Is the Classify Change skill free?

Yes. The skill itself is free from appleboy/skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Classify Change SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Classify Change?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Classify Change with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Classify Change

Leaf-vs-core decision framework for how much AI/review rigor a code change needs.

by appleboy · appleboy/skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · c395786

Ran a real core-vs-leaf call on a shared-ORM caching change: baseline and skill agreed on 'core', but the skill's structured output added concrete review mechanics (2+ reviewers, PR must mark human-reviewed lines, option to split into a human-led core change + leaf feature change) that the freeform baseline answer never surfaced.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Classify Change does

Walks through 6 diagnostic questions (propagation, change frequency, tech-debt tolerance, examples, failure cost, review intensity) to classify a code change as Leaf Node or Core Code, then outputs a concrete recommended review approach. Triggers on phrasing like 'is this leaf or core', 'should I vibe code this', or before any non-trivial change even if the user didn't ask for classification explicitly.

How to install Classify Change

git clone https://github.com/appleboy/skills
cd skills
mkdir -p ~/.claude/skills
cp -r plugins/classify-change/skills/classify-change ~/.claude/skills/classify-change

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Classify Change

/classify-change Leaf-vs-core decision framework for how much AI/review rigor a code change needs.

It also activates on plain-language prompts like these:

Should I vibe code this or get careful human review?
Is adding caching to our shared ORM base class leaf or core?
How much review rigor does this change actually need?

Frequently asked questions

Is the Classify Change skill free?: Yes. The skill itself is free from appleboy/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Classify Change work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran a real core-vs-leaf call on a shared-ORM caching change: baseline and skill agreed on 'core', but the skill's structured output added concrete review mechanics (2+ reviewers, PR must mark human-reviewed lines, option to split into a human-led core change + leaf feature change) that the freeform baseline answer never surfaced.
What is the Classify Change SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Classify Change?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Classify Change with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.