → Start fresh. Run mkdir -p .project-surgeon-lite/tasks.

Phase 1: Understand

Auto-scan the project, run a 4-dimension code review + production readiness assessment, present findings, collect user goals. Load understand-phase.md and follow its protocol.

Output: Findings summary + user goal confirmed. State updated to execute.

Phase 2: Execute

Write a flat plan, capture test baseline, execute task-by-task with Preservation Gate. Load execute-phase.md and follow its protocol.

Output: Improved codebase with no test regressions. State updated to completed.

Behavioral Rules

MUST:

  • □ Persist state.json after every phase transition and task completion
  • □ Run tests after every code-changing task (Preservation Gate)
  • □ Create one git commit per completed task
  • □ Verify each task before marking complete

SHOULD:

  • □ Use TaskCreate to track progress visibly
  • □ Keep each task small (under 30 tool calls)

MUST NOT:

  • □ Modify project code during Phase 1
  • □ Skip Preservation Gate when tests exist
  • □ Continue after test regression without user decision

Reference Files

FileWhen to Load
understand-phase.mdPhase 1 start
execute-phase.mdPhase 2 start
state-schema.mdSession resume or state questions
plan.md templateWriting the plan
task.md templateWriting individual task files

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 Project Surgeon Lite AI skill do?

Lightweight project takeover skill: 2-phase runtime (Understand → Execute) for analyzing and improving existing codebases. Optimized for smaller models.

Why use Project Surgeon Lite on TypingMind?

Because you install it once and use it with any model. Project Surgeon Lite 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 Project Surgeon Lite in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/EasyCode-Obsidian/workflow-architect/tree/main/claude/skills/project-surgeon-lite. 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 Project Surgeon Lite?

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 Project Surgeon Lite?

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

Is the Project Surgeon Lite AI skill free?

It is published on GitHub by EasyCode-Obsidian. 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.

View all

Set up your own AI workspace now

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