TypingMindTypingMindThe best frontend for AI
Incremental Change Cycle logo

Incremental Change Cycle

Community
zhuangwenhui
incremental-change-cycle

Use when the user explicitly asks to run the incremental change cycle after adding code or changing function behavior, especially for long-running or high-token work where checklist continuity and repeated review checkpoints matter.

Overview

Publisherzhuangwenhui
RepositoryCodingSkills
Skill nameincremental-change-cycle
Stars
83
Forks
0
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Incremental Change Cycle 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/zhuangwenhui/CodingSkills/tree/main/incremental-change-cycle
  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/zhuangwenhui/CodingSkills.git /tmp/CodingSkills
mkdir -p .claude/skills
cp -r /tmp/CodingSkills/incremental-change-cycle .claude/skills/incremental-change-cycle
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Incremental Change Cycle 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 Incremental Change Cycle 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 Incremental Change Cycle 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.

Incremental Change Cycle

Overview

Run the explicit workflow for incremental code changes: reconcile task state, perform a review checkpoint, run simplify, verify the touched code, and keep every checklist synchronized. This skill is the workflow controller; simplify remains the cleanup pass.

When to Use

Use this skill only when the user explicitly asks for the incremental change cycle or clearly requests the review-checklist-simplify-verify workflow after an incremental edit.

Do not use this skill for:

  • a standalone simplify pass
  • broad feature planning
  • full PR authoring unless the user explicitly asks for PR creation

Role Boundaries

  • review checkpoint checks correctness, scope, regressions, and readiness to continue.
  • simplify performs behavior-preserving cleanup on the changed scope.
  • this skill coordinates the workflow and task-state continuity across those steps.

If the user says PR, interpret it as a review checkpoint unless they clearly mean an actual pull request.

Workflow

  1. Identify the current change scope.
  2. Load the active checklist or create one if none exists.
  3. If multiple checklists exist for the same workflow, reconcile them before continuing.
  4. Mark the current task as in_progress if a checklist supports explicit states.
  5. Run a review checkpoint on the changed scope.
  6. Address any blocking findings from the review checkpoint.
  7. Run simplify on the changed scope.
  8. Run the most relevant verification for the touched code.
  9. Immediately update every relevant checklist after each completed task or checkpoint.
  10. Before stopping, confirm the checklists agree on what is done and what remains.

Checklist Rules

  • Always reuse an existing checklist if it already tracks the current workflow.
  • Keep completed and remaining items explicit.
  • Consult the checklist before starting the next task.
  • Re-check the checklist after interruptions or context compression.
  • Never leave a task completed in one checklist and incomplete in another.

Multiple Checklist Synchronization

If multiple checklists exist for the same workflow:

  1. Treat them as synchronized views of the same task set.
  2. After completing any task, update every relevant checklist before moving on.
  3. If a task is only partially done, do not mark it complete anywhere.
  4. Resolve status mismatches first; do not continue while checklists disagree.
  5. If one checklist is the source of truth, update it first and propagate the same state immediately.

Continuity And Recovery

Because Codex does not provide a public hooks system for this workflow, this skill must perform the continuity checks itself.

Before resuming work after a pause, interruption, or context compression:

  1. Re-read the active checklist or checklists.
  2. Reconstruct the current task, completed tasks, and remaining tasks from those checklists.
  3. Confirm that the current change scope still matches the recorded task state.
  4. Resolve any checklist drift before doing more implementation work.

If state cannot be reconstructed confidently:

  • stop and ask for clarification rather than guessing
  • do not restart already completed work just because context is thin

Stop-Time Guard

Do not conclude the workflow while any of these are still missing for the current incremental change:

  • review checkpoint
  • simplify pass
  • relevant verification
  • checklist synchronization

Before stopping, explicitly confirm:

  1. the current task is actually complete
  2. review checkpoint has been performed
  3. simplify has been run on the changed scope
  4. verification has been run or its absence has been stated
  5. all relevant checklists reflect the same state

Review Checkpoint

The review checkpoint should answer:

  • did the change implement the intended scope?
  • is the behavior correct?
  • are there regressions or obvious risk gaps?
  • is the current task actually complete?
  • do the checklists match the real execution state?

Use a local review pass by default. Only escalate to an actual pull request flow if the user asked for it.

Common Mistakes

  • treating simplify as a substitute for review checkpoint
  • generating a fresh checklist when a valid one already exists
  • forgetting to sync multiple checklists after finishing a task
  • using PR to mean actual PR creation when the user only wanted a review gate
  • stopping after code changes without a review checkpoint, simplify pass, and verification
  • resuming after interruption without re-reading the checklist state
  • trusting memory over checklist state when the two disagree

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 Incremental Change Cycle AI skill do?

Use when the user explicitly asks to run the incremental change cycle after adding code or changing function behavior, especially for long-running or high-token work where checklist continuity and repeated review checkpoints matter.

Why use Incremental Change Cycle on TypingMind?

Because you install it once and use it with any model. Incremental Change Cycle 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 Incremental Change Cycle in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhuangwenhui/CodingSkills/tree/main/incremental-change-cycle. 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 Incremental Change Cycle?

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 Incremental Change Cycle?

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

Is the Incremental Change Cycle AI skill free?

Yes. It is published on GitHub by zhuangwenhui 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.

Related AI Skills

View all
affaan-m logo

Content Engine

affaan-m
CommunityPopular

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

40.4K
270.2K
1 files
View
affaan-m logo

Crosspost

affaan-m
CommunityPopular

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user…

40.4K
270.2K
1 files
View
affaan-m logo

Deep Research

affaan-m
CommunityPopular

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

40.4K
270.2K
1 files
View
affaan-m logo

Documentation Lookup

affaan-m
CommunityPopular

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React,…

40.4K
270.2K
1 files
View

Set up your own AI workspace now

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