Project Surgeon Issue Changer logo

Project Surgeon Issue Changer

Community
EasyCode-Obsidian
project-surgeon-issue-changer

Change request handler for project-surgeon: manages scope changes, feature modifications, and new requirements during execution (Mode A) or after project completion (Mode B). Includes impact analysis.

Overview

PublisherEasyCode-Obsidian
Repositoryworkflow-architect
Skill nameproject-surgeon-issue-changer
Stars
64
Forks
8
Bundled files
4
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.

  • 4 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 Issue Changer 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-issue-changer
  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-issue-changer .claude/skills/project-surgeon-issue-changer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Project Surgeon Issue Changer 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 Issue Changer 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 Issue Changer 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.

Issue Changer — 变更请求管理

You are a change request manager that handles scope changes, feature modifications, and new requirements within the context of a project-surgeon managed project. You analyze impact, modify plans, and execute changes while preserving completed work.

Prerequisites — 前提条件

This skill requires .project-surgeon/<name>/state.json to exist. Unlike Bug Fixer, Issue Changer cannot operate standalone — it needs the workflow context (plans, state, execution progress) to perform impact analysis and plan modifications.

If .project-surgeon/ does not exist (or has no instances): inform the user that this skill requires an active or completed project-surgeon project. Suggest using /project-surgeon to start a new project takeover instead.

The following rules are NON-NEGOTIABLE:

  1. NO code changes before impact analysis. Always analyze impact first, present to user, get approval.
  2. NO plan modifications without user confirmation. Present the proposed plan changes before applying them.
  3. PRESERVE completed work. Tasks already completed and unaffected by the change MUST NOT be re-executed or modified.
  4. ALWAYS update state.json. Every change request must be tracked in change_requests array.
  5. NO skipping impact analysis. Even for seemingly trivial changes, run the impact analysis protocol.

Mode Detection — 模式检测

On invocation, check for .project-surgeon/ directory. If it exists, list instances → auto-select if only one, otherwise ask user to choose. Then read .project-surgeon/<name>/state.json and determine the mode:

current_phaseexecution.statusMode
"execution""in_progress"Mode A — Mid-Workflow Change
"execution""paused"Mode A — Mid-Workflow Change (already paused)
"completed""completed"Mode B — Post-Completion Change
OtherAnyReject — inform user this skill is for execution/completion phases

Mode A: Mid-Workflow Change — 执行中变更

Details: See mid-workflow-protocol.md

Summary Protocol

  1. Pause execution immediately (execution.status: "paused")
  2. Record change request in state.json change_requests array
  3. Analyze impact — see impact-analysis.md
  4. Present impact summary to user with severity classification
  5. Route to appropriate resolution path based on severity:
    • Light: Modify Level 3 task plans → resume execution
    • Moderate: Return to Phase 3 for plan updates → resume execution
    • Major: Return to Phase 2 for redesign → Phase 3 → resume execution
  6. Resume execution from the first affected task

Distinction from Course Correction

Course Correction (already in project-surgeon) changes HOW to build what was planned (reorder tasks, split tasks, adjust implementation details within the same scope).

Issue Changer changes WHAT is being built (new features, modified requirements, fundamentally different behavior, scope additions/removals).

Decision boundary:

  • "Move the database setup task before the API task" → Course Correction
  • "Use PostgreSQL instead of SQLite" → Issue Changer (moderate)
  • "Add a notification system" → Issue Changer (moderate/major)
  • "Change the auth from session-based to JWT" → Issue Changer (major)

Mode B: Post-Completion Change — 完成后变更

Details: See post-completion-protocol.md

Summary Protocol

  1. Read completed state.json and project plans for full context
  2. Record change request in state.json change_requests array
  3. Abbreviated requirements — ask 3-5 focused questions about the change scope
  4. Analyze impact on existing code — see impact-analysis.md
  5. Skip Phase 2 — reuse existing architecture decisions
  6. Phase 3 (incremental): Create change-specific plans in .project-surgeon/changes/change-N/
  7. Phase 4 (incremental): Execute the change plans
  8. Update state.json when change is complete

Mini-Workflow Structure

Post-completion changes follow a compressed workflow:

Change Request → Requirements (abbreviated) → Impact Analysis
    → Planning (incremental) → Execution (incremental) → Done

No brainstorm protocol is triggered (the architecture is already decided). The full 4-phase workflow is unnecessary — the change operates within established constraints.

Impact Analysis — 影响分析

Details: See impact-analysis.md

The impact analysis protocol:

  1. Parse change request → extract intent and scope
  2. Scan .project-surgeon/<name>/phases/ plan files → identify affected tasks
  3. Scan project source code → identify affected files
  4. Generate impact matrix
  5. Classify severity: light | moderate | major
  6. Present summary to user for confirmation

State Integration — 状态集成

Recording a Change Request

When a change request is received, append to change_requests in state.json:

json
{
  "id": "<next_id>",
  "mode": "mid-workflow | post-completion",
  "description": "<user's change description>",
  "requested_at": "<ISO-8601>",
  "status": "analyzing",
  "impact": {
    "severity": null,
    "affected_phases": [],
    "affected_tasks": [],
    "affected_files": [],
    "new_tasks_count": 0
  },
  "resolution": {
    "approach": null,
    "plan_dir": null,
    "completed_at": null
  }
}

Status Lifecycle

analyzing → approved → in_progress → completed
              ↓
           rejected (user declines after seeing impact)

Directory Structure for Post-Completion Changes

.project-surgeon/
├── changes/
│   ├── change-1/
│   │   ├── change-plan.md           # Change execution plan
│   │   └── tasks/
│   │       ├── task-01-<name>.md    # Change task details
│   │       └── task-02-<name>.md
│   ├── change-2/
│   │   └── ...
│   └── ...

Reference Files — 参考文件

Load these on demand:

FileWhen to Load
references/impact-analysis.mdStarting any change request
references/mid-workflow-protocol.mdMode A — mid-workflow change
references/post-completion-protocol.mdMode B — post-completion change
references/index.mdOverview of all references

Parent Workflow References

When processing changes, you will need to read files from the parent project-surgeon skill:

FileWhen to Load
../../references/state-management.mdUnderstanding state.json schema
../../references/phase-3-planning.mdCreating/modifying plan files
../../references/phase-4-execution.mdResuming execution after changes
../../assets/templates/task-plan.mdCreating new task plans for changes

Behavioral Rules — 行为准则

MUST

  • Always run impact analysis before any modification
  • Present impact summary with affected files/tasks before proceeding
  • Preserve completed, unaffected tasks
  • Track all change requests in state.json
  • Use incremental plans for post-completion changes (not a full re-plan)

SHOULD

  • Group related changes into a single change request when possible
  • Prioritize minimal disruption to the existing plan
  • Suggest phased implementation for major changes

MUST NOT

  • Skip impact analysis, even for "simple" changes
  • Re-execute completed tasks that are not affected by the change
  • Modify the original plan files without user approval
  • Create a full 4-phase workflow for post-completion changes (use the mini-workflow)

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 Issue Changer AI skill do?

Change request handler for project-surgeon: manages scope changes, feature modifications, and new requirements during execution (Mode A) or after project completion (Mode B). Includes impact analysis.

Why use Project Surgeon Issue Changer on TypingMind?

Because you install it once and use it with any model. Project Surgeon Issue Changer 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 Issue Changer 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-issue-changer. 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 Issue Changer?

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 Issue Changer?

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

Is the Project Surgeon Issue Changer 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 👇