Diff Skill for Claude

| Compare two versions of a skill's instructions to detect degradations and complexity increases. Asymmetric check — only regressions count. Additions, clarifications, and strengthenings are not degradations. Compares HEAD → working tree by default. Walks the full reachable file set from SKILL.md via markdown links. Produces a report file under docs/reviews/diff-skill/ and an inline summary.

5k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

147

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/serpro69/claude-toolbox --skill diff-skill

What comes with it

14 136 bytes besides the instruction

diff-process.md

evals/clean-refactor/eval.json

evals/clean-refactor/test-files/after/review-process.md

evals/known-degradation/eval.json

evals/known-degradation/test-files/after/example-process.md

evals/known-degradation/test-files/after/shared-conventions.md

evals/known-degradation/test-files/before/example-process.md

evals/known-degradation/test-files/before/shared-conventions.md

shared-capy-knowledge-protocol.md

The instruction itself

5 sections, as written by the author

Diff Skill Instructions

Goal: Detect whether an edit to a skill's markdown instructions introduced degradations or made the skill harder for an LLM to follow.

Two judgment axes:

Degradation (asymmetric) — load-bearing instruction dropped, constraint weakened, verification step removed, scope narrowed, required output dropped, or reference broken. Content relocated but preserved is neutral.
Complexity — split into _regressions_ (introduced or worsened by the edit, affects verdict) and _pre-existing advisories_ (exist regardless of the edit, surfaced as improvement opportunities, does NOT affect verdict).

Conventions

Read capy knowledge base conventions at shared-capy-knowledge-protocol.md.

Required Outputs

[ ] Report written to docs/reviews/diff-skill/<slug>-<sha-a>-<sha-b>.md
[ ] Inline summary presented (under 10 lines: verdict, finding counts, report path)
[ ] Capy indexed under kk:review-findings if any degradation or complexity regression findings exist (skip on clean results and pre-existing advisories)

Invocation

/kk:diff-skill <skill-name>

Convenience shortcut: resolves klaude-plugin/skills/<skill-name>/SKILL.md. If not found, asks the user for the skill directory path.

Defaults: HEAD (before) → working tree (after). User can specify different refs in the prompt.

Workflow

Mandatory order — load instructions before acting on subject matter. The phases below are strictly sequential. Do not read skill content, build file sets, or produce judgments until you have loaded and internalized the full process file. The only early contact with the target skill is its name and SKILL.md path — enough to validate, not enough to judge.

See diff-process.md for the detailed step-by-step process.

Other skills for the same job

different authors, same section of the catalogue

Receiving Code Review

by ZhanlinCui

×7

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

2k tokens

Requesting Code Review

by ZhanlinCui

×6

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

Comprehensive GitHub code review with AI-powered swarm coordination

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.

2k tokens

How to use it

Copy the folder

Take serpro69/diff-skill from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.